- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/HEAD/packages/authoring-toolkit/.pi/skills/faq-mineDe l'éditeur
Orchestrate FAQ extraction from project knowledge docs AND pi-hermes memory
stores into docs/faq.md.
Two source classes:
docs/*.md. How-to / what-is questions.Inputs:
--docs <a.md>,<b.md> — explicit doc list. Default = README.md + every evergreen docs/*.md. --docs skip = memory-only run (disables doc mining; the ship-change harvest path).--memory <off|project|failures|all> — hermes stores to mine. Default failures = project store + global failures.md (relevance-filtered). off = docs only. all = also global MEMORY.md.--max <N> — entry cap per source (default ~10).Non-interactive: passing BOTH --docs (incl. --docs skip) and --memory skips the Phase 1 prompt — the headless invocation faq-mine --docs skip --memory failures runs memory-only with no ask_user.
docs/faq.md if it exists. Extract every ## <Question> heading into a dedupe list.
# FAQ
FAQ. How-to answers that already live in README.md + docs/. New entries here when same question recurs.
--docs skip — memory-only run):
ls README.md docs/*.md 2>/dev/null
Exclude:
docs/faq.md itselfdocs/faq.agent.md (condensed index derived FROM faq.md — refreshed in Phase 4, never mined)docs/AGENTS.md and any AGENTS.md (index, not narrative)docs/session-knowledge-*.md (point-in-time notes)docs/spec-gap-analysis.md and any *-resolved.md (transient analyses)docs/.faq-draft-*.md (in-flight draft)wc -l to surface size.--memory off):
PROJ=$(basename "$(git rev-parse --show-toplevel)")
ls -l "$HOME/.pi/agent/projects-memory/$PROJ/MEMORY.md" \
"$HOME/.pi/agent/pi-hermes-memory/failures.md" \
"$HOME/.pi/agent/pi-hermes-memory/MEMORY.md" 2>/dev/null
projects-memory/$PROJ/MEMORY.md — all entries repo-scoped, no filter. If $PROJ dir absent (e.g. worktree name differs), ls ~/.pi/agent/projects-memory/ and pick the matching dir; skip if none.pi-hermes-memory/failures.md — mixed across projects, needs a repo-relevance filter (subagent applies it).pi-hermes-memory/MEMORY.md — mixed, only when --memory all.Use ask_user (multiselect) to let the user pick which sources to mine — list the docs AND the resolved hermes stores as options. Pre-select the evergreen docs + the project store + failures.md. Skip the prompt only when the user already passed both --docs and --memory.
Dispatch ONE general-purpose subagent with model: @fast, run_in_background: true per selected source (docs AND stores). All agents run in parallel — each writes to its OWN draft file to avoid write conflicts:
docs/.faq-draft-<basename>.mddocs/.faq-draft-mem-<label>.md (label = project | failures | memory)Subagent prompt template (substitute <DOC> with the source doc path):
Mine FAQ-worthy entries from
<DOC>and write them to a NEW filedocs/.faq-draft-<basename>.md. Do NOT touch any other file.STEP 1 — read existing
docs/faq.md. Extract every## <Question>heading. DEDUPE: skip questions already covered (or trivially equivalent).STEP 2 — read
<DOC>fully. Identify recurring how-to / what-is questions a user or future agent would actually ask. Aim for 4–10 entries. Quality > quantity. Skip implementation trivia.STEP 3 — write the draft using the EXACT format of existing faq.md entries:
## <Question>? <one-line terse answer> Command: `<cmd>` (when applicable; omit for what-is questions). <optional bullets / sub-sections with concrete tokens> Cross-refs: - <DOC>:<line> - <other source file:line>CAVEMAN STYLE (verbatim, all docs/ prose obeys):
- Short declarative fragments. Drop articles (a/an/the) and most copulas (is/are/was) when meaning survives.
- Subject → verb → object, present tense. No hedging, no marketing voice, no "we", no "you".
- One fact per line/row. No restating context the file already establishes.
- Prefer concrete tokens (paths, function names, env vars, ports, exit codes) over prose.
- Keep symbols/identifiers verbatim; only connective tissue compresses.
Verify every command + path against the source doc. No invented flags, no speculation. Confirm completion in your final reply with the entry count.
Runtime problems live in the hermes stores as §-separated terse entries, each stamped ``. Convert each FAQ-worthy problem into a symptom-first Q&A entry. One subagent per store.
