- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill faq-mine -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/HEAD/packages/authoring-toolkit/.pi/skills/faq-mineFrom the publisher
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.mdOverview
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
Download packages/authoring-toolkit/.pi/skills/faq-mine/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/BlackBeltTechnology/pi-agent-dashboard.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.