jleechanorg/jleechan-skills/evidence-review

Claude Code and agent skill by jleechanorg/jleechan-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Review claim coverage, integrity and provenance with an explicit evidence verdict.

Install

npx vskill@latest install jleechanorg/jleechan-skills/evidence-review

SKILL.md

Evidence review

Read evidence-standards, the claimed outcome, repository evidence overlays and exact current revision. Review the actual artifacts and their source records.

Check separately: (1) byte integrity/checksums, (2) source and revision provenance, (3) whether real execution occurred at the claimed layer/model/service, and (4) whether the evidence covers each acceptance claim. Actual model identity comes from authoritative runtime receipts, not a filename or requested flag. Verify privacy/redaction and authorized audience before sharing.

Report one primary verdict: PASS when every required claim is supported; FAIL for contradicted claims or violated mandatory standards; PARTIAL when some required claims are supported but coverage is incomplete; INCONCLUSIVE when provenance/availability prevents a reliable determination. FAIL takes precedence over PARTIAL/INCONCLUSIVE when a mandatory violation is established. Notes are annotations, not a separate WARN approval state. Missing proof never earns PASS.

Use independent native review when required by the active workflow; do not label self-checks independent. Cite file/line or artifact locators, hash/revision, finding severity, missing evidence and a concrete remedy. Public hosting is not required for valid private evidence, and publication is never automatic.

On a head or external-artifact change, inspect the delta before reusing a verdict. Preserve original capture provenance; material changes require new evidence and review. Return the report to the owning workflow without starting unrequested repairs or ending its other authorized work.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jleechanorg/jleechan-skills/evidence-review/badge)](https://verified-skill.com/skills/jleechanorg/jleechan-skills/evidence-review)

Something wrong with this skill or its page? Tell us.