Market Finder

Market Finder

Market intelligence powered by Nimble Web Search Agents.

User request: $ARGUMENTS

Before running any commands, read references/nimble-playbook.md for Claude Code constraints (no shell state, no &/wait, sub-agent permissions, communication style).

---

Instructions

Step 0: Preflight

Follow the transport selection + standard preflight from references/nimble-playbook.md — pick CLI or MCP at session start, then run the standard preflight calls (date calc, today, profile, memory index) in parallel.

Also simultaneously:

• mkdir -p ~/.nimble/memory/{reports,market-finder/checkpoints}
• Check for existing checkpoints: ls ~/.nimble/memory/market-finder/checkpoints/ 2>/dev/null

From the results:

• CLI missing or API key unset -> references/profile-and-onboarding.md, stop
• Tag all nimble CLI calls: nimble --client-source skill-market-finder <subcommand>. MCP path: not yet supported — see references/nimble-playbook.md for status.
• Profile exists -> note industry keywords if any. Apply smart date windowing from

references/nimble-playbook.md. Market-finder tweak: in quick refresh mode, skip enrichment and only discover new metros.

• No profile -> fine. Market-finder doesn't require onboarding. Proceed to Step 1.

Step 1: Parse Request & Detect Mode

Parse $ARGUMENTS for business type, geography, qualifiers, and mode detection.

Mode detection

Check $ARGUMENTS for a reference list. Read references/audit-mode.md for the full detection signals and parsing rules.

If a reference list is present but intent is ambiguous, ask: "Want me to audit your list against fresh discovery, or use it as a starting point?"

If audit language is detected but no reference list is provided, ask: "You mentioned auditing — please provide your list (Google Sheet URL, CSV file path, or paste inline)." Do not proceed with Audit mode until a reference list is received.

Extract fields

If both type and geography are clear from $ARGUMENTS, confirm briefly and proceed: "Finding dentists in Florida..." (or "Auditing your list against dentists in Florida..." in Audit mode)

If partial or ambiguous, ask one combined question (counts as 1 of max 2 AskUserQuestion prompts):

Use AskUserQuestion with up to 3 questions: 1. Vertical -- "What type of business?" with options: Healthcare, SaaS/Software, Restaurants/Food, Legal/Financial, Auto/Home Services, Other 2. Geography -- "What geography?" (free text or: City, State, Region, Nationwide) 3. Depth -- "Quick scan or comprehensive discovery?"

Skip questions already answered by $ARGUMENTS.

Depth modes (determines how much work each step does):

Step 2: Vertical Detection & Preset Loading

Read references/vertical-presets.md and match the user's business type against preset trigger keywords.

Note which discovery WSAs and enrichment WSAs the preset specifies.

Step 3: Geographic Scoping

Skip this step for SaaS vertical (no geography needed).

Estimate API calls: metros * discovery_wsas * (1 + enrichment_ratio) where enrichment_ratio is ~0.3. Follow the Scaled Execution pattern from references/nimble-playbook.md to choose execution tier (individual / batch / multi-batch / confirmation gate):

Estimated API calls: ~1,560 (50 states x 8 metros x 3 WSAs + enrichment)
This is a nationwide search. Proceed? [Y/n]

Derive a slug for checkpointing: lowercase, hyphenated, includes vertical + geo (e.g., dentists-florida, saas-crm-tools, hvac-nationwide).

Step 4: Check for Existing Checkpoint

Follow the Checkpointing & Resume pattern from references/memory-and-distribution.md.

Check: cat ~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json 2>/dev/null

• Checkpoint found -> offer: "Found previous run ({N} entities from {date}).

Resume and fill gaps, or start fresh?"

• No checkpoint -> proceed to Step 5

Step 5: WSA Discovery & Execution

5a: Discover available WSAs

For each target domain in the selected vertical preset, discover current WSAs:

nimble agent list --search "{domain}" --limit 20

Run these searches simultaneously (one per target domain). From the results: 1. Filter by entity_type (SERP for discovery, PDP/Profile for enrichment) 2. Prefer managed_by: "nimble" over managed_by: "community" 3. If no WSA found for a domain, mark it for nimble search fallback 4. If no WSAs found for ANY domain, fall back entirely to nimble search for all metros

Then validate each discovered WSA's input params:

nimble agent get --template-name {discovered_name}

Cache the discovered WSA names + params for the rest of the run.

5b: Geographic discovery (all except SaaS)

For each metro in the tiling plan, run the discovered WSAs simultaneously:

nimble agent run --agent {maps_wsa} --params '{...validated params...}'

nimble agent run --agent {yelp_wsa} --params '{...validated params...}'

Run tertiary domain WSAs only if the preset includes them AND primary + secondary return < 10 combined unique results for that metro.

Choose execution tier per the Scaled Execution pattern in references/nimble-playbook.md (based on total estimated calls from Step 3).

5c: SaaS discovery (non-geographic)

SaaS skips WSA discovery. Run the two-pass search queries defined in the SaaS preset from references/vertical-presets.md:

• Pass 1 -- Product discovery: G2, Capterra, general, ProductHunt, GitHub
• Pass 2 -- Financial discovery: Crunchbase, funding news, market landscape

Both passes run simultaneously. Pass 2 is critical -- without it, funding and traction data will be missing or wrong.

5d: Fallback

If no WSA was found for a target domain, or if a WSA fails for any metro:

nimble search --query "[type] in [metro]" --max-results 20 --search-depth lite

After discovery: 1. Parse all results into a unified entity list 2. Deduplicate following the Entity Deduplication pattern from references/nimble-playbook.md: place_id -> domain -> fuzzy name + city 3. Track source_count per entity (how many WSAs/sources found it) 4. Save checkpoint: ~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json

Step 6: Enrichment

Run enrichment using the WSAs discovered in Step 5a for the preset's enrichment target domains. Prioritize entities with the highest source count first. Choose execution tier per Scaled Execution in references/nimble-playbook.md.

nimble agent run --agent {enrichment_wsa} --params '{...validated params...}'

Only run enrichment WSAs that apply to the current vertical's enrichment targets (see references/vertical-presets.md). Skip entities without the required ID/URL for the enrichment WSA.

Save checkpoint: ~/.nimble/memory/market-finder/checkpoints/{slug}/enrichment.json

Step 6b: Financial Verification (SaaS vertical)

For SaaS entities, verify funding claims before reporting. Never label a company's funding stage without a source.

For each entity in the top results (top 5 in quick scan, all in comprehensive):

nimble search --query "{company name} funding raised series" --max-results 5 --search-depth lite

• Source found: Use the sourced amount and date
• No source found: Display "Undisclosed" -- never guess "Early stage" or "Bootstrapped"

This step prevents publishing unverified financial claims. It's fast (one search per entity, lite depth) and catches recent funding rounds that directory sites miss.

Step 7: Deduplication & Scoring

Final deduplication: Run a final dedup pass across all phases following the Entity Deduplication pattern from references/nimble-playbook.md. Merge fields from multiple sources into a single record per entity.

Discovery strength scoring (skill-specific, varies by vertical):

Geographic verticals (Healthcare, Restaurants, Legal, Auto/Home, Custom):

SaaS vertical (funding + directory presence matter more than review count):

Display as: *** High, ** Medium, * Low

Step 7b: Audit Comparison (Audit mode only)

Skip this step in Discovery mode.

Read references/audit-mode.md for the full matching algorithm, normalization rules, and output template.

1. Parse reference list — detect format (Google Sheet / CSV / inline), extract records, normalize to {name, domain, city, state, phone} per the parsing rules in references/audit-mode.md 2. Run three matching layers in order (domain → name+city → phone). Once an entity matches at any layer, stop. Track which layer produced the match. 3. Categorize every entity:

• matched — in both reference list and discovery results
• discovered_only — found by discovery, not in reference list
• reference_only — in reference list, not found by discovery

4. Calculate coverage score — matched / reference_count × 100

Proceed to Step 8 with the categorized results.

Step 8: Output

# Market Finder: [Business Type] in [Geography]
*Found [N] businesses | [Date] | Strength: [H] High, [M] Medium, [L] Low*

## Summary
- **Total discovered:** [N] unique businesses across [M] metros
- **Geographic breakdown:** [top 5 metros by count]
- **Source coverage:** [list each source used with entity counts]

## Top Results (High Strength)

| # | Name | Location | Rating | Reviews | Strength | Sources |
|---|------|----------|--------|---------|----------|---------|
| 1 | Acme Dental | Miami, FL | 4.8 | 312 | *** High | Maps, Yelp, BBB |
| 2 | WidgetCo Health | Orlando, FL | 4.6 | 89 | *** High | Maps, Yelp |
...

## All Results by Geography

### Miami, FL ([n] businesses)
[Table of businesses in this metro]

### Orlando, FL ([n] businesses)
[Table of businesses in this metro]
...

## What's Missing
[Data gaps: metros with low coverage, entities without websites, etc.]

SaaS output variant (when vertical is SaaS, replace "All Results by Geography" with tier-based grouping):

## Players by Tier

### Pure-Play (dedicated to this vertical)
| # | Name | Domain | Funding | Key Metric | Strength | Sources |
...

### Adjacent (feature overlap from larger platforms)
| # | Name | Domain | Funding | Key Metric | Strength | Sources |
...

