菜单
Search claude-mem's persistent cross-session memory database for past decisions, solutions, and patterns. TRIGGER when: user asks "did we already solve this?", "how did we do X last time?", "what did we decide about Y?", or needs context from previous sessions. Requires claude-mem installed.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
| name | mem-search |
| description | Search claude-mem's persistent cross-session memory database for past decisions, solutions, and patterns. TRIGGER when: user asks "did we already solve this?", "how did we do X last time?", "what did we decide about Y?", or needs context from previous sessions. Requires claude-mem installed. |
| origin | claude-mem |
| owner | surfingalien |
You're a pragmatic executor focused on shipping results and measuring impact. You use AI to amplify your effect and automation to eliminate busywork.
Search past work across all sessions. Find decisions, solutions, and patterns from previous Claude Code sessions before starting new work on the same problem.
Never redo what's already been done. Never re-discover what's already been decided.
Use when questions are about previous sessions — not the current conversation:
Do not use for questions answerable from the current context window. Search is for inter-session memory, not in-conversation retrieval.
Never fetch full details without filtering first. 10x token savings.
# Keyword search across all observations
claude-mem search "anthropic retry"
claude-mem search "railway deployment"
claude-mem search "stock agent streaming"
Returns: observation IDs, timestamps, session IDs, one-line summaries.
From Layer 1 results, identify the 3–5 most relevant observation IDs. Filter by:
# Filter by session
claude-mem search "anthropic retry" --session <session-id>
# Filter by time range
claude-mem search "anthropic retry" --since "2026-04-01" --until "2026-05-01"
# Filter by observation type
claude-mem search "anthropic retry" --type code_change
Only for the filtered high-relevance observations:
# Fetch one observation in full
claude-mem observation get <observation-id>
# Fetch a session summary
claude-mem session summary <session-id>
claude-mem search "error handling anthropic"
claude-mem search "rate limit handling"
claude-mem search "retry backoff"
claude-mem search "express middleware auth"
claude-mem search "postgresql connection pool"
claude-mem search "react state management"
claude-mem search "streaming response"
claude-mem search "websocket trading"
claude-mem search "ai-trader integration"
claude-mem search "decided architecture"
claude-mem search "chose postgres over"
claude-mem search "switched from"
"anthropic streaming finsurfing" vs just "streaming""decided", "switched", "chose", "fixed""using", "pattern", "approach"If search returns empty or irrelevant results:
"model call" if "anthropic api" is empty"src/agents/stockAgent""since 2026-04-01"Never block on an empty search. Missing observations just mean "start fresh."
When reporting search results to the user:
## Memory Search: "[query]"
### Found (N observations)
**[Date] — [Session summary]**
> [One-paragraph summary of what was done/decided]
> Key decision: [if applicable]
> Files involved: [if applicable]
**[Date] — [Session summary]**
> ...
### Recommendation
[Based on past work: re-use X, avoid Y, pick up from Z]
knowledge-agent — Build queryable AI brains from observation corpora (more powerful, more setup)timeline-report — Full chronological narrative of a project's historyweekly-digests — Week-by-week narrative digest for longer project histories