Status
Snapshot the FPF (`.fpf/`) knowledge base—hypothesis layers, evidence freshness, and decisions—before the next context-engineering step.
Overview
status is an agent skill most often used in Build (also Validate → scope, Operate → iterate) that displays the current state of the FPF `.fpf/` knowledge base.
Install
npx skills add https://github.com/neolabhq/context-engineering-kit --skill statusWhat is this skill?
- Verifies `.fpf/` directory tree and required knowledge/evidence/decision folders
- Counts hypotheses per layer: L0 Proposed, L1 Verified, L2 Validated, plus invalid/rejected
- Evidence freshness scan with fresh/stale/expired totals and named stale warnings
- Infers current FPF phase: ABDUCTION | DEDUCTION | INDUCTION | DECISION | IDLE
- Structured markdown status report for the user including recent decisions table
- Reports hypothesis layers L0 (Proposed), L1 (Verified), L2 (Validated), and invalid/rejected
- Evidence table columns: Total, Fresh, Stale, Expired
Adoption & trust: 512 installs on skills.sh; 1.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are running FPF context engineering but cannot see at a glance how many hypotheses sit in each layer, whether evidence expired, or what phase the workflow is in.
Who is it for?
Builders maintaining a `.fpf/` repo who want a repeatable status ritual before verification, validation, or decision commands.
Skip if: Projects without the FPF directory layout or anyone who only needs generic git status instead of hypothesis-layer metrics.
When should I use this skill?
Display the current state of the FPF knowledge base when working with `.fpf/` directories and context-engineering workflows.
What do I get? / Deliverables
You get a formatted FPF Status report with directory checks, layer counts, evidence table, warnings, and recent decisions so you can pick the next kit skill (e.g. decay) with context.
- Markdown FPF Status report with phase inference and warnings
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build → pm is the canonical shelf because status answers “where are we in the FPF workflow?” while you are still shaping product knowledge, not operating production infra. PM subphase fits hypothesis counts (L0–L2), decision records, and phase inference (abduction through decision)—planning artifacts, not runtime monitoring.
Where it fits
Before sprint planning, run status to see three L0 hypotheses still awaiting verification.
Confirm one L2 validated hypothesis and zero expired evidence before locking build scope.
After a month idle, status flags expired evidence and suggests running decay.
How it compares
Use instead of manual `ls` and spreadsheet tracking when you already adopted the FPF knowledge directory convention.
Common Questions / FAQ
Who is status for?
Solo builders and small teams using the neolabhq FPF context-engineering-kit who store hypotheses and evidence under `.fpf/` and need a dashboard-style check.
When should I use status?
Use it in Build → pm before major FPF moves; in Validate → scope when deciding if L2 hypotheses are ready to commit; and in Operate → iterate when reviewing stale or expired evidence after long gaps between agent sessions.
Is status safe to install?
It reads your local `.fpf/` tree; confirm scope on the Security Audits panel for neolabhq/context-engineering-kit and avoid pointing agents at sensitive decision files you do not want summarized.
SKILL.md
READMESKILL.md - Status
# Status Check Display the current state of the FPF knowledge base. ## Action (Run-Time) 1. **Check Directory Structure:** Verify `.fpf/` exists and contains required subdirectories. 2. **Count Hypotheses:** List files in each knowledge layer: - `.fpf/knowledge/L0/` (Proposed) - `.fpf/knowledge/L1/` (Verified) - `.fpf/knowledge/L2/` (Validated) - `.fpf/knowledge/invalid/` (Rejected) 3. **Check Evidence Freshness:** Scan `.fpf/evidence/` for expired evidence. 4. **Count Decisions:** List files in `.fpf/decisions/`. 5. **Report to user.** ## Status Report Format ```markdown ## FPF Status ### Directory Structure - [x] .fpf/ exists - [x] knowledge/L0/ exists - [x] knowledge/L1/ exists - [x] knowledge/L2/ exists - [x] evidence/ exists - [x] decisions/ exists ### Current Phase Based on hypothesis distribution: ABDUCTION | DEDUCTION | INDUCTION | DECISION | IDLE ### Hypothesis Counts | Layer | Count | Status | |-------|-------|--------| | L0 (Proposed) | 3 | Awaiting verification | | L1 (Verified) | 2 | Awaiting validation | | L2 (Validated) | 1 | Ready for decision | | Invalid | 1 | Rejected | ### Evidence Status | Total | Fresh | Stale | Expired | |-------|-------|-------|---------| | 5 | 3 | 1 | 1 | ### Warnings - 1 evidence file is EXPIRED: ev-benchmark-old-2024-06-15 - Consider running `/fpf:decay` to review stale evidence ### Recent Decisions | DRR | Date | Winner | |-----|------|--------| | DRR-2025-01-15-use-redis | 2025-01-15 | redis-caching | ``` ## Phase Detection Logic Determine current phase by examining the knowledge base state: | Condition | Phase | Next Step | |-----------|-------|-----------| | No `.fpf/` directory | NOT INITIALIZED | Run `/fpf:propose-hypotheses` | | L0 > 0, L1 = 0, L2 = 0 | ABDUCTION | Continue with verification | | L1 > 0, L2 = 0 | DEDUCTION | Continue with validation | | L2 > 0, no recent DRR | INDUCTION | Continue with audit and decision | | Recent DRR exists | DECISION COMPLETE | Review decision | | All empty | IDLE | Run `/fpf:propose-hypotheses` | ## Evidence Freshness Check For each evidence file in `.fpf/evidence/`: 1. Read the `valid_until` field from frontmatter 2. Compare with current date 3. Classify: - **Fresh**: `valid_until` > today + 30 days - **Stale**: `valid_until` > today but < today + 30 days - **Expired**: `valid_until` < today If any evidence is stale or expired, warn the user and suggest `/fpf:decay`. ## Example Output ``` ## FPF Status ### Current Phase: DEDUCTION You have 3 hypotheses in L0 awaiting verification. Next step: Continue the FPF workflow to process L0 hypotheses. ### Hypothesis Counts | Layer | Count | |-------|-------| | L0 | 3 | | L1 | 0 | | L2 | 0 | | Invalid | 0 | ### Evidence Status No evidence files yet (hypotheses not validated). ### No Warnings All systems nominal. ```