skill-recall — Claude Code skill: find local skills
This Claude Code skill matches a task with local skills. Run /skill-recall to find candidates or record a gap when none fit.
MIT ★ 26 updated 2026-11-16
npx skills add wrg32786/aigent-os --skill skill-recall -a claude-codeWhat skill-recall does
The skill compares a task with the local skill catalog and ranks possible matches. It reads $AIGENT_VAULT/memory/SKILL_LEDGER.md, checks task terms against taxonomy paths, then searches $AIGENT_VAULT/memory/SKILL_CHAINS.md for similar sequences. A matching sequence can appear as a suggested chain.
Each result includes a skill name, taxonomy path, short description, and invocation hint. When nothing matches, the skill adds the task to memory/SKILL_GAPS.md and suggests /skill-hunt. It needs $AIGENT_VAULT to read the catalog files at those paths.
What it helps with
- find a local skill for a task
- match a request to a taxonomy path
- identify a skill sequence for a similar goal
- record a task that has no matching skill
Example prompts for the agent
/skill-recall find a skill for investigating a bug/skill-recall— match local skills to the current task/skill-recall suggest a skill sequence for data analysis
How to install skill-recall
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill skill-recall -a claude-code2Manually: put the files in place
~/.claude/skills/skill-recall/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill-recall/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill skill-recall -a codex2Manually: put the files in place
.agents/skills/skill-recall/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill skill-recall -a cursor2Manually: put the files in place
.cursor/skills/skill-recall/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wrg32786/aigent-os skills/skill-recall2Manually: put the files in place
.github/skills/skill-recall/SKILL.md1Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill skill-recall -a gemini-cli2Platform CLI
gemini skills install https://github.com/wrg32786/aigent-os --path skills/skill-recallManually: put the files in place
.devin/skills/skill-recall/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wrg32786/aigent-os --skill skill-recall -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 skill-recall
How do I install skill-recall in Claude Code?
Run npx skills add wrg32786/aigent-os --skill skill-recall -a claude-code. The skill file is at ~/.claude/skills/skill-recall/SKILL.md.
What does skill-recall do?
It searches local skills for task matches, ranks the results, and can suggest related chains. If nothing matches, it logs the task in memory/SKILL_GAPS.md and suggests /skill-hunt.
What does skill-recall need to work?
It reads $AIGENT_VAULT/memory/SKILL_LEDGER.md and $AIGENT_VAULT/memory/SKILL_CHAINS.md. Tasks without a match are recorded in memory/SKILL_GAPS.md.
Source text
SKILL.md · MIT
---
name: skill-recall
description: "Find local skills for the current task and log gaps. Use when checking which local skill matches a task or whether a suitable skill exists."
---
# /skill-recall — Find local skills for current task
When invoked, match the current task against the installed skill taxonomy. Return ranked suggestions or log a gap.
## Trigger
`/skill-recall` or `/skill-recall <task description>`
## Flow
1. **Parse intent** — extract key action words and domain from the task description or current conversation context
2. **Read taxonomy** — load `$AIGENT_VAULT/memory/SKILL_LEDGER.md`
3. **Prefix match** — match intent keywords against taxonomy paths:
- Direct path match: `research.deep` matches all `research.deep.*` skills
- Keyword match: "browser" matches `automation.browser.*`, "lyrics" matches `music.lyrics.*`
- Fuzzy domain match: "investigate a bug" matches `research.deep.investigate` + `strategy.debug.investigate`
4. **Check chains** — read `$AIGENT_VAULT/memory/SKILL_CHAINS.md` for prior successful multi-skill sequences with similar objectives
5. **Rank results** — prioritize by:
- Exact taxonomy path match (highest)
- Prior chain match (high — proven to work)
- Keyword overlap (medium)
- Domain proximity (lower)
6. **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.md` and 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
© wrg32786 · MIT · wrg32786/aigent-os