skill-recall
Skill25 starsChanged 7 days agoMITView on GitHub
Find local skills for the current task and log gaps. Use when checking which local skill matches a task or whether a suitable skill exists.
In this repository71 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- agent-fitnessSkill
- body-checkSkill
- briefSkill
- capsule-compactSkill
- closeSkill
- codex-adapterSkill
- cognitive-updateSkill
- comms-summarizeSkill
- compact-noteSkill
- context-capsuleSkill
- context-hygieneSkill
- critique-planSkill
- decideSkill
- deep-reconSkill
- DiagnoseSkill
- digestSkill
- dreamSkill
- EnvelopeSkill
- find-weaknessSkill
- First 10 MovesSkill
- first-winSkill
- frontend-slidesSkill
- Honesty CheckSkill
- humanize-docsSkill
- impeccableSkill
- learn-from-failureSkill
- LearnSkill
- memory-bridgeSkill
- meta-improveSkill
- meta-improve-vaultSkill
- nightly-close-paritySkill
- nightly-ledger-captureSkill
- nightlySkill
- openSkill
- operator-setupSkill
- orientSkill
- pauseSkill
- ponytailSkill
- port-specSkill
- PromoteSkill
- reconcileSkill
- research-deepSkill
- resumeSkill
- Sandbox RoutingSkill
- scout-vaultSkill
- Self-ReviewSkill
- semantic-searchSkill
- setupSkill
- ship-adapterSkill
- Skill AuditSkill
- skill-huntSkill
- solution-huntSkill
- sprite-specSkill
- startSkill
- statusSkill
- StuckSkill
- supersedeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 8
When invoked, match the current task against the installed skill taxonomy.
- Distinctive: line 29
If matches found: return ranked list with skill name, taxonomy path, one-line description, and invocation hint
- Very specific: line 30
If chain match found: suggest the full chain with → notation
- Very specific: line 31
If NO match found: log to memory/SKILL_GAPS.md and suggest /skill-hunt
- Very specific: line 35
When no match is found, append a row to memory/SKILL_GAPS.md:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
/skill-recall — Find local skills for current task
When invoked, match the current task against the installed skill taxonomy. Return ranked suggestions or log a gap.
Trigger
/skill-recall or /skill-recall <task description>
Flow
- Parse intent — extract key action words and domain from the task description or current conversation context
- Read taxonomy — load
$AIGENT_VAULT/memory/SKILL_LEDGER.md - Prefix match — match intent keywords against taxonomy paths:
- Direct path match:
research.deepmatches allresearch.deep.*skills - Keyword match: "browser" matches
automation.browser.*, "lyrics" matchesmusic.lyrics.* - Fuzzy domain match: "investigate a bug" matches
research.deep.investigate+strategy.debug.investigate
- Direct path match:
- Check chains — read
$AIGENT_VAULT/memory/SKILL_CHAINS.mdfor prior successful multi-skill sequences with similar objectives - Rank results — prioritize by:
- Exact taxonomy path match (highest)
- Prior chain match (high — proven to work)
- Keyword overlap (medium)
- Domain proximity (lower)
- Output:
- If matches found: return ranked list with skill name, taxonomy path, one-line description, and invocation hint
- If chain match found: suggest the full chain with
→notation - If NO match found: log to
memory/SKILL_GAPS.mdand suggest/skill-hunt
Gap Logging
When no match is found, append a row to memory/SKILL_GAPS.md:
| {today's date} | {task context, 1 line} | {what capability is missing} | — | open |Then output: "No matching skill found. Gap logged. Run /skill-hunt {gap description} to search externally."
Example
User: /skill-recall transcribe this meeting recording
aigent:
Match: `research.audio.transcriber` — /audio-transcriber
"Transcribe audio files to structured markdown with speaker labels via Whisper"
Invoke: /audio-transcriber <path-to-audio>Related
- [[memory/SKILL_LEDGER]] — the taxonomy this skill searches
- [[memory/SKILL_GAPS]] — where misses are logged
- [[memory/SKILL_CHAINS]] — prior successful sequences
- [[concepts/Capability Expansion Doctrine]] — the doctrine governing recall + hunt
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.

