Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude-
llms.txt1 starsChanged 39 days agoMITView on GitHub
Five Claude Code / Agent Skills that force local proof before an agent may say "faster", "tests pass", or "done". Repo: https://github.com/David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- npx skills add David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- Claude Code: /plugin marketplace add David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- /plugin install dont-trust-faster@dont-trust-faster Python 3 stdlib. Linux/macOS for perf-verifier. MIT.
In this repository5 other files it gives its agents.
- code-verifierSkill
- context-saverSkill
- perf-verifierSkill
- prompt-clarifierSkill
- repo-mapSkill
The file
Files
# Don't trust "I made it faster" Five Claude Code / Agent Skills that force local proof before an agent may say "faster", "tests pass", or "done". Repo: https://github.com/David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- ## Install npx skills add David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- Claude Code: /plugin marketplace add David-Florian2013/Stop-trusting-made-it-faster-here-is-5-best-skills-for-Claude- /plugin install dont-trust-faster@dont-trust-faster ## Skills - skills/perf-verifier/SKILL.md — statistical before/after, profile, scale. scripts/pf.py - skills/code-verifier/SKILL.md — tests, imports, OWASP-ish scan, test-tamper. scripts/vf.py - skills/context-saver/SKILL.md — outline/peek/squeeze. scripts/cs.py - skills/repo-map/SKILL.md — writes .claude/MAP.md - skills/prompt-clarifier/SKILL.md — restates vague requests and waits Python 3 stdlib. Linux/macOS for perf-verifier. MIT.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