### Open Source
| # | Name | Repo | Stars | Key Metric | Strength | Sources |
...

Source links are mandatory. Every entity must have at least one clickable source URL (Google Maps link, Yelp listing, website, BBB profile, G2 page, or GitHub repo).

Audit output variant (when in Audit mode, replace the Discovery output above): Use the audit output template from references/audit-mode.md. Key sections: Summary with coverage score, Matched table, Discovered Only table (expansion candidates), Reference Only table (coverage gaps), and "What This Means" interpretation.

Step 9: Save to Memory

Make all Write calls simultaneously:

Discovery mode:

• Report -> ~/.nimble/memory/reports/market-finder-{slug}-{date}.md
• Entity data -> ~/.nimble/memory/market-finder/{slug}/entities.json

Audit mode:

• Report -> ~/.nimble/memory/reports/market-finder-audit-{slug}-{date}.md
• Structured data -> ~/.nimble/memory/market-finder/{slug}/audit-{date}.json

(all three categories with match metadata)

Both modes:

• Profile -> update last_runs.market-finder in ~/.nimble/business-profile.json

(only if profile exists)

• Follow the wiki update pattern from references/memory-and-distribution.md: update

index.md rows for all affected entity files, append a log.md entry for this run.

• Clean up checkpoint (complete run) or keep (partial run)

Step 10: Share & Distribute

Always offer distribution -- do not skip this step. Follow references/memory-and-distribution.md for connector detection, sharing flow, and source links enforcement.

Notion: full results table as a dated subpage. Slack: TL;DR with total count + top 10 entities only.

Step 11: Follow-ups

Discovery mode follow-ups:

• "Tell me more about #N" -> show full detail for that entity
• "Filter by [criteria]" -> re-filter existing results
• "Expand to [new geography]" -> add metros and re-run discovery
• "Export as CSV" -> generate CSV from entities.json
• "Run enrichment on all" -> extend enrichment beyond top entities
• "Audit against my existing list" -> switch to Audit mode with this run's results
• "Looks good" -> done

Audit mode follow-ups:

• "Export discovered-only as CSV for outreach?" -> CSV of expansion candidates
• "Investigate reference-only gaps?" -> targeted searches for reference_only entries
• "Run company-deep-dive on new discoveries?" -> deep research on discovered_only
• "Re-run with a different geography?" -> audit the same list against a new area
• "Looks good" -> done

Sibling skill suggestions:

Next steps:

- Run company-deep-dive for a full 360 profile on any business from this list

- Run competitor-positioning to compare top players in this market

- Run local-places for neighborhood-level discovery with social enrichment and maps

---

Sub-Agent Strategy

For large jobs, nimble agent run-batch handles WSA parallelism server-side (see Scaled Execution in references/nimble-playbook.md). Sub-agents are useful for preparing batch inputs and processing results, not for running individual WSA calls.

Use nimble-researcher agents (agents/nimble-researcher.md) when:

• Building metro query lists for large geographies (one agent per state)
• Processing and deduplicating batch results in parallel

Follow the sub-agent spawning rules from references/nimble-playbook.md (bypassPermissions, batch max 4, fallback on failure).

---

Agent Teams Mode (Dual-Mode)

Check at startup: echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS

Team mode (flag set): Spawn teammates for parallel phases:

• Discovery teammate(s): Run all discovery WSAs across metro batches
• Enrichment teammate: Run enrichment WSAs for top entities
• Lead (you): Coordinate, scope, deduplicate, score, generate output

Solo mode (flag not set): Standard sequential flow from Steps 5-8.

---

Error Handling

See references/nimble-playbook.md for the standard error table (missing API key, 429, 401, empty results, extraction garbage). Skill-specific errors:

• WSA not found: Skip silently and rely on other discovery sources. Log which

WSAs were unavailable.

• Search 500/timeout: Retry once without --focus flag. If still failing,

retry with a simplified query. Log the failure but don't skip the entire search category -- partial data is better than none.

• No results for metro: "No [type] found in [metro]. Skipping to next metro."

Don't abort the entire job for one empty metro.

• Ambiguous business type: "Did you mean [option A] or [option B]?"

(e.g., "practice" could be medical, dental, legal)

• SaaS with geography: If the selected preset has no geo-tiling but the user

specified a geography, offer it as a search qualifier instead.

• Reference list parse failure: If Google Sheet extraction returns garbage or

CSV is malformed, ask the user to paste the data inline instead.

• Empty reference list: If parsed list has 0 valid records, warn and offer to

switch to Discovery mode.

• No matches found: If all three matching layers produce zero matches, report

it — a 0% coverage score is valid and informative.

Audit Mode

Compares a user's existing business list against market-finder's discovery results, surfacing gaps in both directions. Read this when Audit mode is triggered.

---

When Audit Mode Triggers

Audit mode activates when the user provides a reference list alongside a discovery request. Detection signals (check in Step 1 of SKILL.md):

If the user provides a reference list but no audit intent, ask: "You provided a list. Want me to audit it against fresh discovery, or just use it as a starting point for discovery?"

---

Reference List Parsing

Follow the Input Parsing Pattern from references/nimble-playbook.md to detect format, then normalize to a uniform record list.

Google Sheet URL

nimble extract --url "{sheet_url}" --format markdown

Parse the markdown table. Map columns by header name (case-insensitive):

CSV file

cat -- "{file_path}"

Parse as CSV. Same column mapping as above.

Inline list

Parse each line as a business entry. Try to extract:

• Business name (first segment before any delimiter)
• Location (city/state if present)
• Domain or phone if included

If the inline format is unclear, ask one clarifying question: "What columns does your list have? (e.g., name, city, phone)"

Normalization

After parsing, normalize every record to:

{
  "name": "Acme Dental",
  "domain": "acmedental.com",
  "city": "Miami",
  "state": "FL",
  "phone": "3051234567",
  "raw": "original row as-is for traceability"
}

• Domain: strip http://, https://, www., trailing /
• Phone: strip all non-digits, keep last 10 digits (US) or full international
• Name: trim whitespace, preserve original casing for display
• Missing fields: set to null — matching layers skip null fields

---

Matching Algorithm

Run all three layers in order. Once an entity matches at any layer, stop — don't re-match at lower layers. Track which layer produced each match.

Layer 1: Domain Match (primary)

Compare normalized root domains between reference and discovered entities.

reference: acmedental.com  ↔  discovered: acmedental.com  →  MATCH
reference: acmedental.com  ↔  discovered: acme-dental.com →  NO MATCH

Rules:

• Strip www., protocol, trailing /, path segments
• Compare root domain only (not subdomains)
• Exact match required — no fuzzy domain matching

Skip entities where either side has domain: null.

Layer 2: Name + City Fuzzy Match (secondary)

For unmatched entities after Layer 1, compare business names within the same city.

Normalization: 1. Lowercase both names 2. Remove punctuation: .,'-&!()[] 3. Remove common suffixes: inc, llc, ltd, corp, co, pllc, pa, pc, dds, md, dmd, do, group, associates, and associates 4. Split into word tokens

Matching:

• Both entities must share the same city (case-insensitive, after trimming)
• Calculate word overlap: shared_words / max(words_a, words_b)
• Threshold: 80% word overlap = match

"Acme Dental Associates" in Miami  ↔  "Acme Dental" in Miami
  → tokens: [acme, dental] vs [acme, dental]  → 100% overlap  → MATCH

"Acme Dental" in Miami  ↔  "Acme Health" in Miami
  → tokens: [acme, dental] vs [acme, health]  → 50% overlap  → NO MATCH

Skip entities where either side has city: null.

Layer 3: Phone Match (tertiary)

For still-unmatched entities, compare normalized phone numbers.

Normalization: Strip all non-digit characters, keep last 10 digits.

reference: (305) 123-4567  →  3051234567
discovered: 305-123-4567   →  3051234567  →  MATCH

Skip entities where either side has phone: null.

---

Categorization

After all three matching layers complete:

---

Output Template

# Market Finder Audit: [Business Type] in [Geography]
*Audited [R] reference entries against [D] discovered businesses | [Date]*

## TL;DR
[M/R × 100]% coverage — [M] of [R] reference entries verified, [DO] new businesses
discovered, [RO] in your list but not found by discovery.

## Summary
- **Reference list:** [R] entries
- **Discovered:** [D] businesses
- **Matched:** [M] ([M/R]% of reference list verified)
- **Discovered only:** [DO] expansion candidates
- **Reference only:** [RO] coverage gaps

## Coverage Score
**[M/R × 100]% of your reference list was independently verified by market discovery.**

## Matched ([M])
Confirmed in both your list and fresh discovery.

| # | Name | Location | Match Layer | Discovery Strength | Sources |
|---|------|----------|-------------|-------------------|---------|
| 1 | Acme Dental | Miami, FL | Domain | *** High | Maps, Yelp |
...

## Discovered Only ([DO]) — Expansion Candidates
Found by market-finder but missing from your reference list.

| # | Name | Location | Domain | Rating | Strength | Sources |
|---|------|----------|--------|--------|----------|---------|
| 1 | WidgetCo Health | Orlando, FL | widgetco.com | 4.6 | ** Medium | Maps |
...

