evidence-first
Skill1 starsChanged 2 months agoMITView on GitHub
Defines deterministic evidence, executes the smallest relevant validation, and reports outcomes without invented claims.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- kanthorlabs/dotagentstheir own version, first seen Nov 8, 2026
- timmo001/skillstheir own version, first seen Nov 7, 2026
- yinguangyao/codex-work-skillstheir own version, first seen Oct 20, 2026
- paulasilvatech/awesome-copilot-adventuresword for word, first seen Sep 5, 2026
- Maxrall-Inc/nexrall-skillstheir own version, first seen Aug 19, 2026
- yinguangyao/evidence-first-skilltheir own version, first seen Jul 15, 2026
Other versions6 projects use a version of this.
Word for word · 1
- paulasilvatech/awesome-copilot-adventures★ 1100% same
Edited · 0
None found.
Wrote their own version · 5
- kanthorlabs/dotagents★ 4same name
- timmo001/skills★ 2same name
- yinguangyao/evidence-first-skill★ 2same name
- Maxrall-Inc/nexrall-skills★ 0same name
- yinguangyao/codex-work-skills★ 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
- .github/copilot-instructions.mdCopilot instructions
- canvas-designSkill
- frontend-dashboard-visualizationSkill
- frontend-experience-coreSkill
- frontend-form-interactionsSkill
- frontend-mobile-desktop-testingSkill
- frontend-requirements-and-storiesSkill
- frontend-visual-e2e-testingSkill
- frontend-visual-systemSkill
- ms-presentation-deckSkill
- official-docsSkill
- web-design-reviewerSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
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 8
Use this skill whenever a task changes code, configuration, documentation links, or a runnable lab.
- Distinctive: line 14
Run validation after the change.
- Distinctive: line 17
Never convert “looks correct” into a success claim.
“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
Evidence-first delivery
Use this skill whenever a task changes code, configuration, documentation links, or a runnable lab.
Method
- Translate the requested outcome into observable acceptance criteria.
- Select the smallest existing command or probe that covers each criterion.
- Run validation after the change.
- Record the exact command and whether it passed.
- Distinguish unverified assumptions from verified results.
- Never convert “looks correct” into a success claim.
Evidence examples
- A route exists: start the service and probe the route.
- A link works internally: resolve the target from the source file.
- A customization loads: verify its expected location and required metadata.
- A refactor preserves behavior: run the pre-existing focused tests.
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.