closed-loop-testing
Skill0 starsChanged 7 months agoMITView on GitHub
Collect fresh evidence into a task-local evidence pack and turn implemented work into a structured verdict before calling it done.
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.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use when a task needs fresh evidence before it can be treated as complete.
- Distinctive: line 20
update the task-local evidence pack
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Closed Loop Testing
Use when a task needs fresh evidence before it can be treated as complete.
Read First
skills/harness/closed-loop-testing/references/evidence-pack-format.mdskills/harness/closed-loop-testing/assets/evidence-index.jsonskills/harness/closed-loop-testing/assets/verdict.jsonprotocols/verify.md
Goals
- collect the strongest available evidence
- update the task-local evidence pack
- separate implemented, verified, unverified, and remaining risks
Process
- identify the strongest available validation path
- collect evidence into
evidence-index.json - summarize the outcome in
verdict.json - escalate to
verifyorqawhen the task still needs stronger proof
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- aleiby/claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex/AGENTS.mdAGENTS.md
- claude/CLAUDE.mdCLAUDE.md
- backend-refactorSkill
- buildSkill
- discussSkill
- docSkill
- frontend-designSkill
- frontend-refactorSkill
- low-altitude-interviewerSkill
- pdfSkill
- repo-bootstrapSkill
- skill-maintenanceSkill
- tdd-executionSkill
- architecture-guardrailsSkill
- harness-marathonSkill
- task-harnessSkill
- api-designSkill
- architecture-designSkill
- brainstormSkill
- codex-record-retrospectiveSkill
- database-designSkill
- integration-designSkill
- map-codebaseSkill
- migration-designSkill
- observability-designSkill
- planSkill
- query-optimizationSkill
- scalability-checkSkill
- service-boundary-reviewSkill
- api-change-checkSkill
- browseSkill
- bugfix-verificationSkill
- debugSkill
- incident-debugSkill
- performance-investigationSkill
- qaSkill
- reviewSkill
- security-reviewSkill
- verifySkill
- release-checkSkill
- shipSkill
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.