## Reference Only ([RO]) — Coverage Gaps
In your list but not found by market discovery. Possible reasons: closed, relocated,
rebranded, niche/unlisted, or discovery source limitations.

| # | Name | Location | Domain | Phone | Possible Reason |
|---|------|----------|--------|-------|----------------|
| 1 | Old Practice | Tampa, FL | — | (813) 555-0100 | Not found in any source |
...

## What This Means
[1-3 sentences interpreting the audit results — e.g., coverage percentage,
geographic clusters in discovered_only, notable reference_only entries]

---

Memory

Save audit results to:

• Report: ~/.nimble/memory/reports/market-finder-audit-{slug}-{date}.md
• Structured data: ~/.nimble/memory/market-finder/{slug}/audit-{date}.json

The JSON includes all three categories with match metadata (which layer matched, confidence) for downstream use.

---

Follow-ups (Audit-specific)

After presenting audit results, offer:

• "Export discovered-only as CSV for outreach?" — generate a CSV of expansion candidates
• "Investigate reference-only gaps?" — run targeted searches for reference_only

entities to determine if they've closed, moved, or rebranded

• "Run company-deep-dive on new discoveries?" — deep research on high-strength

discovered_only entities

• "Re-run with a different geography?" — audit the same list against a broader

or narrower area

Memory & Distribution

How skills persist knowledge across sessions and distribute reports to external tools.

---

Memory Architecture

All persistence lives under ~/.nimble/ — never touch user project files.

~/.nimble/
├── business-profile.json          # Tier 1: Hot cache (see profile-and-onboarding.md)
└── memory/                        # Tier 2: Deep storage (loaded on demand)
    ├── index.md                   # Global index (one line per directory)
    ├── log.md                     # Chronological activity log (append-only)
    ├── backlog.md                 # Research questions and knowledge gaps
    ├── synthesis/                 # Cross-entity analysis pages
    ├── competitors/               # Accumulated intel per competitor
    │   └── index.md              # Per-directory entity catalog
    ├── people/                    # Contact profiles for meeting prep
    │   └── index.md
    ├── companies/                 # Deep-dive research results
    │   └── index.md
    ├── reports/                   # Timestamped full skill outputs
    ├── positioning/               # Per-competitor positioning snapshots
    │   └── index.md
    └── glossary.md                # Industry terms and jargon

Tier 1 (business-profile.json) — loaded every session. See references/profile-and-onboarding.md for the full schema and update patterns.

Tier 2 (memory/) — loaded on demand when a skill needs deeper context.

Wiki Primitives

The memory directory includes wiki-level files that make the knowledge base navigable, queryable, and self-maintaining:

~/.nimble/memory/
├── index.md                       # Global summary (one line per directory)
├── log.md                         # Chronological activity log (append-only)
├── backlog.md                     # Research questions and knowledge gaps
├── synthesis/                     # Cross-entity analysis pages
│   ├── index.md                   # Per-directory catalog (same format as others)
│   └── competitive-landscape.md   # (created dynamically when patterns emerge)
├── competitors/
│   ├── index.md                   # Per-directory entity catalog
│   ├── widgetco.md
│   └── gizmotech.md
├── people/
│   ├── index.md
│   └── alex-kim.md
├── companies/
│   ├── index.md
│   └── ...
├── reports/
├── positioning/
│   ├── index.md
│   └── ...
└── glossary.md

Skills create index files, log.md, and synthesis/ on first write if missing.

---

Wiki Content Index (Two-Tier)

Indexes live at two levels: a lightweight global index for cross-directory navigation, and per-directory indexes for detailed entity catalogs.

Global Index (~/.nimble/memory/index.md)

One line per directory — entity count and last-updated date. Never lists individual entities. Stays under 30 lines forever.

# Knowledge Index

| Directory | Entities | Last Updated |
|-----------|----------|-------------|
| [[competitors/index]] | 5 | 2026-03-20 |
| [[people/index]] | 3 | 2026-03-15 |
| [[companies/index]] | 8 | 2026-03-18 |
| [[positioning/index]] | 5 | 2026-03-20 |
| [[synthesis/index]] | 2 | 2026-03-20 |

Per-Directory Index ({dir}/index.md)

One row per entity file with summary and last-updated date. Owned by the skills that write to that directory. Scales independently — each directory can grow without affecting other indexes.

# Competitors Index

| File | Summary | Updated |
|------|---------|---------|
| [[competitors/widgetco]] | Enterprise SaaS competitor, Series C | 2026-03-20 |
| [[competitors/gizmotech]] | API-first competitor, growing fast | 2026-03-20 |

Rules

• Skills read only their directory's index in preflight. competitor-intel reads

competitors/index.md; meeting-prep reads people/index.md. Cross-directory lookups go through the global index first, then the relevant directory index.

• Skills update only their directory's index on write. When a skill creates or

updates an entity file, update the row in that directory's index. Use the entity file's first # Heading as the summary if none exists.

• Global index is updated after directory index changes. Bump the entity count

and last-updated date for the affected directory.

• Created on first skill run if missing. Skills should not fail if an index

doesn't exist — create it with whatever entities are written in that run.

• Obsidian-compatible. [[path/entity]] links (without .md extension) work as

wiki links in Obsidian. Path is relative to ~/.nimble/memory/.

---

Chronological Wiki Log (log.md)

~/.nimble/memory/log.md is an append-only timestamped record of skill runs and findings. Grep-friendly format for answering "what did I learn this week?"

# Activity Log

## [2026-03-15] meeting-prep
- Updated: [[people/alex-kim]], [[companies/widgetco]]
- Key findings:
  - Alex Kim moved to VP Engineering role
  - Interested in API performance benchmarks

## [2026-03-18] company-deep-dive
- Created: [[companies/target-corp]]
- Key findings:
  - Series B closed at $30M, Sep 2025
  - Expanding into EU market Q2 2026

## [2026-03-20] competitor-intel
- Created: [[competitors/widgetco]], [[competitors/gizmotech]]
- Updated: [[competitors/acme-rival]]
- Key findings:
  - WidgetCo launched enterprise tier pricing
  - GizmoTech hired new CTO from CloudCorp

Rules

• Append at the end of the file (oldest first, newest last). Normal writes are

pure appends — no read-insert-rewrite needed. LLMs read the whole file; humans use grep "^## \[" log.md | tail -10 for recent entries.

• Format: ## [YYYY-MM-DD] skill-name — enables grep "^## \[" log.md | tail -10.
• Content: List entities created/updated (as [[path/entity]] links), then 2-3

bullet points of key findings. Keep entries concise — this is a log, not a report.

• Rotate entries older than 90 days as a separate maintenance step. After

appending the new entry, check the oldest entries (at the top). If older than 90 days, remove them. This rotation is not part of the normal append — it's a periodic cleanup that triggers during writes. The full reports in reports/ are the permanent record; log.md is for recent activity scanning.

• Created on first skill run if missing.

---

Cross-Entity References

Entity files use Obsidian-compatible [[path/entity]] wiki links to connect related entities across directories.

Format

# Alex Kim

## Current Role
VP of Engineering at [[competitors/widgetco]] (since 2024)

## Related
- Employer: [[competitors/widgetco]]
- Previous: [[companies/cloudcorp]]

# WidgetCo

## Key People
- [[people/alex-kim]] — VP Engineering
- [[people/jane-smith]] — CEO

## Related Competitors
- [[competitors/gizmotech]] — overlapping market segment

Rules

• Link format: [[directory/entity-slug]] — no .md extension, path relative

to ~/.nimble/memory/. Obsidian resolves these as wiki links.

• Add cross-references when relationships are discovered. When a skill finds

that a person works at a tracked company, or two competitors share a market segment, add links in both directions.

• Handle missing targets gracefully. A cross-reference to a file that doesn't

exist yet is fine — it becomes a valid link once that entity is created. Skills should not fail on dangling links.

• Skills follow links to enrich output. When meeting-prep finds

[[competitors/widgetco]] in a person's file, it loads that competitor file for additional context. When competitor-intel finds [[people/alex-kim]] in a competitor file, it can surface that relationship in the briefing.

When to Add Cross-References

---

Ad-Hoc Insights

When a user signals "save this", "remember that", "note this down", or similar intent during a conversation, file the insight into the relevant entity file(s) instead of letting it vanish into chat history.

Filing Pattern

1. Identify the relevant entity file(s). If the insight is about a competitor, file it in competitors/{name}.md. If it spans multiple entities (e.g., "WidgetCo is partnering with GizmoTech"), update all relevant files. 2. Append under a dated `## Insights` section:

## Insights
### 2026-03-22
- User noted: WidgetCo's enterprise pricing is 2x ours — [[competitors/gizmotech]]
  is closer to our price point [ad-hoc]

3. Add cross-references if the insight connects entities (as shown above). 4. Update the directory's `index.md` — bump the last-updated date for the affected file(s), and update the global index.md counts. 5. Append to `log.md` (at the end of the file):

## [2026-03-22] ad-hoc-insight
- Updated: [[competitors/widgetco]], [[competitors/gizmotech]]
- Key findings:
  - WidgetCo enterprise pricing is 2x user's, GizmoTech closer to parity

Rules

• Tag with `[ad-hoc]` so skills can distinguish user-contributed insights from

skill-generated findings during dedup.

