kill-test-first
Skill3 starsChanged 4 months agoCC-BY-4.0View on GitHub
[决策:预注册] Pre-registration audit for new research directions, quant strategies, or thesis topics: falsifiable hypothesis, prior-art check, strongest counter-argument, death criteria before results, cheapest falsification with strong baseline, three-state verdict (GO/STOP/REDESIGN). Use before committing resources to a new direction. Not for bug fixes, experiment reproduction, or routine controlled experiments.
In this repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- session-endSkill
- write-claude-mdSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.