List your recurring tasks; get a keep-as-agent / skill / script verdict and read-only .claude/agents drafts.
Claude CodeのCLAUDE.md設計・運用を100プロジェクト以上で経験。肥大化したCLAUDE.mdが無視される原因（トークン浪費・矛盾・曖昧指示）を体系化し、最小トークンで最大効果を得る設定ファイルの書き方をスキルに落とし込みました。
Audit the memory and instruction files your AI agent reads (AGENTS.md, CLAUDE.md, LEARNINGS.md, system prompts). A bundled offline Python script finds pasted secrets, injected instructions, hidden characters, risky commands, contradictions, duplicates, stale entries and broken file references, and writes cleaned copies. Download package: you bring your own AI agent and Python 3; no model is included.
Create a reversible, project-local Codex copy of Claude Code agents, skills, commands, compatible hooks, MCP, and persistent GPT routing—while keeping Claude untouched.
Generate structured daily review reports from local Claude Code / Codex conversation logs, with support for today, yesterday, the last 3 days, and the last 7 days. 根据 Claude Code / Codex 本地对话记录生成结构化每日复盘报告，支持今天、昨天、近 3 天、近 7 天。
AI Brainstorm puts Claude, Gemini, and ChatGPT in the same room — each one answering independently, so you actually see where they agree, where they don't, and why. Useful when the stakes are high enough to want more than one opinion: picking a tech stack, stress-testing a strategy, getting honest feedback on your writing, or thinking through a decision you've been sitting on too long. Stop copy-pasting the same prompt across three tabs. One question gets you all three answers, in one place.
Automatically generate a structured weekly work report from your Claude Code, Cursor activity and git commits — no manual tracking needed. The skill scans your conversation history across multiple AI tools and reconstructs everything you did this week.
Stop guessing whether Claude Code can do something. This skill lists the features that look like they work but quietly do not - session-only cron jobs, connectors that show 'connected' with zero usable tools, skills that load empty because of one quote mark in the YAML. Every claim was verified by running it, and each section ends with the exact command that settles the question on your own machine.