Dig
- 74 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
Dig is an agent skill that refines an active Tome research session by drilling into a subtopic or channel and merging re-ranked findings into the saved report.
About
Dig is a refinement skill for the Claude Night Market Tome research stack. Solo and indie builders use it when a `/tome:research` pass returned useful breadth but one subtopic or source channel needs more depth—competitor papers, a single distribution angle, or a narrower keyword slice. The workflow loads the latest session, runs a focused search, merges and re-ranks new hits into the existing report, and surfaces deltas to you. It does not replace starting research or final synthesis; those stay on `/tome:research` and `/tome:synthesize`. Fits agents that already maintain session state and multi-channel search. Intermediate complexity: you need an active session and sane channel names from the first pass.
- Loads the most recent session via SessionManager before any new search
- Parses subtopic plus optional channel filter (e.g. papers only)
- Dispatches targeted search on one channel or all channels and merges into the session
- Re-ranks findings and updates the saved report for interactive review
- Clear errors when no session exists or the channel was not in the original session
Dig by the numbers
- 74 all-time installs (skills.sh)
- Ranked #5,508 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill digAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 74 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Drill into one angle or channel after an initial Tome research session without starting a new topic from scratch.
Who is it for?
Best when you're already running Tome research and want interactive narrow-down on one subtopic or source type.
Skip if: Cold-start topics, final narrative synthesis, or anyone without a prior `/tome:research` session.
When should I use this skill?
Drilling into a subtopic after an initial research session or narrowing results to a specific channel.
What you get
The session report grows with targeted findings and updated ranking so you can decide whether to dig again or invoke `/tome:synthesize` for a final write-up.
- Updated saved research report
- Presented new findings and ranking deltas
By the numbers
- 6-step workflow from load session through present findings
Files
Dig Deeper
When To Use
- Drilling into a subtopic after an initial research session
- Narrowing results to a specific channel (e.g. papers only)
When NOT To Use
- Starting a new research topic (use
/tome:researchfirst) - Synthesizing results (use
/tome:synthesize)
Refine an active research session interactively.
Workflow
1. Load most recent session via SessionManager 2. Parse the subtopic and optional channel filter 3. Dispatch targeted search (single agent or all channels) 4. Merge new findings into existing session 5. Re-rank and update the saved report 6. Present new findings to user
Error Cases
- No active session: "Start a session first with
/tome:research \"topic\""
- Specified channel not in original session: warn and
suggest available channels
Exit Criteria
- [ ] Active session loaded from SessionManager before any search
executes; if absent, error "Start a session first with /tome:research \"<topic>\"" is emitted and skill halts
- [ ] New findings merged into the existing session without
overwriting prior findings from other channels
- [ ] Session report re-ranked and saved after the merge so
the updated file reflects the deeper search results
- [ ] If the specified channel is not in the original session,
a warning is emitted listing the available channels
- [ ] New findings presented to the user after the session is
saved, not before
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use after broad `/tome:research` instead of restarting discovery in a new chat thread.
FAQ
Who is dig for?
Developers using the Tome research skills who need a second pass on a subtopic or channel while keeping one session and one report.
When should I use dig?
In the Idea research phase after `/tome:research`, when you want papers-only or angle-specific depth; not when starting a new topic or when you are ready to synthesize.
Is dig safe to install?
Review the Security Audits panel on this Prism page and the Night Market repo before enabling network-backed search in your agent environment.