Subagent prompt template (substitute <STORE> = absolute store path, <LABEL> = project|failures|memory, <FILTER> = the relevance rule below):
Mine FAQ-worthy runtime problems from the pi-hermes memory store
<STORE>and write them to a NEW filedocs/.faq-draft-mem-<LABEL>.md. Do NOT touch any other file.STEP 1 — read existing
docs/faq.md. Extract every## <Question>heading. DEDUPE: skip any problem already covered (or trivially equivalent — e.g. RPC-keeper, ctx-stats, session-stuck entries already exist).STEP 2 — read
<STORE>fully. Entries are separated by lines containing only§. Each entry may be prefixed[failure]/[correction]/[insight]/[convention]/[tool-quirk]and ends with an HTML `` comment. IGNORE the comment metadata.STEP 3 — for each KEPT entry, write a symptom-first FAQ entry in the EXACT faq.md format:
## Why does <symptom>? (or: How do I fix <symptom>?) <one-line root cause — terse> Fix: `<cmd>` (or the concrete file/edit; omit when not a command). <optional bullets: concrete tokens — paths, env vars, flags, exit codes> Cross-refs: - <STORE> - <every file path / package named inside the entry>
- Question = the OBSERVABLE symptom a user/agent would search (the error string, the wrong behaviour), NOT the internal cause. A reader who hits the problem must recognise their symptom in the heading.
- Keep the wrong-way → right-way fix intact; that is the whole value of the entry.
- Merge near-duplicate store entries (same problem, consolidated across dates) into ONE FAQ entry.
CAVEMAN STYLE (verbatim, all docs/ prose obeys):
- Short declarative fragments. Drop articles (a/an/the) and most copulas (is/are/was) when meaning survives.
- Subject → verb → object, present tense. No hedging, no marketing voice, no "we", no "you".
- One fact per line. No restating context the file already establishes.
- Prefer concrete tokens (paths, function names, env vars, ports, exit codes) over prose.
- Keep symbols/identifiers verbatim; only connective tissue compresses.
Verify every command + path against the source entry. No invented flags, no speculation — if an entry lacks a concrete fix, skip it. Confirm completion in your final reply with the kept/skipped counts.
<FILTER> value by store:
<LABEL>=project): STEP 2b — no filter. Every entry is scoped to this repo; consider all of them.failures.md / MEMORY.md (<LABEL>=failures|memory): STEP 2b — RELEVANCE FILTER. This store mixes many projects. KEEP only entries about THIS project specifically, its paths (packages/, docs/, openspec/, src/), or a dev-in-this-repo tooling quirk (test runner, linter, build tool, git worktree, etc.). DROP everything else (unrelated product decks, OAuth-license research, Drive/rclone uploads, other repos). When unsure, DROP.Wait for all agents (2A + 2B) to finish.
grep -n '^## ' docs/.faq-draft-*.md
Edit.
failures.md. Keep the one carrying the concrete fix; drop the other.## [Unreleased] example inside ```markdown blocks is content, not a heading).cat docs/.faq-draft-*.md >> docs/faq.md && rm docs/.faq-draft-*.md
grep -c '^## ' docs/faq.md
wc -l docs/faq.md
Then refresh the condensed index docs/faq.agent.md so new entries appear in the pull-only map. Delegate to ONE general-purpose subagent (docs/ write → subagent per Rule 6):
Append condensed one-liners for these NEW faq.md entries to
docs/faq.agent.md. For each, add a line- <short question stem> — <key answer / fix in ≤12 words>under a## Runtime problems & quirkssection (create the section if absent, at the end). Keep the existing sections untouched. Caveman style. New questions + answers: <paste the merged headings + one-line answers>.
Report to user:
## headings inside code fences (if any).This skill writes under docs/ (faq.md + faq.agent.md). Per AGENTS.md:
docs/ writes go through subagents (general-purpose). Main orchestrator only cat/rm/Edits for merge + targeted dedupe.~/.pi/agent/**. Extraction copies knowledge into faq.md; it does not move or prune the memory.## headings — packages/shared/src/tool-registry/__tests__/install-hints.test.ts asserts each tool docsAnchor maps to a heading. Append only.AGENTS.md (incl. docs/AGENTS.md) or docs/faq.agent.md — indexes, not narrative knowledge.session-knowledge-*.md or spec-gap-analysis.md — point-in-time notes; entries would rot fast.failures.md/MEMORY.md mix projects; unfiltered mining leaks other repos' quirks into this FAQ.Cross-refs: block — agents lose the source trail otherwise (memory entries cross-ref the store path).Mine docs/faq.md from README.md, docs/*.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when aske
---name: faq-minedescription: Mine docs/faq.md from README.md, docs/*.md, and the pi-hermes memory stores. Dispatches @fast subagents per…---# packages/authoring-toolkit/.pi/skills/faq-mine/SKILL.mdVue d'ensemble
Mine docs/faq.md from README.md, docs/*.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime problems in the FAQ", or "create FAQ from README + docs".
FAQ
Téléchargez packages/authoring-toolkit/.pi/skills/faq-mine/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/BlackBeltTechnology/pi-agent-dashboard.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.