kb-recall
Skill1 starsChanged 33 days agoMITView on GitHub
Use to find existing product knowledge in this repo before answering, deciding, or capturing — navigates index-first (MAP → domain index → specific notes) instead of reading everything.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- kb-captureSkill
- kb-dashboardSkill
- kb-elicitSkill
- kb-evolveSkill
- kb-goalSkill
- kb-orientSkill
- kb-planSkill
- kb-recapSkill
- kb-sanitizeSkill
- kb-visualizeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Read index/MAP.md to pick the relevant domain(s) by note counts and names.
- Very specific: line 15
Follow links (and index/backlinks.json for reverse links) to pull in directly related notes — one hop unless the question needs more.
- Very specific: line 32
Never read the whole knowledge/ tree.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
kb-recall — index-first retrieval
Goal: find the relevant notes for a question while reading as little as possible.
Steps
- Read
index/MAP.mdto pick the relevant domain(s) by note counts and names. - Open the relevant
index/<domain>.index.md. Use thesummarycolumn to shortlist candidate ids — do NOT open notes yet. - Open only the shortlisted note files.
- Follow
links(andindex/backlinks.jsonfor reverse links) to pull in directly related notes — one hop unless the question needs more. Backlinks cover all reference fields (goalscope, plan lists, timelinesequence,sources,relations), so "which goal/plan mentions X" is answered by backlinks.json too. For MEANING ("what mitigates RISK-003?", "who does FEAT-002 serve?") readindex/relations.json— typed edges with inverses. - Structured questions over fields ("all must-requirements still draft", "what
serves PER-002", "unvalidated assumptions") → run a saved query
(
npm run query -- --list, thennpm run query -- <name> [--param X]) instead of opening notes one by one. If none fits and the question will recur, add aqueries/<name>.yml(format inlib/query.mjs); for a one-off, write the YAML to a scratch file and runnpm run query -- <path>.yml. - Report findings:
debug: list the ids you read and their statuses.autonomous: summarize what's already known in plain language, no ids.
Rules
- Never read the whole
knowledge/tree. If the index can't answer it, widen the shortlist by one hop at a time. - Recall is read-only. To write, hand off to
kb-capture.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

