collect-evidence
Skill1 starsChanged 34 days agoMITView on GitHub
Collect reproducible results for checks already selected by a caller, using documented commands or a running application. Use to execute checks reliably and distinguish observations, failures, unavailable checks and stale results. Does not choose a test strategy, independently review a change, fix code or declare acceptance.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Greg-Klein/implementation-factoryword for word, first seen Oct 11, 2026
- yezhwi/superpowers-engineering-harnesstheir own version, first seen Sep 29, 2026
- iangogentic/venture-labtheir own version, first seen Jul 31, 2026
- Omerfaruk-aydn/Agent_OStheir own version, first seen Jul 20, 2026
Other versions4 projects use a version of this.
Word for word · 1
- Greg-Klein/implementation-factory★ 1100% same
Edited · 0
None found.
Wrote their own version · 3
- yezhwi/superpowers-engineering-harness★ 3same name
- Omerfaruk-aydn/Agent_OS★ 1same name
- iangogentic/venture-lab★ 0same 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- clarify-specSkill
- document-changeSkill
- figma-reviewSkill
- gh-github-apiSkill
- gitlab-ticketsSkill
- glab-gitlab-apiSkill
- howSkill
- review-changeSkill
- self-checkSkill
- unslopSkill
- whySkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
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 13
Check that the source and environment stayed stable during measurement.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Collect evidence
Input: selected checks, their expected observations and sources, repository or app, and permitted execution scope. Return observations with reproduction details and limitations. The caller owns any output files and verdict.
- Establish what is being measured: code version, relevant local changes, command or route, environment and expected result. Do not expose credentials.
- For command execution, read commands.md. For browser observations, read browser.md. Load only the applicable reference.
- Execute only authorized checks. Record actual results, not what the command or code was supposed to do. Never weaken an assertion or change the implementation to obtain a passing measurement.
- Check that the source and environment stayed stable during measurement. If they moved, return a non-conclusive observation for remeasurement on stable code.
- Return one result per selected check: method, exact command or reproduction steps, expected and actual, version, attachments when useful, and a concrete obstacle if blocked. Distinguish fresh execution from inspecting another person's evidence.
This skill supplies measurement mechanics only. The developer, code reviewer and QA choose their own checks under their separate methods. Do not turn a list supplied by the author into a claim of complete coverage.
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.