kyleamathews/linux-config/evaluate-review

Claude Code and agent skill by kyleamathews/linux-config

Trust tier 3
  • community
Source check pending

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

Evaluate an external pull-request review for technical accuracy, reviewer quality, and closure of the underlying bug class through applicable oracles. Preserve every finding in a lossless audit. Use when review findings need code verification, fixes, an omission audit, or a separate PR readiness verdict.

Install

npx vskill@latest install kyleamathews/linux-config/evaluate-review

SKILL.md

evaluate-review

Use the review to close the class of bug it reveals. For each behavioral finding, inventory the subsystem's observable guarantees, derive the relevant law and its authority, and challenge how that law interacts with neighboring guarantees. When an oracle applies, encode the law over legal histories and public observation cuts using an independent judgment. A passing reproduction or a complete item ledger is diagnosis, not closure: show that the oracle rejects the original behavior or a plausible wrong implementation, including a one-trace fix when relevant. Keep any unenforced part of the law open with its missing witness.

Before you work on findings one at a time, look at all of them together. Plan the oracle changes that would generate every behavioral finding, make those changes first, and run them against unchanged production.

When a review involves oracles, present the result as law, experiment, inference, and remaining enforcement work before the item ledger. Deferral is a rare, fully justified exception.

When asked whether a PR is ready, give a separate readiness verdict. A completed review audit or a bounded passing oracle cannot establish whole-PR readiness.

Read references/workflow.md in full, then follow those instructions exactly for the current request.

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/kyleamathews/linux-config/evaluate-review/badge)](https://verified-skill.com/skills/kyleamathews/linux-config/evaluate-review)

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