메뉴
Natural language memory search. Use when the user asks "what did we decide about X", "do we know anything about X", "have we dealt with X before", or "/recall X". Faster than search-memory — single grep pass, no parallel agents.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Scans a real codebase and writes coding-conventions.md from what it actually finds — variable style, SQL patterns, error handling, INSERT strategy, naming. Run once on any new project to bootstrap the convention system. Triggers on "scan conventions", "generate conventions", "bootstrap conventions", "extract conventions from code", "what are the conventions".
Security audit — checks auth, SQL injection, exposed endpoints, and sensitive data. Triggers on "security check", "is this secure", "check for vulnerabilities", "check auth", "audit security", "security audit".
Use when switching environments, updating config values, or verifying URLs/settings. Triggers on "check environment", "switch to production", "update URLs", "check config", "is this prod-ready".
Use when verifying a feature works, after making changes, or before shipping. Triggers on "verify this works", "test this", "does this work", "run the checklist", "before I ship", "check this end to end".
Use when cleaning up, simplifying, or restructuring existing code without changing behavior. Triggers on "refactor", "clean up", "simplify this", "this is getting messy", "too long", "hard to read", "extract this".
Use when the user wants to review a file for bugs, antipatterns, or quality issues. Triggers on "review", "check for issues", "look for problems", "audit", "before I ship".
| name | recall |
| description | Natural language memory search. Use when the user asks "what did we decide about X", "do we know anything about X", "have we dealt with X before", or "/recall X". Faster than search-memory — single grep pass, no parallel agents. |
| allowed-tools | Bash, Read, Grep |
| effort | fast |
Trigger phrases:
/recall [question or topic]Use search-memory instead when: the question could span 3+ memory categories and you want parallel agents with a synthesized answer.
Pull the search term(s) from the user's message. If it's a full question ("why did we move files to mobile/?"), extract the key nouns: "mobile files location".
Try semantic search first (finds related memories even with different wording). Falls back to keyword search automatically if the index doesn't exist or sentence-transformers isn't installed.
python tools/memory.py --search-semantic "[query]" --top 8
Run this via Bash. If semantic search returns no matches, also run keyword search:
python tools/memory.py --search "[query]" --top 8
If results found:
## Recall: "[query]"
**[file name]** (score N)
> [matching lines]
**[file name]** (score N)
> [matching lines]
---
Bottom line: [1 sentence summary of what memory says]
If nothing found:
No memory found for "[query]".
This topic hasn't been captured yet. If it comes up this session, run /learn at the end to save it.
If a result looks relevant but partial:
"Found in
lessons.md— want me to read the full entry?"
memory.py is not found, fall back to: Grep(pattern="[query]", path="[MEM]") recursivelysearch-memory