Running the Bug Review Board (QA Pass)
Runs a real-user QA pass on your app and produces P0/P1/P2 bug reports, an HTML QA dashboard, and a YES/NO ship verdict.
Dev & CodingAdvanced★ 124⑂ 19AI score 9/10Last updated: Jul 19, 2026
What it does
- Real-user QA passes: the agent drives the actual app (clicks, forms, navigation) instead of declaring PASS from code inspection.
- App discovery first: reads product spec / README / phase docs / open bug index, then detects the surface (web, iOS/iPadOS, Electron·Tauri, native macOS, or a mixed monorepo) and activates the matching playbook.
- Structured bug filing: files bugs immediately on FAIL with reproduction steps, evidence (snapshots, verbatim console errors), impact, and P0/P1/P2 priority.
- Bi-directional tracker sync: discovers and confirms Linear / GitHub / Jira / Notion, records the choice in
qa-config.json, pushes new bugs and pulls status changes without silent overwrites. - HTML QA dashboard: regenerates a typography-driven static report; markdown stays the source of truth.
- Clear sign-off: a coordinator merge doc whose top line is "Phase N ready? YES/NO", plus a paste-ready handoff prompt.
- Interactive BRB: a deliberately separate triage session with duplicate/cluster heuristics that suggest but never auto-merge.
Who it's for
- Solo devs and small teams who keep shipping bugs that users hit first
- PMs who need evidence-backed ship/no-ship decisions per phase or sprint
- Teams running a web + iOS monorepo
- Teams standing up QA process (test plans, bug templates, gates) from scratch
Examples
- "QA this phase" → the skill reads the spec, generates a manual test plan, runs scenarios at mobile 375×812 / tablet 768×1024 / desktop 1280×800, files bugs, and returns a YES/NO verdict.
- "Is this build ready to ship?" → it checks open P0/P1s against phase gates and hands back a merge doc listing blockers and unrun scenarios.
- "Let's triage the bug backlog" → in a separate BRB session it pulls tracker status, surfaces duplicate candidates with the heuristic that flagged them, flips statuses, writes minutes, and regenerates the HTML report.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/RayFernando1337/rayfernando-skills/HEAD/plugins/running-bug-review-board/skills/running-bug-review-board/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the plugins/running-bug-review-board/skills/running-bug-review-board folder from the GitHub repo RayFernando1337/rayfernando-skills into my ~/.claude/skills/running-bug-review-board/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/RayFernando1337/rayfernando-skills.git && mkdir -p ~/.claude/skills && cp -r rayfernando-skills/plugins/running-bug-review-board/skills/running-bug-review-board ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/RayFernando1337/rayfernando-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r rayfernando-skills/plugins/running-bug-review-board/skills/running-bug-review-board ~/.claude/skills/ - Verify with
ls ~/.claude/skills/running-bug-review-board— you should seeSKILL.md,references/, andscripts/. - Start Claude Code inside the project you want to test.
- For web apps, have a browser driver available (cursor-ide-browser MCP, chrome-devtools-mcp, or Playwright); for iOS apps, also install a simulator-driving companion skill.
- Trigger it with a prompt like "QA this app" or "is this ready to ship?". If the repo has no QA folder yet, run
bash ~/.claude/skills/running-bug-review-board/scripts/scaffold-qa.sh "$PWD" 1to scaffold it.
View source on GitHub ↗License: Apache-2.0