Summary
This extracts learnings from debugging sessions, failed attempts, and solved problems so they don't disappear when the conversation ends. It structures insights into three buckets: discoveries (bugs and root causes), patterns (reusable solutions), and agent recommendations (workflows you've repeated enough times that automation makes sense). The skill hooks into Kuzu memory backend and suggests updates to PATTERNS.md. Honestly most valuable after you've spent 45 minutes debugging something obscure, since it forces you to write down what actually went wrong and why, which is the stuff you'll forget in two weeks but desperately need when the issue resurfaces.
Install to Claude Code
npx -y skills add rysweet/amplihack --skill knowledge-extractor --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
