gongshichen/luminacode/qa-report

Claude Code and agent skill by gongshichen/luminacode

Trust tier 2
  • community
LLM review pending
Source check pending

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

Write a durable QA report with evidence, command results, unresolved findings, and verdict rationale.

Install

npx vskill@latest install gongshichen/luminacode/qa-report

SKILL.md

Write QA evidence as <project_root>/QA_REPORT.md.

Before writing:

  • Call GetTeamContext and use its runtime contract as the authoritative Team Acceptance Contract.
  • Do not invent a missing-contract finding because there is no TEAM_ACCEPTANCE_CONTRACT.md file. A file is required only if the runtime contract lists that file in required_artifacts.
  • Keep the report concise enough for repair: normally 80-180 lines for small/medium tasks.

Required sections:

  1. Scope verified
  • User request summary.
  • Runtime Team Acceptance Contract summary from GetTeamContext.
  • Documents checked: PRD, UX design, plans, interface contract, integration report.
  1. Environment
  • Working directory.
  • Runtime/tool versions when relevant.
  • Setup commands and services started.
  1. Command evidence
  • Each required command from the Team Acceptance Contract.
  • Exit status.
  • Short stdout/stderr summary.
  • Whether output proves the requirement.
  1. Integration evidence
  • Real user-facing component path exercised.
  • Backend/API/storage/tooling contract exercised.
  • Positive, negative, and persistence checks where applicable.
  1. Parent workspace cleanliness
  • Files present in the parent directory before/after when named-project work is used.
  • Any byproducts and cleanup performed.
  1. Findings
  • Blocking findings.
  • Non-blocking findings.
  • Deferred items and why they are safe.
  • Any failure of an explicit user requirement, PRD acceptance criterion, UX requirement, or runtime contract item belongs in blocking findings. Examples include localized-error requirements, required exit-code semantics, required integration behavior, or required artifacts.
  • Do not classify an explicit requirement violation as non-blocking just because the happy path works or the issue is common in a framework.
  1. Verdict
  • pass, fail, or not_applicable.
  • Rationale and evidence references.

After writing the report, call SubmitGateVerdict and reference QA_REPORT.md in the evidence.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

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

Source

Popularity

7-day trend score
0

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/gongshichen/luminacode/qa-report/badge)](https://verified-skill.com/skills/gongshichen/luminacode/qa-report)

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