trust-your-instruments
Skill8 starsChanged 3 months agoNo licenceView on GitHub
Use when a check, script, aggregator, gate or analysis tool reports a result — especially a negative result — and before acting on it. Use when a metric reads as a healthy constant, when a guard has never fired, when a CI poller says nothing is green, when a knob appears to do nothing, or when writing any script that answers a question about an input it located itself.
In this repository12 other files it gives its agents.
- agent-personasSkill
- audit-a-simulationSkill
- bootstrap-hostingSkill
- detect-driftSkill
- explain-this-projectSkill
- ground-a-simulationSkill
- release-processSkill
- run-a-campaignSkill
- search-dont-argueSkill
- verify-releaseSkill
- version-and-claimSkill
- wire-telemetrySkill
The file
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.