loop-prove
Skill0 starsChanged 5 months agoMITView on GitHub
Run and record the proof command for a loop iteration before completion, publish, merge, deploy, or handoff.
In this repository11 other files it gives its agents.
- loop-anythingSkill
- loop-dog-foodSkill
- loop-recordSkill
- loop-reviewSkill
- loop-triageSkill
- loop-anythingSkill
- loop-dog-foodSkill
- loop-proveSkill
- loop-recordSkill
- loop-reviewSkill
- loop-triageSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill before any completion claim or publish action.
- Very specific: line 12
Read the active task in loop-state.md.
- Distinctive: line 14
Run the full command from the correct working directory.
- Distinctive: line 15
Read the exit code and output.
- Distinctive: line 20
Do not replace the proof command with an easier command after implementation.
- Distinctive: line 21
Do not claim success when the proof command fails.
- Distinctive: line 23
If proof requires network or hosted service writes, confirm the state board allows that service.
≈ “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.
Files
Loop Prove
Use this skill before any completion claim or publish action.
Process
- Read the active task in
loop-state.md. - Identify the proof command recorded during triage.
- Run the full command from the correct working directory.
- Read the exit code and output.
- Record the command, result, and residual risk in
loop-state.md.
Rules
- Do not replace the proof command with an easier command after implementation.
- Do not claim success when the proof command fails.
- Record failed proof runs because they are useful state.
- If proof requires network or hosted service writes, confirm the state board allows that service.
Output
Write:
- command
- exit code
- relevant output
- result
- residual risk
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.