菜单
Search and retrieve relevant information from the cognitive memory system. Use when user says "search memory", "recall", "what do I know about", or needs to find previously saved learnings, decisions, and patterns.
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。
Batch dispatch — read queued tasks from ~/.claude/batch/inbox.md, fix each task's spec contract, fan them out to background subagents per case, and leave the user free until review time. Also surfaces unreported client sessions (~/.claude/batch/unreported.md). Use when the user says "batch", "morning batch", "朝バッチ", "タスク投入", "/batch", "/morning-batch", or at the start of a work day with queued tasks.
Standardized "investigate → written report" pipeline for SRE client work. Fixes the deliverable contract up front (format + done-criteria), delegates repo/infra scanning to subagents, verifies every claim, and outputs an issue-ready Markdown report. Use when the user says "調査して", "調べてレポート", "investigation report", "報告書にまとめて", or hands over an investigation-shaped task.
Turn a finished case (case-reflect / sreaas report output) into a generalized, confidentiality-scrubbed company tech-blog draft. Use when the user says "会社ブログ", "テックブログ", "案件を記事化", "company blog", or wants to asset-ify case outcomes for public publishing. Realizes the company-blog stage of learn_cycle.md.
Generate a personalized learning guide (text + hands-on script) for a technology/topic, tuned to the user's level and case context — like an AI-personalized intro book. Use when the user says "学習ガイド", "入門ガイド", "ハンズオンを作って", "learn guide", "この技術を学びたい", or wants a guided, output-oriented way to learn something. Powers the learning half of learn_cycle.md.
From a Claude Code /insights report, generate a Japanese-translated HTML report AND reflect its actionable recommendations into the config (~/.claude/), confirming EACH item one-by-one (apply or skip). Skipped items are left untouched. Use when the user says "insights apply", "insightを設定に反映", "insightを日本語HTML", "apply insights to config".
Systematically investigate and fix a GitHub Issue with root cause analysis. Use when user says "fix issue", "fix
| name | search-memory |
| description | Search and retrieve relevant information from the cognitive memory system. Use when user says "search memory", "recall", "what do I know about", or needs to find previously saved learnings, decisions, and patterns. |
| user-invocable | true |
| allowed-tools | Read, Grep, Glob |
Searches the cognitive memory system for information related to $ARGUMENTS.
find .claude/memory -type f 2>/dev/null | head -30 || echo "No memory files found"Search order follows cognitive memory architecture (fallback to available directories):
Most relevant and recent information
.claude/memory/local/session-state.json.claude/memory/local/current-task.mdSession history and interaction patterns
.claude/memory/local/session-metrics.jsonl.claude/memory/local/edit-audit.jsonl.claude/memory/local/learnings.mdGeneralized patterns, architecture decisions, and project knowledge
.claude/memory/project/architecture.md.claude/memory/project/ (all project-level knowledge)## Memory Search Results: "$ARGUMENTS"
### Working Memory
- [Recent context information]
### Relevant Episodic Memories
- [Session 2026-02-01] Experience solving a similar problem
- Situation: ...
- Solution: ...
### Semantic Knowledge
- [Concept: error-handling] Related patterns
- ...
### Confidence Score
Overall relevance: 0.85