ground-truth-discipline
Skill4 starsChanged 7 days agoNo licenceView on GitHub
Foundational, apply-first discipline. Before building, optimizing, experimenting, or explaining ANY system, establish that its three representations agree — the formal spec/claim, the implementation that actually runs, and the prose/docs that describe it. They must be one. And treat every claim about what a system does or why as a hypothesis until verified against the deployed artifact and, for causal claims, an isolating measurement. A conditional/qualified claim must state its conditions where it is most prominently asserted (abstract, headline, summary), not only where it is proved. Load-bearing claims (ones many things depend on) should be confirmed by two or more INDEPENDENT routes (different methods, not the same check twice), so the foundation is trustworthy up front instead of re-audited later. Heuristics and tuning come AFTER a consistent foundation, never before.
In this repository10 other files it gives its agents.
- decision-gateSkill
- decision-under-irreversibilitySkill
- diagnostic-disciplineSkill
- enforcement-disciplineSkill
- operating-modesSkill
- pin-and-traceSkill
- pr-checklistSkill
- reader-firstSkill
- triage-against-historySkill
- unattended-opsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.