Loop triage
Select one bounded task for an agent loop from visible state, real repo evidence, permission boundaries, and a named proof command.From its SKILL.md
npx -y skills add rossinsilico/loop-anything --skill loop-triageAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.0 KB, 186 tokens by cl100k_base, as published. Nobody here has run it
Loop Triage
Use this skill at the start of a loop iteration.
Inputs
loop-state.mdloop-contract.md- Current repository state
- Any explicit human instruction for this run
Process
- Read
loop-state.mdandloop-contract.md. - Inspect the real target named by the state board.
- Identify candidate tasks that fit inside one loop iteration.
- Select exactly one task.
- Name the proof command before implementation starts.
- Stop if the task needs destructive action, hidden credentials, or a broader permission boundary than the state board allows.
Output
Write or update the Active Task section in loop-state.md with:
- task
- reason
- expected files or services
- proof command
- stop condition
Do not implement until the active task and proof command are clear.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.