菜单
Full memory hygiene cycle — compresses memory-sessions.md, deduplicates memory-decisions.md, and syncs key project facts to the memory MCP graph. Run monthly or when context feels heavy.
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
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
Stages all changes and generates a lean Conventional Commits message via caveman-commit — user reviews and commits manually. Triggers on any commit intent: "commit", "stage my changes", "ready to push", "let's commit", "make a commit", "commit this", "push changes", "squash and commit", or any variation. Use whenever the user signals they're done with changes and ready to commit, even if they don't mention "message" or "caveman". Does NOT run git commit — outputs a ready-to-run command for the user to execute after review.
Autonomous ML research - agent modifies GPT training code, runs 5-min experiments, keeps improvements
Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
AI spend analytics — see where your token budget goes by task, model, tool, and project across 31 AI coding tools including Claude Code. Use when the user asks about AI costs, token usage, spend breakdown, or wants to optimize their AI budget.
| name | compact-memory |
| description | Full memory hygiene cycle — compresses memory-sessions.md, deduplicates memory-decisions.md, and syncs key project facts to the memory MCP graph. Run monthly or when context feels heavy. |
Run the following steps in order. Report results after each step.
Read .claude/rules/memory-sessions.md. Summarize all entries older than 30 days into a ## Archive block. Keep the 4 most recent sessions in full. Rewrite the file.
Report: lines before → lines after.
Read .claude/rules/memory-decisions.md. Identify decisions whose tools, files, or patterns no longer exist in the project (check with Glob/Grep). Remove obsolete entries. Flag anything you removed so the user can restore it if needed.
Report: decisions before → decisions after, what was removed.
Extract 3–5 key project facts from the memory files (active integrations, key constraints, architectural choices). Write each as an entity to the memory MCP graph using mcp__memory__create_entities. This makes them queryable in future sessions without loading the full files.
Report: entities written.
Print a single table: lines saved, decisions pruned, entities synced.