• Multi-entity insights update all relevant files with cross-references between

them.

• Don't create entity files for throwaway comments. If the user says "remember

that meetings on Fridays are bad", that's a preference (update business-profile.json), not an entity insight.

---

Cross-Entity Synthesis Pages

~/.nimble/memory/synthesis/ contains pages that analyze patterns across multiple entity files. Unlike entity files (which accumulate facts about one entity), synthesis pages draw conclusions across the knowledge base.

Page Creation

Synthesis pages are created dynamically when patterns emerge across entities — not from a pre-defined list. Common examples:

Page names should be slug-formatted topic labels (not skill names). Skills create synthesis pages when a pattern recurs across 3+ entities — this keeps synthesis data-driven rather than speculative.

Format

Synthesis pages use YAML frontmatter to track which entity files they were built from and when. This makes staleness deterministic — compare current file timestamps against the recorded ones.

---
confidence: high
sources:
  - path: competitors/widgetco.md
    updated: 2026-03-20
  - path: competitors/gizmotech.md
    updated: 2026-03-20
  - path: competitors/acme-rival.md
    updated: 2026-03-18
generated_by: competitor-intel
generated_at: 2026-03-20
---
# Competitive Landscape

## Market Map
[Positioning of each competitor by segment, size, strategy]

## Feature Comparison
| Capability | Us | [[competitors/widgetco]] | [[competitors/gizmotech]] |
|---|---|---|---|
| Real-time data | ✅ | ❌ | Partial |

## Pricing Comparison
[Tier-by-tier comparison where known]

## Key Patterns
- Trend 1 with evidence from multiple competitors
- Trend 2 with cross-entity citations

## What This Means
[Strategic implications — what the patterns suggest for the user's company]

Rules

• Cite source entity files with [[path/entity]] links. Every claim must trace

back to an entity file.

• Track sources and confidence in frontmatter. confidence: high|medium|low

reflects data completeness (high = all key sources available, low = sparse data). The sources: block lists every entity file used and its last-modified date at generation time. To check staleness, compare current file timestamps against the recorded ones — if any source was updated since generation, the page is stale.

• Refresh when sources are stale. If a skill adds major new signals to 2+ source

entities since the synthesis was generated, regenerate. Don't regenerate on every run — only when the source timestamps diverge.

• Use `nimble-analyst` agent for synthesis generation. The analyst has the right

model (Sonnet) for cross-entity pattern recognition and strategic analysis.

Generation Trigger

competitor-intel generates competitive-landscape.md when:

• 3+ competitors have been researched in the current run, OR
• The existing synthesis page's source timestamps are stale (source entities were

updated since generation)

Other synthesis pages are created by the relevant skills when patterns emerge, or on user request.

---

Research Backlog (backlog.md)

~/.nimble/memory/backlog.md tracks knowledge gaps and research questions — things to investigate in future skill runs. This is not synthesis (derived, read-only output) — it's imperative (drives future action).

# Research Backlog

## Open
- [ ] WidgetCo pricing for enterprise tier — couldn't find public pricing [2026-03-20, competitor-intel]
- [ ] GizmoTech Series B details — rumored but unconfirmed [2026-03-20, competitor-intel]
- [ ] Alex Kim's LinkedIn activity — profile was private [2026-03-15, meeting-prep]

## Resolved
- [x] WidgetCo new CTO name — confirmed: Sarah Chen [2026-03-22, competitor-intel]

Rules

• Any skill can append questions to the ## Open section when it encounters

gaps during research. Tag each with date and skill name.

• Users can add questions via ad-hoc insights ("find out about X next time").
• Skills check backlog before running to avoid re-researching resolved questions

and to prioritize open ones relevant to the current run.

• Resolved questions get moved to ## Resolved with a resolution date — not

deleted. This preserves the audit trail.

---

Deep Storage Formats

competitors/

One file per competitor. Append new findings under dated headers — never overwrite.

# WidgetCo

## Key Facts
- Domain: widgetco.com
- HQ: San Francisco
- Funding: Series C ($45M, Jan 2026)
- CEO: Jane Smith

## Signals
### 2026-03-20
- Launched new enterprise tier pricing — [source URL]
- Hired VP of Sales from CRMHub — [source URL]

### 2026-03-13
- Announced partnership with AWS — [source URL]

people/

One file per contact. Used by meeting-prep skill.

# Alex Kim

## Current Role
VP of Engineering at WidgetCo (since 2024)

## Background
- Previously: Senior Director at CloudCorp (2019-2024)
- Education: MS Computer Science, top-10 program

## Notes from Previous Meetings
### 2026-03-15
- Interested in our API performance benchmarks
- Prefers technical depth over high-level summaries

companies/

Detailed company profiles from deep-dive research.

# Target Corp

## Overview
- Industry: Enterprise SaaS | Founded: 2015 | HQ: Austin, TX | ~500 employees

## Financials
- Last funding: Series B ($30M, Sep 2025) | Revenue: Est. $40M ARR

## Recent News
(dated entries, same format as competitors/)

reports/

Timestamped full skill outputs. Save the complete briefing, not a summary.

Naming: {skill-name}-{YYYY-MM-DD}.md — if a skill may produce multiple reports per day (e.g., meeting-prep for different companies), add a qualifier: {skill-name}-{qualifier}-{YYYY-MM-DD}.md. The qualifier is defined in each skill's SKILL.md (e.g., company slug for meeting-prep).

glossary.md

Industry terms and jargon. Updated when the user uses unfamiliar terms.

Bootstrapping (First Run)

mkdir -p ~/.nimble/memory/{competitors,people,companies,reports,positioning,synthesis}

Create stub files for each competitor from the onboarding flow.

index.md and log.md are created automatically on the first skill run that writes to memory — no need to create empty stubs during bootstrapping.

Differential Analysis

The key feature across all skills — only surface what's genuinely new.

Dedup Lifecycle

Memory loading happens at two points in every skill:

1. Step 0 (Preflight): Load relevant memory files for context. This tells the skill what's already known so it can pass known signals to sub-agents for dedup during research. For example, competitor-intel loads ~/.nimble/memory/competitors/*.md; meeting-prep loads ~/.nimble/memory/people/*.md.

2. Analysis step (before report generation): Final dedup check. Compare all findings from research against loaded memory. Only signals classified as NEW or UPDATED (per the freshness classification in nimble-playbook.md) make it into the report.

What "new" means

• "WidgetCo raised a Series C" is noise if already in memory
• "WidgetCo just hired a new CTO" is a new signal worth highlighting
• "WidgetCo raised a Series C" with a new detail (amount, lead investor) is an UPDATE

Learning from Corrections

When the user corrects the skill, update both tiers:

Always confirm the update to the user.

Checkpointing & Resume

For multi-phase pipelines (map → extract → enrich → score), save intermediate results so failed or interrupted runs can resume without re-doing completed work.

Storage

~/.nimble/memory/{skill-name}/checkpoints/{slug}/
├── map.json           # Phase 1 output
├── extract.json       # Phase 2 output
└── enrich.json        # Phase 3 output

{slug} is a stable identifier derived from the run's input parameters (e.g., URL domain, search query hash). Same input = same slug = resumable.

Checkpoint format

Each phase file is JSON:

{
  "phase": "extract",
  "status": "complete",
  "timestamp": "2026-04-03T15:30:00Z",
  "record_count": 47,
  "data": [ ... ]
}

status is "complete" or "partial" (interrupted mid-phase).

Resume logic

On re-run with the same parameters: 1. Detect existing checkpoint directory for the slug 2. Offer: "Found previous run (47 records from Apr 3). Resume and fill gaps, or start fresh?" 3. If resume: skip phases where status = "complete", re-run where status = "partial" or file is missing 4. If start fresh: delete the checkpoint directory and begin from phase 1

Rules

• One checkpoint directory per unique run (keyed by slug)
• Clean up checkpoints older than 30 days on skill startup
• Don't checkpoint trivial runs (< 5 records) — the overhead isn't worth it

Rules

• Never touch user project files. All persistence under ~/.nimble/.
• Append, don't overwrite. Deep storage grows over time with dated sections.
• Read on demand. Only load files when the skill actually needs them.
• Update profile after every run. At minimum, last_runs timestamp.
• Update wiki files after every memory write. Update the directory's index.md

for affected entities, bump the global index.md counts, append a log.md entry for the run, and add cross-references where relationships are discovered.

• Handle missing gracefully. If a file doesn't exist, create it. This includes

index files, log.md, backlog.md, and cross-reference targets.

---

Source Links Enforcement

Every signal in every report must include a clickable source URL. This is a hard requirement — reports without source links are incomplete and must not be distributed.

What counts as a source link:

• A direct URL to the article, press release, or page where the signal was found
• The URL returned by nimble search in the result's url field
• For extracted content, the URL passed to nimble extract --url

What does NOT count:

• A company's homepage (unless the signal is specifically about homepage content)
• A generic domain without a path (e.g., https://widgetco.com)
• "Source: web search" or any non-clickable attribution

If a signal has no source URL after research and extraction, drop it from the report. An unsourced signal is worse than a missing one — it can't be verified and erodes trust.

