evidence-verification
Skill1 starsChanged 11 days agoApache-2.0View on GitHub
Verify technical claims and review findings against source, contracts, tests, and runtime evidence while seeking counterevidence. Use when deciding whether an assertion is supported or reconciling conflicting findings.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- myshra777-ai/garudatheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- myshra777-ai/garuda★ 4same 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 repository24 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- ab-testingSkill
- artifact-inspectionSkill
- comparative-evaluationSkill
- cue-synced-demoSkill
- design-analysisSkill
- design-writingSkill
- intent-alignmentSkill
- interactive-experienceSkill
- narrative-transitionsSkill
- pr-description-writingSkill
- presenter-scriptSkill
- promptlings-memory-captureSkill
- pr-videoSkill
- reasoning-first-narrationSkill
- reasoning-first-writingSkill
- review-comment-writingSkill
- review-ensembleSkill
- spec-deliverySkill
- technical-demo-productionSkill
- technical-illustrationSkill
- technical-investigationSkill
- test-analysisSkill
- tts-setupSkill
The file
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 16
Search for counterevidence, such as a guard, alternate caller, rollback, schema constraint, or test path that invalidates the proposed …
- Distinctive: line 24
Stop when material claims are resolved or the next useful check is unavailable.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Evidence Verification
Goal
Determine which claims the evidence supports, contradicts, or leaves unresolved. Agreement between reviewers is provenance, not proof.
Method
- Extract the material factual claims, target revision, claimed triggering conditions, and asserted consequence. Resolve the cited source and surrounding context, including affected producers and consumers.
- Identify a falsifiable check for each claim: source inspection, a contract reference, a focused test, or a bounded runtime observation. Perform only authorized checks and record what actually ran.
- Search for counterevidence, such as a guard, alternate caller, rollback, schema constraint, or test path that invalidates the proposed mechanism. Check applicability rather than accepting a matching pattern.
- Classify the claim as supported, contradicted, or unresolved. Keep missing evidence distinct from evidence of failure. Revise or reject an objection when its mechanism is disproved.
- Reconcile conflicting observations using the target and underlying evidence. Preserve a supported singleton finding. Deduplicate the same root cause without discarding distinct triggering conditions or consequences.
Return and stop
Return the claim, evidence and counterevidence locations, check results, disposition, and material limitations. For defects, explain what fails, under what conditions, and why. Recommend what fully addresses the problem rather than optimizing for fix size.
Stop when material claims are resolved or the next useful check is unavailable. State what is missing and which conclusion it prevents. Never certify a revision different from the one examined or infer global correctness from a finite set of checks.
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.