sk Skill · ElliotJLT
agent-audit
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
Open on skills.sh ↗read 2026-09-15
- installs 8w
- 0
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 7
markdownPython
- Host repository
- ElliotJLT/Claude-Skill-Potions
- Allowed tools
- bash: grep, find, wc, python, file: read, write, mcp: task
- Host stars
- 62
- Host language
- Python