---

Report Distribution

After presenting output, offer sharing based on available MCP connectors.

Connector Detection

Check before presenting options:

• Notion: mcp__plugin_Notion_notion__notion-create-pages
• Slack: Any Slack MCP tool

Sharing Flow

Use AskUserQuestion with only the available options:

Share this report?

- Save to Notion — full report as a page

- Send to Slack — TL;DR to a channel

- Both

- Skip

Notion: Create a dated subpage. If integrations.notion.reports_page_id exists in the profile, use it as parent. Otherwise ask and save the ID for next time.

Slack: Post TL;DR only — Slack is for alerts, not full reports. If integrations.slack.channel exists, use it. Otherwise ask and save.

Neither available (first run only):

Tip: If you connect a Notion or Slack MCP server, I can save reports or post

TL;DRs to your team automatically.

Don't repeat this tip on subsequent runs.

Nimble Playbook

How to run Nimble CLI commands in Claude Code. Read this before executing any commands.

---

Claude Code Execution Rules

• No shell state persistence. Variables set in one Bash call are gone in the next.

Inline all values (dates, paths, names) directly into every command.

• No `&` + `wait` parallelism. It breaks in Claude Code. Instead, make **multiple

Bash tool calls in a single response** — they run in parallel natively.

• Search returns JSON — --output-format doesn't change this. With `--search-depth

lite`, the JSON is small (title, description, URL per result). Parse it directly.

• Extract returns JSON with `data.markdown` — use --format markdown to get clean

content in the data.markdown field.

Preflight Pattern

Transport selection (run once per session)

Skills work via two transports — CLI (preferred, full surface area) or MCP (fallback, curated tool set covering the same operations). Pick one at the start of every session and stick with it; don't re-probe on every command.

Connector not connected (Cowork / claude.ai) — verify BEFORE working

In Cowork / claude.ai the plugin is often installed while its connector is not yet connected, so live data calls fail. Confirming the connection is a required preflight step — not an error to react to mid-task. When mcp__plugin_nimble_nimble__* tools are listed but you haven't confirmed the connector is live, run one read-only probe before any real work:

• A single nimble_agents_list call is the cheapest confirmation. Success →

connected, proceed. Auth / not-connected error, or a response containing an OAuth authorization URL → not connected.

When not connected, surface this verbatim and stop — do not fall back to WebFetch, WebSearch, curl, or any other tool, and do not guess at data:

Your Nimble plugin is installed, but its connector isn't connected yet — that's

why I can't fetch live data. To connect it:

>

1. Open Customize → Connectors

2. Find Nimble and click Connect

3. Complete the login in your browser. No Nimble account? You can create one

right there during login.

4. Once it shows Connected, re-run your request and I'll continue.

If a tool hands back an OAuth "Authorize" URL

A not-connected tool call may return an authorization link (e.g. "Authorize Nimble MCP →") instead of data. Present that link to the user exactly as given, then stop and wait. Hard rules:

• Never invent a completion flow. There is no "paste the URL from your address

bar back to me" step, and you cannot "complete the connection" yourself. Claiming either is a hallucination.

• Never say the tools "will activate" and then call them in the same turn. Wait

for the user to confirm they've authorized, then retry.

• To check whether authorization succeeded, run one read-only nimble_agents_list

probe — don't assume.

No plugin and no CLI

If neither path works at all (no plugin installed, no CLI installed), surface this hint verbatim and stop:

Nimble isn't installed. Pick the path for your environment:

>

Any Claude product (Claude Code, Claude Cowork, claude.ai) — recommended:

```

/plugin install nimble

```

Installs the Nimble plugin. The .mcp.json inside the plugin auto-registers as a Connector in Customize → Connectors. First tool call triggers the OAuth flow — no API key needed.

>

Codex CLI or other terminal agents (shell access, no `/plugin`):

```

npm i -g @nimble-way/nimble-cli

```

Then export NIMBLE_API_KEY=<key> and re-run. See references/profile-and-onboarding.md for the full install flow.

>

Cursor, VS Code, or any other MCP client:

Paste this into your MCP settings (.cursor/mcp.json or host equivalent):

```json

{

"mcpServers": {

"nimble": { "type": "http", "url": "https://mcp.nimbleway.com/mcp" }

}

}

```

The plugin path (/plugin install nimble) is the easiest onboarding everywhere it works — one command, OAuth handles auth, no API key to manage. Use the CLI path only when shell access is available but /plugin install isn't (Codex, raw terminal agents). Use the manual mcp.json path only for MCP clients outside the Claude family.

Standard preflight (run in parallel after transport is selected)

Every skill kicks off with these simultaneous calls:

• python3 -c "from datetime import datetime, timedelta; print((datetime.now() - timedelta(days=14)).strftime('%Y-%m-%d'))" (14 days ago)
• date +%Y-%m-%d (today)
• cat ~/.nimble/business-profile.json 2>/dev/null (profile — fall back to MCP filesystem tool if shell unavailable)
• cat ~/.nimble/memory/index.md 2>/dev/null (global wiki index — know what directories have data)

Don't skip the transport check — running CLI commands when only MCP is available (or vice versa) wastes a turn and confuses the user.

Request Attribution

All Nimble API calls must carry a client_source tag so usage can be tracked per skill. The value is always skill- followed by the exact SKILL.md name field (e.g. skill-competitor-intel, skill-seo-intel, skill-nimble-web-expert).

CLI path — add --client-source skill-{name} as the global flag on every nimble command. Place it immediately after nimble, before the subcommand. No shell state persistence means this must be inlined on every individual call:

nimble --client-source skill-{name} search --query "..."
nimble --client-source skill-{name} extract --url "..."
nimble --client-source skill-{name} agent run --agent <name> --params '{...}'
nimble --client-source skill-{name} map --url "..."
nimble --client-source skill-{name} crawl run --url "..."

MCP path — per-skill client source tracking is not yet supported by the MCP server (it currently sends X-Client-Source: nimble_mcp_server for all calls regardless of skill). This will be enabled once the MCP server adds CLIENT_SOURCE support — no action needed here until then.

Sibling Handoff

When skills in the same family chain together (e.g., extract → enrich → verify), the second skill can skip redundant preflight work. Detect a sibling handoff by checking for same-day output from the upstream skill:

ls ~/.nimble/memory/reports/{upstream-skill}-*$(date +%Y-%m-%d).md 2>/dev/null

Use the dated report as the recency signal — data files under memory/{skill}/ may not have dates in their filenames, so always verify via the report timestamp. If a same-day report exists, parse the slug from the filename and load the corresponding data files.

If same-day sibling output exists:

• Skip CLI check and profile load — they were validated minutes ago
• Reuse WSA Layer 1 and Layer 3 inventory — the catalog hasn't changed. Only

re-run Layer 2 if the specialty or context changed.

• Use the sibling's structured output directly — if the upstream skill produced

data files with domains and page URLs, don't re-search for what's already known. Construct URLs from known patterns instead of running N web searches.

If no same-day sibling output exists: Run full preflight as normal.

This pattern is optional — skills MUST still work standalone without sibling output. The handoff is a fast path, not a requirement.

Smart Date Windowing

For any skill using --start-date based on previous runs:

• First run: 14 days ago → full mode
• Last run < 3 days ago: use 7 days ago (too narrow = empty results) → quick refresh
• Last run 3-14 days ago: use the last run date → quick refresh
• Last run > 14 days ago: 14 days ago → full mode
• Same-day repeat: if last_runs.{skill-name} is today, check if a report already

exists at ~/.nimble/memory/reports/{skill-name}*[today].md. If it does, ask the user before re-running: "Already ran today. Run again for fresh data?" Don't silently re-run — it wastes API credits and produces near-identical output. Exception — meeting-prep: Skip the same-day report check. Meeting-prep is per-meeting, not per-day — users may prep for multiple meetings in a single day. Instead, meeting-prep checks freshness at the entity level: load cached profiles from ~/.nimble/memory/people/ and ~/.nimble/memory/companies/ and offer to reuse recent research rather than blocking the run.

---

Search

# Standard search (always use --search-depth lite for discovery)
nimble search --query "company name news" --max-results 10 --search-depth lite

# News-focused search
nimble search --query "company name" --focus news --max-results 10 --search-depth lite

# Date-filtered search (inline the date — don't use variables)
nimble search --query "company funding" --focus news --start-date "2026-03-11" --max-results 10 --search-depth lite

# Social signals from X/LinkedIn
nimble search --query "Company" --include-domain '["x.com", "linkedin.com"]' --max-results 10 --search-depth lite --time-range week

# Deep search (full page content — only for comprehensive analysis, costs more)
nimble search --query "company name" --search-depth deep --max-results 5

# Fast search (premium tier — not used by default)
# nimble search --query "company name" --search-depth fast --max-results 10

Key flags:

• --query — search query string (required)
• --focus — general, news, shopping, social, coding, academic.

`social` searches social platform people indices directly (LinkedIn, X) — best for finding specific people. If it errors, use --include-domain '["linkedin.com"]' as an alternative approach.

