napkin

About napkin

Napkin A skill for Claude Code that gives the agent persistent memory of its mistakes. The agent maintains a markdown file in your repo () where it tracks what went wrong, what you corrected, and what worked. It reads the file at session start and writes to it continuously as it works. By session 3-5 the behavior shift is significant — the agent stops making mistakes you've already corrected and starts pre-empting issues before you catch them. Baby continual learning in a markdown file. Install Claude Code Codex That's it. The skill activates every session, unconditionally.

Quick Facts

Compatible Skills

These tools work well together with napkin for enhanced workflows:

• omega-memory — semantic(0.36)+complementary+similar_pop+shared_platform (48%)
• task-orchestrator — semantic(0.19)+complementary+similar_pop+shared_platform (47%)
• mcp-memory-service — semantic(0.18)+complementary+similar_pop+shared_platform (46%)
• skill-codex — semantic(0.31)+complementary+similar_pop+shared_platform (46%)
• claude-memory-mcp — semantic(0.29)+complementary+similar_pop+shared_platform (45%)

More Claude Skill Tools

Explore other popular claude skill tools:

• skills ⭐ 157.3k
• claude-code ⭐ 136.8k
• claude-mem ⭐ 86.4k
• caveman ⭐ 82.6k
• Understand-Anything ⭐ 71.9k
• oh-my-openagent ⭐ 65.2k
• get-shit-done ⭐ 63.8k
• Pake ⭐ 59.6k
• codegraph ⭐ 58.3k
• Understand-Anything ⭐ 49.9k

Frequently Asked Questions