evidence
Skill0 starsChanged 19 days agoMITView on GitHub
Frame a concrete goal, run an evidence-led task, or judge completed work against claims and checks. Use when asked for an evidence workflow, a reusable goal prompt, a read-only judge of one artifact or parallel agent results, an evidence-based report rewrite, or a domain workflow. Not for routine test execution (verify) or an adversarial code-change decision ledger (second-opinion).
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jacksnxly/keryxtheir own version, first seen Nov 8, 2026
- adiutama/skillstheir own version, first seen Nov 1, 2026
- hoophq/hooptheir own version, first seen Oct 17, 2026
- ltlongtma/solo-sdlctheir own version, first seen Oct 2, 2026
- SoFarSoGoodya/mathmodel-weavetheir own version, first seen Oct 2, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- hoophq/hoop★ 848same name
- ltlongtma/solo-sdlc★ 2same name
- SoFarSoGoodya/mathmodel-weave★ 2same name
- adiutama/skills★ 1same name
- jacksnxly/keryx★ 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 repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/comments.mdcCursor rule
- .cursor/rules/commit-messages.mdcCursor rule
- .cursor/rules/git-workflow.mdcCursor rule
- .cursor/rules/manage-stack.mdcCursor rule
- .cursor/rules/no-worktrees.mdcCursor rule
- manage-stackSkill
- convert-as-skillSkill
- create-agentSkill
- create-agents-mdSkill
- create-commandSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- retrospectiveSkill
- super-architectureSkill
- super-cachingSkill
- super-elixirSkill
- super-nodejsSkill
- super-protobufSkill
- super-tech-blueprintSkill
- atomic-semantic-commitSkill
- code-reviewSkill
- create-bruno-collectionSkill
- create-documentationSkill
- create-ticketsSkill
- ready-specSkill
- write-adrSkill
- write-changelogSkill
- write-mr-descriptionSkill
- write-planSkill
- write-postmortemSkill
- write-runbookSkill
- noslopSkill
- output-saversSkill
- safe-refactorSkill
- tddSkill
- verifySkill
- get-movingSkill
- later-listSkill
- standupSkill
- challenge-meSkill
- codebase-learnerSkill
- researchSkill
- second-opinionSkill
- traceSkill
- color-kitSkill
- design-system-kitSkill
- diagramSkill
- infographicSkill
- product-polish-workflowSkill
- prototype-wireframeSkill
- ui-ux-kitSkill
- find-skillsSkill
- handoffSkill
- rumblingSkill
- use-levistackSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
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 53
Use this entry point when the user asks to frame, run, or judge work through evidence.
- Distinctive: line 84
Every stated fact names evidence, and every completion claim names a fresh check or an explicit limit.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Use this entry point when the user asks to frame, run, or judge work through evidence. Keep each mode separate. A request to judge existing work stays read-only; a request to run a task may edit within its authorized scope.
Select a mode
| Request | Mode | Read |
| "Turn this idea into a goal", "write a goal prompt for a fresh session" | Goal | goal.md |
| "Use evidence to do this task", "run the evidence workflow", or "run the evidence loop" | Run | run.md |
| "Evidence plan" or "evidence workflow plan" | Plan | run.md, stop before changes |
| "Audit the evidence", "judge this work", "judge these agent results", or "judge suite" | Judge | judge.md |
| "Rewrite the evidence report" | Report | report.md |
| "Build a domain workflow" or "make a domain adapter" | Domain | domain.md |
The modes share three rules. State what result would count as done. Read the actual source of each fact before using it. Match every completion claim to a check run on the finished artifact. A source conflict or missing verification stays visible in the result. Goal writes a prompt for a later session only when the user requests that prompt; otherwise Run carries out the task here.
Use the project's instructions and the matching task-specific skill inside Run. Do not replace a specialized security, medical, legal, finance, deployment, or incident procedure with this general workflow. Reversible local edits follow the user's task authorization. Posting, publishing, pushing, deploying, installing, and destructive actions require authorization for the exact action.
Related skills
use-levistack: default catalog entry point when the user did not request this workflow.verify: run fresh, claim-matched checks and report limits.second-opinion: challenge a code change with independent reviewers and resolve its decision ledger. Judge checks claims and artifacts; it does not replace that review.rumbling: coordinate parallel agents on independent tasks, competing solutions, or one judgment question, then hand their completed results to Judge.create-skill: author a new domain skill with evals and catalog metadata.convert-as-skill: adapt or merge existing domain material rather than inventing a new skill.diagram: draw a technical flowchart when branching needs a figure.infographic: explain an evidence-backed workflow visually for its audience.
Done when
- The requested mode produced its own result without leaking into another mode.
- Every stated fact names evidence, and every completion claim names a fresh check or an explicit limit.
- evals/evals.json covers the entry modes, parallel-result judgment, and requests that should use another skill.
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.