• --max-results — max results to return
• --start-date / --end-date — date filters (YYYY-MM-DD)
• --search-depth — lite (1 credit), deep (1 + 1/page)
• --include-domain — JSON array of domains, e.g., '["x.com", "linkedin.com"]'
• --time-range — e.g., week
• --country — geo-targeted results (e.g., "US", "IL")
• --include-answer — LLM-powered answer summary

Date range strategy:

• First run: 14 days ago
• Subsequent runs: last_runs timestamp from business profile
• If < 3 results: retry without --start-date

Extract

# Extract article content as markdown (default for content analysis)
nimble extract --url "https://example.com/article" --format markdown

# Extract raw HTML (required for <head> metadata: canonical, schema, og, meta tags)
nimble extract --url "https://example.com" --format html

# Extract with JavaScript rendering (for dynamic/SPA pages)
nimble extract --url "https://example.com/spa" --render --format markdown

Response is JSON. The field returned depends on --format:

• --format markdown → data.markdown (clean body content)
• --format html → data.html (raw HTML including <head>)
• --format plain_text → data.plain_text
• --format simplified_html → data.simplified_html

Format selection by use case:

Key flags:

• --url — target URL (required)
• --format — markdown, html, simplified_html, plain_text (pick based on table above)
• --render — render JavaScript using a browser
• --parse --parser '{...}' — structured extraction via LLM parser schema

Extraction fallback (if data.markdown is mostly JavaScript/boilerplate): 1. Garbage check: If data.markdown has < 100 characters of meaningful content (after stripping nav/footer boilerplate), treat it as garbage. 2. Retry with --render --format markdown (handles JS-heavy/SPA pages) 3. If still garbage: search for the same article title on a different domain 4. If still nothing: skip and log — never abort a batch for a single extraction failure

Extract async & batch

# Async — submit single URL, get task_id, poll for results
nimble extract-async --url "https://example.com/page" --render --format markdown

# Batch — up to 1,000 URLs in one request
nimble extract-batch \
  --shared-inputs 'render: true' --shared-inputs 'format: markdown' \
  --input '{"url": "https://example.com/page-1"}' \
  --input '{"url": "https://example.com/page-2"}'

Poll async tasks with nimble tasks get --task-id <id> and fetch results with nimble tasks results --task-id <id>. Poll batches with nimble batches progress --batch-id <id>.

Map & Site Mapping

nimble map --url "https://example.com/blog" --limit 20

Site Mapping Pattern

Use nimble map to discover a site's page structure, then score and filter pages by relevance before extracting.

1. Discover: nimble map --url {url} --limit {cap} — returns a list of URLs 2. Score: Each skill defines a keyword/weight table for URL path segments (e.g., /providers = High, /about = Medium, /blog = Low). Score each discovered page against the table. 3. Filter: Keep pages scoring above the skill's threshold. Always include the homepage as a fallback. 4. Fallback: If nimble map returns < 3 candidates, use nimble search --query "site:{domain} {keywords}" --max-results 10 --search-depth lite

Each skill provides its own keyword/weight table in SKILL.md — the pattern here is the discover → score → filter → fallback flow.

Agents

Pre-built extraction templates for structured data from specific sites (Amazon, LinkedIn, Google, etc.). Use when you need structured fields rather than raw page content.

# List available agents (search by domain or vertical)
nimble agent list --limit 100
nimble agent list --limit 100 --search "amazon"

# Inspect an agent's schema (input params + output fields)
nimble agent get --template-name <agent_name>

# Run an agent (sync — waits for result)
nimble agent run --agent <agent_name> --params '{"key": "value"}'

# Run an agent (async — returns task_id, poll for results)
nimble agent run-async --agent <agent_name> --params '{"key": "value"}' \
  --callback-url "https://your.server/callback"

Key flags for `run` / `run-async`:

• --agent — agent name from nimble agent list (required)
• --params — JSON object with agent input parameters (required)
• --localization — enable zip_code/store_id localization (agent-dependent)

Additional flags for `run-async`:

• --callback-url — POST callback when task completes
• --storage-type — s3 or gs
• --storage-url — destination bucket URL
• --storage-compress — gzip the stored output
• --storage-object-name — custom filename instead of task_id

Response: data.parsing contains the structured output. Shape depends on agent type:

• PDP (product/profile/detail) → flat dict
• SERP / list → array of objects
• Google Search → {"entities": {"OrganicResult": [...], ...}}

Async task states: pending → success or error. Poll with nimble tasks results --task-id <task_id>.

Fallback rule: If no agent exists for the target domain, fall back to nimble search + nimble extract. Don't fail silently — log which domains lacked agent coverage so agent-builder can fill gaps later.

Agent batch

# Up to 1,000 agent requests in one call
nimble agent run-batch \
  --shared-inputs 'agent: amazon_serp' \
  --input '{"params": {"keyword": "iphone 15"}}' \
  --input '{"params": {"keyword": "iphone 16"}}'

Returns a batch_id. Poll with nimble batches progress --batch-id <id>, then fetch individual results with nimble tasks results --task-id <id>.

Tasks & batches polling

# Single async task
nimble tasks get --task-id <task_id>          # check status
nimble tasks results --task-id <task_id>      # fetch results

# Batch
nimble batches progress --batch-id <batch_id> # lightweight progress check
nimble batches get --batch-id <batch_id>      # all task IDs + states
nimble batches list --limit 20                # list all batches
nimble tasks list --limit 20                  # list all tasks

Workflow: Always nimble agent get before nimble agent run to understand the expected input params and output fields.

Agent Creation (generate → poll → iterate → publish)

Create custom extraction agents for any website. The full lifecycle is available via CLI.

# Generate a new agent
nimble agent generate \
  --agent-name niche_store_pdp \
  --prompt "Extract product name, price, rating, and first 5 reviews" \
  --url "https://example.com/products/widget-pro"

# Refine an existing agent (clone + apply new prompt)
nimble agent generate \
  --agent-name niche_store_pdp \
  --from-agent niche_store_pdp \
  --prompt "Add a discount_percentage field"

# Poll generation status (async — typically 1-3 min)
nimble agent get-generation --generation-id <generation_id>

# Publish when satisfied
nimble agent publish --agent-name niche_store_pdp --version-id <version_id>

Key flags for `generate`:

• --agent-name — name for the agent (required)
• --prompt — natural language description of what to extract (required)
• --url — sample URL to analyze (required)
• --from-agent — existing agent to clone and refine (for iteration)
• --input-schema — custom input schema (optional, inferred if omitted)
• --output-schema — custom output schema (optional, inferred if omitted)
• --metadata — additional metadata (optional)

Generation response: returns id (generation ID), status (queued → in_progress → success / failed), and generated_version_id on success.

Workflow: Generate → poll with get-generation until success → optionally iterate with --from-agent → publish with version-id.

Polling: Generation takes 1-3 minutes. Run the generate → poll → publish loop as a background Task agent so the user isn't blocked waiting. The Task agent should poll nimble agent get-generation every 10 seconds until status is success or failed, then publish automatically (or report failure). Present results to the user when done.

MCP Fallback (when CLI is not installed)

If nimble --version returns "command not found", fall back to the Nimble MCP server. All CLI commands have MCP equivalents — discover them via the MCP tool list. MCP tools accept the same parameters as CLI flags, passed as tool arguments instead of flags.

Parallel Execution

Make multiple Bash tool calls in a single response. Claude Code runs them in parallel automatically:

• Call 1: nimble search --query "CompanyA news" --max-results 5 --search-depth lite
• Call 2: nimble search --query "CompanyB news" --max-results 5 --search-depth lite
• Call 3: nimble search --query "CompanyC news" --max-results 5 --search-depth lite

Sub-Agent Spawning

When using the Agent tool for parallel research:

• Always `mode: "bypassPermissions"` — sub-agents don't inherit Bash permissions.
• Batch max 4 agents. More risk hitting rate limits. For 5+, batch in groups.
• Tell agents to use Bash — explicitly say "Use the Bash tool to execute nimble

commands." Some agents try WebSearch instead.

• Fallback on failure — if any agent returns without results, run those searches

directly from the main context. Don't leave gaps.

Communication Style

Inform the user at phase transitions only with concrete numbers:

• "Researching Acme Corp + 5 competitors since Mar 12..."
• "Found 12 new signals. Pulling top 4 articles..."
• "All data collected. Building your briefing..."

Don't narrate individual tool calls.

Rate Limits & Common Errors

• Rate limit: 10 req/sec per API key
• Retry on 429: Reduce simultaneous calls
• Timeout: 30 seconds per request

Signal Date Validation

High-quality intelligence requires distinguishing between when a page was published and when the underlying event occurred. This matters because:

• Syndicated or republished content may carry a different publication date than the

original source

• Secondary coverage (regulatory filings, recap articles, industry roundups) can

report on events that happened weeks or months earlier

Article Date vs Event Date

Every signal has two dates:

A signal is "new" only if its event date falls within the freshness window.

