status · neolabhq — Claude Code skill: check your FPF knowledge base
Reports what is in the FPF knowledge base right now: hypothesis counts per layer, evidence freshness, and recent decisions.
npx skills add NeoLabHQ/context-engineering-kit --skill status -a claude-codeWhat status does
The skill walks the .fpf/ directory and builds a report. First it checks that the structure is intact: knowledge/L0/, knowledge/L1/, knowledge/L2/, knowledge/invalid/, evidence/, decisions/. Then it counts files in each knowledge layer and in the decisions folder.
Next comes the freshness pass. Every file in .fpf/evidence/ gets its valid_until frontmatter field compared against today's date, and lands in one of three buckets: fresh, stale, or expired. Expired evidence triggers a warning and a nudge toward /fpf:decay. From the distribution of hypotheses the skill names the current phase — ABDUCTION, DEDUCTION, INDUCTION, DECISION, or IDLE — and points at the next step.
It only works where an FPF base already exists. With no .fpf/ directory the report says NOT INITIALIZED and suggests /fpf:propose-hypotheses instead. So create the base before the first run.
What it helps with
- see how many hypotheses sit in L0 waiting for verification
- catch expired evidence before a decision leans on it
- tell which FPF phase the work is in
- confirm the
.fpf/subdirectories are still in place - list recent decisions and their winners
Example prompts for the agent
- show me the FPF status
- what's in the FPF knowledge base right now?
- run /fpf:status and flag any expired evidence
How to install status
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill status -a claude-code2Manually: put the files in place
~/.claude/skills/status/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/status/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill status -a codex2Manually: put the files in place
.agents/skills/status/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill status -a cursor2Manually: put the files in place
.cursor/skills/status/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit status2Manually: put the files in place
.github/skills/status/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill status -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/statusManually: put the files in place
.devin/skills/status/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill status -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about status
How do I install status in Claude?
Run npx skills add NeoLabHQ/context-engineering-kit --skill status -a claude-code. The skill lands in ~/.claude/skills/status/SKILL.md.
What does the status skill do?
It reports on the FPF knowledge base: directory structure, hypothesis counts per layer, evidence freshness, decision count, and the current phase.
What do I need for a useful report?
An existing base in .fpf/. Without it the skill reports that the base is not initialized and points you to /fpf:propose-hypotheses.
Similar skills
All skills for Agent setup: memory, context, orchestration →status by other authors comes first.
