code-proof
Skill4 starsChanged 26 days agoNo licenceView on GitHub
Produce a checkable correctness proof for a piece of code, an algorithm, or a procedure — a formalized claim, independently-discharged lemmas, a composed proof using the technique that fits the claim's shape (induction / contradiction via minimal counterexample / finite case-analysis / reduction to a trusted reference), a genuine attempted refutation, and a verdict of Proved / Disproved / Unresolved. Never returns Proved for a claim quantified over an unbounded parameter unless a valid induction actually closes it. Use when the user asks to prove a function, algorithm, or procedure correct, asks "is this really race-free / idempotent / never-stale", or wants a rigorous correctness argument rather than a claim backed only by tests passing. Proves code correct, not that a ticket is worth doing.
In this repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- block-diagramSkill
- brainstormSkill
- buildSkill
- call-treeSkill
- checkpoint-commitsSkill
- code-tidySkill
- codifySkill
- coding-standardsSkill
- consistencySkill
- escalateSkill
- experimentSkill
- explainSkill
- hparam-priorsSkill
- minimal-coverSkill
- ml_loggingSkill
- notesSkill
- outlineSkill
- plan-docSkill
- prior-workSkill
- project-briefSkill
- proof-of-valueSkill
- recapSkill
- reflectSkill
- repo-layoutSkill
- reportSkill
- rl-env-mvpSkill
- run-triageSkill
- schema-diagramSkill
- sequence-diagramSkill
- sft-env-mvpSkill
- skill-auditSkill
- skills-repo-accessSkill
- spec-docSkill
- sprint-tasksSkill
- test-planSkill
- tldrSkill
- tune-loopSkill
- tune-preflightSkill
- tune-reportSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
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.
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.