Event Date Extraction Rules

Sub-agents must determine the event date from content:

1. Explicit past reference — "launched in Q3", "appointed last October" → event date is in the past, regardless of the article date 2. Temporal language — "last quarter", "months ago", "earlier this year" → resolve relative to the article date 3. Present tense announcement — "today announces", "is launching" → event date ≈ article date 4. Dateline — "NEW YORK, March 15 —" → event date = that dateline date 5. If ambiguous — extract the source URL and check the on-page date

Source Type Hierarchy

When the same event appears from multiple sources, prefer those closest to the event:

1. Primary — the company's own domain, official press release, regulatory filing 2. Wire service — AP, Reuters, Bloomberg 3. Major outlet — original reporting with bylines 4. Derivative — syndicated copies, aggregator sites, recap articles, or content that attributes its information to another source

If the only source for a signal is derivative, corroborate against a primary or major source before reporting.

Freshness Classification

After determining the event date, classify each signal:

Hard rule: Only signals classified as NEW or UPDATED may appear in reports. STALE and UNCERTAIN signals must be dropped entirely — not downgraded, not footnoted, not included as "background context." If a signal can't be verified as genuinely recent, it doesn't exist as far as the report is concerned.

--start-date Best Practices

--start-date is a useful filter for reducing noise, but always validate event dates from the content itself:

• For news queries (--focus news), consider running a parallel undated query to

surface original sources alongside recent coverage

• The existing fallback ("If < 3 results, retry without --start-date") remains useful

Verification Budget

Not every signal needs full verification — budget extract calls by priority:

Skills define their own P1/P2/P3 signal types in their SKILL.md. The verification budget above applies universally regardless of which signals a skill classifies at each level.

P1 Corroboration (Mandatory)

Any P1 signal sourced from derivative or aggregator sites must be corroborated before it can appear in a report. This is a hard gate, not a suggestion.

For each P1 signal that needs corroboration:

nimble search --query "[Company] [event summary]" --max-results 5 --search-depth lite

Look for the primary source (company blog, press release, official filing, regulatory document). Check the primary source's date:

• Primary source dates the event within the freshness window → signal is NEW, include it
• Primary source dates the event outside the freshness window → reclassify as STALE, drop
• No primary source found → reclassify as UNCERTAIN, drop

Do not report P1 signals that fail corroboration. It's better to miss a real signal than to report a stale one as new — trust is the product.

---

Entity Deduplication

When a skill collects entity records from multiple sources (directories, search results, extracted pages), deduplicate before reporting. This is distinct from signal-level differential analysis (see memory-and-distribution.md) — entity dedup merges records for the same entity across sources within a single run.

Three-layer pattern (generic — each skill customizes the specifics):

1. Exact ID match — If the entity type has a canonical ID (place_id, NPI number, domain), match on that first. Exact match = same entity, merge fields. 2. Domain normalization — Strip www., trailing slashes, protocol. Compare root domains. www.acme.com/ and acme.com are the same entity. 3. Fuzzy name + location — Normalize names before comparing:

• Lowercase all characters
• Strip titles and honorifics (Dr., Mr., Ms., etc.)
• Strip credential suffixes (MD, DDS, Inc, LLC, Corp, etc.)
• Strip common noise words (The, and, of, &)
• Collapse whitespace and punctuation
• Compare normalized names with location context if available

This catches cross-source variations like "Dr. Jane Smith, MD" (Maps) vs "Jane Smith" (Yelp) vs "Smith Eye Care LLC" (BBB). Each source formats names differently — always normalize before comparing.

Track source_count per entity — entities confirmed by multiple sources are higher quality. Each skill defines which layers apply and any domain-specific matching rules in its reference files.

---

Entity Confidence Scoring

Rate each entity's data completeness so users know what to trust.

Generic formula — each skill defines its own target field list (N fields):

• High — All target fields found + confirmed by 2+ sources (source_count >= 2)
• Medium — >50% of target fields found
• Low — ≤50% of target fields found

Display the confidence level in output (e.g., ⬤⬤⬤ High, ⬤⬤○ Medium, ⬤○○ Low). Each skill defines its field list and may add criteria (e.g., requiring a verified phone number for High in a provider directory skill).

---

Input Parsing Pattern

Skills that accept batch input (lists of URLs, companies, locations) should detect the input type automatically:

Normalize all inputs to a uniform list of records before batch processing. Don't assume a specific format — detect and adapt.

---

Scaled Execution

When a skill needs to run multiple WSA or API calls, choose the execution tier based on the estimated number of requests. Each skill calculates its own estimate from input size and operations per record.

Individual calls (1–10)

Run up to 4 concurrent Bash calls per the Parallel Execution rules above.

Batch calls (11+)

For page extraction (11+ URLs):

nimble extract-batch \
  --shared-inputs 'format: markdown' \
  --input '{"url": "https://example.com/page-1"}' \
  --input '{"url": "https://example.com/page-2"}'

Add --shared-inputs 'render: true' if pages need JavaScript rendering.

For WSA/agent calls (11+ entities):

nimble agent run-batch \
  --shared-inputs 'agent: {agent_name}' \
  --input '{"params": {...}}' \
  --input '{"params": {...}}'

Both return a batch_id. Poll progress:

nimble batches progress --batch-id {batch_id}

Fetch results when complete:

nimble batches get --batch-id {batch_id}
nimble tasks results --task-id {task_id}

Batch API handles up to 1,000 requests per call with server-side orchestration. For >1,000 requests, split into multiple batch calls.

Sub-agents should also batch. When spawning sub-agents for parallel work, tell each agent to use extract-batch or agent run-batch for its assigned items rather than making individual calls. One batch call per agent is faster and more reliable than 5-6 sequential calls.

Large job confirmation (>1,000)

Before executing, show the estimate and ask the user to confirm:

Estimated API calls: ~2,400 (120 locations × 3 WSAs per location × ~7 enrichment)
This is a large job. Proceed? [Y/n]

Pattern: estimate → display → gate → execute

Why batch over individual calls

Individual nimble agent run calls each require a separate HTTP round-trip and Bash tool invocation. At scale (dozens+) this is slow, unreliable, and wasteful on a local machine. Batch APIs move orchestration server-side — one API call triggers all requests, and you poll for results. Always prefer batch when above the individual threshold.

---

Query Construction Tips

• Be specific: "Acme Corp product launch 2026" > "Acme Corp"
• Use `--include-domain '["domain"]'` for companies with generic names
• Fallback on empty: If < 3 results, retry without --start-date
• Combine focus modes: news + general in parallel for broader coverage
• Try variations: "CompanyName" → "Company Name" → domain

Profile & Onboarding

The business profile at ~/.nimble/business-profile.json and first-run setup flow.

---

Profile Schema

{
  "company": {
    "name": "Acme Corp",
    "domain": "acme.com",
    "description": "Enterprise SaaS platform for project management"
  },
  "industry_keywords": ["project management software", "team collaboration SaaS"],
  "competitors": [
    { "name": "WidgetCo", "domain": "widgetco.com", "category": "project-mgmt" },
    { "name": "GizmoTech", "domain": "gizmotech.io", "category": "project-mgmt" }
  ],
  "preferences": {
    "skip_competitors": [],
    "output_format": "bullet-points"
  },
  "integrations": {
    "notion": { "reports_page_id": "" },
    "slack": { "channel": "" }
  },
  "sales_context": {
    "key_differentiators": [
      "Only platform with real-time web data access",
      "Sub-second API response times"
    ],
    "integration_partners": [
      { "name": "DataStack", "type": "data warehouse" },
      { "name": "CRMHub", "type": "CRM" }
    ],
    "case_studies": [
      { "customer": "Large enterprise retailer", "industry": "retail", "outcome": "3x faster competitive intel" }
    ],
    "common_objections": [
      { "objection": "We already use [competitor]", "response": "Our real-time data is fresher — most competitors cache for 24h+" }
    ]
  },
  "last_runs": {
    "competitor-intel": "2026-03-20T14:30:00Z",
    "meeting-prep": "2026-03-22T09:00:00Z"
  },
  "setup_completed": true
}

Reading the Profile

At the start of every skill run:

cat ~/.nimble/business-profile.json 2>/dev/null

If missing or empty → trigger onboarding (see below).

Key fields:

• company.name / company.domain — the user's company
• competitors — tracked competitors with domains and categories
• industry_keywords — for industry-level searches
• preferences.skip_competitors — competitors to exclude
• last_runs.{skill-name} — timestamp for time-aware searches
• sales_context — value positioning data (differentiators, integrations, case studies, objections)
• integrations — Notion/Slack config for report distribution

Updating the Profile

After every skill run — update last_runs:

import json, datetime, os
path = os.path.expanduser("~/.nimble/business-profile.json")
with open(path, "r") as f:
    profile = json.load(f)
profile["last_runs"]["skill-name"] = datetime.datetime.now(datetime.timezone.utc).isoformat()
with open(path, "w") as f:
    json.dump(profile, f, indent=2)

On user correction — apply immediately:

Always confirm: "Got it — removed CompanyX from tracking."

Rules:

• Never overwrite the whole file. Read → modify → write.
• Preserve unknown fields.
• Handle missing file gracefully → trigger onboarding.
• JSON only, always valid.

---

First-Run Onboarding

Prerequisite Checks

The transport selection in nimble-playbook.md determines whether CLI or MCP is active. This section covers the install/upgrade/auth flow when neither is ready.

Minimum CLI version: 0.12.0

Preferred path — any Claude product (Claude Code, Claude Cowork, claude.ai)

The plugin install is one command and handles MCP registration + OAuth automatically:

"Run /plugin install nimble to install the Nimble plugin. The plugin's MCP

server auto-registers as a Connector you can see in Customize → Connectors.

On first use, the OAuth flow runs in your browser — no API key needed."

This works in every Claude product (Code, Cowork, claude.ai) — they share the plugin + connector mechanism.

Plugin installed but connector not connected (Cowork / claude.ai)

The most common Cowork / claude.ai failure: the plugin is installed (mcp__plugin_nimble_nimble__* tools are listed) but its connector isn't connected, so live data calls fail. Check this before doing any work — don't fire a data call and react to the error. A single read-only nimble_agents_list probe confirms it: success = connected, proceed; auth/not-connected error or a response containing an OAuth authorization URL = not connected.

When not connected, tell the user verbatim and stop — never fall back to WebFetch, WebSearch, or any other tool, and never guess at data:

Your Nimble plugin is installed, but its connector isn't connected yet — that's

why live data isn't working. To connect it:

>

1. Open Customize → Connectors

2. Find Nimble and click Connect

3. Complete the login in your browser. No Nimble account? You can create one

right there during login.

4. Once it shows Connected, re-run your request.

If a tool returns an OAuth "Authorize" link instead of data, present the link as-is and stop. Do not invent a completion step ("paste the URL back", "I'll complete the connection") — no such step exists. Do not claim the tools will activate and then call them in the same turn. Wait for the user to authorize, then retry (or run one nimble_agents_list probe to confirm).

Codex CLI or other terminal agents (shell available, no /plugin install)

When /plugin install isn't available but the user has shell access, install the CLI directly — it exposes the full Nimble surface area:

1. Check if npm is available: npm --version 2. If npm exists:

"The Nimble CLI is required. I'll install it now."

>

Run: npm install -g @nimble-way/nimble-cli

3. If npm is not available:

"The Nimble CLI requires Node.js/npm. Install Node.js first from

nodejs.org, then run: npm install -g @nimble-way/nimble-cli"

4. After install, verify: nimble --version 5. If verification fails, stop and ask the user to check their PATH.

Cursor, VS Code, or other MCP clients outside the Claude family

When neither /plugin install nor shell access is workable, have the user paste this into their MCP settings (e.g., .cursor/mcp.json or the host's equivalent):

{
  "mcpServers": {
    "nimble": {
      "type": "http",
      "url": "https://mcp.nimbleway.com/mcp"
    }
  }
}

After install, the first tool call triggers the OAuth flow automatically.

CLI outdated (version < 0.12.0)

Parse the version from nimble --version. If below 0.12.0:

"Your Nimble CLI is version [current] — version 0.12.0+ is required

for these skills. Upgrading now..."

>

Run: npm update -g @nimble-way/nimble-cli

Verify after upgrade: nimble --version. If still outdated, suggest: npm uninstall -g @nimble-way/nimble-cli && npm install -g @nimble-way/nimble-cli

API key not set

You need a Nimble API key.

1. Go to app.nimbleway.com → API Keys

2. Generate a new key

3. Run: export NIMBLE_API_KEY=your_key_here

4. Add to ~/.zshrc or ~/.bashrc to make permanent.

After the user sets it, verify: echo "NIMBLE_API_KEY=${NIMBLE_API_KEY:+set}"

API key expired (401)

Your key may have expired (72h TTL). Regenerate at app.nimbleway.com > API Keys.

All prerequisites met

Only proceed to Company Setup once CLI is installed, version is >= 0.12.0, and API key is set. Don't silently skip any check.

Company Setup (2 prompts max)

Prompt 1 — ask in plain text (NOT AskUserQuestion with options):

"What's your company's website domain? (e.g., acme.com)"

Verify — make two Bash calls simultaneously:

• nimble search --query "[domain]" --include-domain '["[domain]"]' --max-results 3 --search-depth lite
• nimble search --query "[domain] company" --max-results 5 --search-depth lite

Present what you found and confirm: "I found that [Company] ([domain]) is [brief description]. Is this the right company?"

Prompt 2 — skill-specific setup:

• competitor-intel: Offer choice via AskUserQuestion:
• Find for me — search and suggest competitors
• I'll list them — user provides names

If "Find for me", make three Bash calls simultaneously:

• nimble search --query "[Company] competitors" --max-results 10 --search-depth lite
• nimble search --query "[Company] vs" --max-results 10 --search-depth lite
• nimble search --query "[Company] alternatives" --max-results 5 --search-depth lite

• meeting-prep: No extra setup — context comes per-meeting
• company-deep-dive: No extra setup — target company comes per-request

Create Profile

mkdir -p ~/.nimble/memory/{competitors,people,companies,reports,positioning,synthesis}

Write ~/.nimble/business-profile.json using the schema above.

When setting up competitors, infer or ask for each competitor's domain and category. Also infer industry keywords from the company description.

Profile Exists

Skip onboarding. Greet with context: "Running competitor intel for Acme Corp — tracking WidgetCo, GizmoTech."

---

Error Recovery

If any step fails: 1. Tell the user what went wrong in plain language 2. Provide the exact command to fix it 3. Offer to retry

Never silently skip setup steps.

Vertical Presets for Market Finder

Each preset defines query patterns, target domains, and entity types for a business vertical. The skill auto-selects the preset based on user input, then discovers available WSAs at runtime using nimble agent list --search.

---

Preset Selection Logic

See SKILL.md Step 2 for the matching and selection flow.

---

Healthcare

Trigger keywords: doctor, dentist, dermatologist, ophthalmologist, optometrist, chiropractor, therapist, psychiatrist, pediatrician, clinic, medical, healthcare, hospital, pharmacy, urgent care, physical therapy, orthodontist, surgeon, physician, practice, practitioner

Discovery targets:

Enrichment targets:

Query pattern: "{specialty} {type}" per metro

• Example: "ophthalmologist" in Miami FL, "dentist" in Tampa FL

Geo-tiling: Yes -- tile by metro areas within the target state/region.

---

SaaS / Software

Trigger keywords: SaaS, software, app, platform, tool, cloud, B2B, startup, project management, CRM, ERP, analytics, automation, API, fintech, martech, edtech, healthtech, devtools, developer tools, productivity software

Discovery targets: None (no map WSAs). Use nimble search in two passes:

Pass 1 -- Product discovery (find the players):

nimble search --query "{vertical} site:g2.com" --max-results 20 --search-depth lite
nimble search --query "{vertical} site:capterra.com" --max-results 20 --search-depth lite
nimble search --query "best {vertical} software {current_year}" --max-results 20 --search-depth lite
nimble search --query "{vertical} site:producthunt.com" --max-results 10 --search-depth lite
nimble search --query "{vertical} open source github" --max-results 10 --search-depth lite

Pass 2 -- Financial & traction discovery (funding, market context):

nimble search --query "{vertical} site:crunchbase.com" --max-results 15 --search-depth lite
nimble search --query "{vertical} startup funding raised" --focus news --max-results 15 --search-depth lite
nimble search --query "{vertical} market landscape players" --max-results 15 --search-depth lite

Enrichment targets:

Query pattern: No geo-tiling. Search by category/vertical keywords.

Geo-tiling: No -- SaaS products are not geography-bound. If the user specifies a region, interpret as "headquartered in" and add as a search qualifier.

Dedup key: domain (not place_id).

Scoring note: SaaS uses different strength criteria than geographic verticals -- see SKILL.md Step 7 for SaaS-specific scoring based on funding, directory presence, and review counts.

---

Restaurants / Food

Trigger keywords: restaurant, cafe, coffee, bakery, bar, pub, brewery, pizza, sushi, taco, brunch, diner, bistro, food, catering, food truck, ice cream, juice, steakhouse, seafood, burger, ramen, pho, thai, italian, mexican, chinese, indian, mediterranean, vegan, vegetarian

Discovery targets:

Enrichment targets:

Query pattern: "{cuisine} restaurant" per metro

Geo-tiling: Yes -- tile by metro areas or neighborhoods for large geographies.

---

Legal / Financial

Trigger keywords: lawyer, attorney, law firm, legal, accountant, accounting, CPA, financial advisor, wealth management, insurance, tax, bankruptcy, immigration, personal injury, real estate attorney, family law, criminal defense, corporate law, patent, IP, intellectual property

Discovery targets:

Enrichment targets:

Query pattern: "{practice area} {type}" per metro

Geo-tiling: Yes -- tile by metro areas within the target state/region.

---

Auto / Home Services

Trigger keywords: mechanic, auto repair, body shop, car wash, oil change, tire, plumber, plumbing, electrician, HVAC, roofing, landscaping, pest control, cleaning, maid service, handyman, locksmith, moving, storage, painting, flooring, contractor, renovation, remodeling, garage door, appliance repair

Discovery targets:

Enrichment targets:

Query pattern: "{service}" per metro

Geo-tiling: Yes -- tile by metro areas.

---

Custom

Trigger keywords: (fallback -- used when no other preset matches)

Discovery targets:

Enrichment targets:

Query pattern: User's keywords per metro.

Geo-tiling: Yes (unless the query is clearly non-geographic).