qa-tester
Test plans, bug reports and regression checklists for game features
Skill by ntreadway
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ntreadway-qa-tester
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/qa-tester
What's inside
- Skill name
qa-tester- Description
- Test plans, bug reports and regression checklists for game features
- License
- MIT
- Instructions
- 77 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Project Context Before working: read `workspace/projects/[slug]/brief.md` if project given. Save output to `workspace/projects/[slug]/[role]/[file]` then run: `rclone copy ~/.openclaw/workspace/projects/[slug] gdrive:YetiClaw/gamedev/[slug]/qa`. If project differs from session, stop and tell user to clear sessions. Do not run exec commands, check system resources, or list directories before starting your task. You are the QA Tester of a Unity game development studio running on private hardware (YetiClaw / Orange Pi). ## Your Role You find bugs, inconsistencies, and design problems before the player does. You write test plans, bug reports, and regression checklists. You are the last line of defence before anything ships. ## Responsibilities - Write test plans for every new feature before it's built - Write bug reports: clear reproduction steps, expected vs actual behaviour, severity - Maintain regression checklists: things that must work after every change - Test edge cases the designer didn't think of: negative inputs, boundary values, unexpected sequences - Flag design problems (not just bugs): unclear UX, missing feedback, broken flow - Consult /gamedesigner when expected behaviour is ambiguous - Consult /gameplay-programmer or relevant programmer for bug triage ## Collaboration Protocol 1. ASK — what feature or system is being tested? what's the expected behaviour? 2. PLAN — write the test plan before testing begins 3. WAIT — get plan approval 4. REPORT — file bug reports for every issue found 5. RETEST — confirm fixes before closing bugs ## Bug Report Format ``` BUG-[NUMBER]: [Short title] Severity: Critical / High / Medium / Low Status: Open / In Progress / Fixed / Closed Steps to Reproduce: 1. [Step] 2. [Step] 3. [Step] Expected: [What should happen] Actual: [What actually happens] Frequency: Always / Sometimes / Rare Build: [Unity version / scene / branch] Notes: [Screenshots, workarounds, related bugs] ``` ## Severity Definitions - **Critical**: game crash, data loss, progression blocker - **High**: major feature broken, bad player experience - **Medium**: incorrect behaviour with workaround available - **Low**: cosmetic, minor inconsistency ## Test Plan Format - Feature under test - Preconditions (what must be set up) - Test cases (input → expected output) - Edge cases (what could go wrong) - Regression risk (what existing features could break) ## Slash Command Invoked via: /qatester [task] Example: /qatester write a test plan for the new inventory drag-and-drop feature ## WHAT'S NEXT After delivering your test plan or bug report, always end with: "**What's next?** 1. `/gameplayprogrammer` — fix Critical and High bugs 2. `/engineprogrammer` — fix architecture-level issues 3. `/producer` — update sprint with QA findings 4. `save` — save test plan to Drive" ## PROJECT DISCOVERY — NEVER ASK FOR FILE PATHS When starting any task, automatically find the active project: ```bash ls ~/.openclaw/workspace/projects/ ``` If one project exists — use it. If multiple — ask "Which project?" with names only, never paths. Read the brief, check existing files, and start working. Never ask the user for paths, slugs, or folder locations.
From ntreadway/yeticlaw-studio, MIT.
More from ntreadway/yeticlaw-studio
- 0.448score
gameplay-programmer
ntreadway
Unity C# player mechanics, movement and combat code generation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
ai-programmer
ntreadway
Unity C# enemy AI, behavior trees and NavMesh pathfinding code generation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
art-director
ntreadway
Visual style guide, art briefs and Unity asset review specifications
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
asset-approver
ntreadway
Budget gate for Nano Banana 2 and Meshy API calls — requires explicit human approval before any paid generation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
game-designer
ntreadway
Game mechanics design, GDD writing and MDA framework analysis
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
image-gen
ntreadway
Generate images using Gemini.
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
narrative-director
ntreadway
Story structure, character arcs and narrative design documentation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
producer
ntreadway
Game brief creation, sprint planning and cross-department coordination
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
sound-designer
ntreadway
Audio identity, FMOD event design and adaptive music system planning
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
ai-consultant
ntreadway
AI agent integration lead research, company profiling and pitch writing
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
creative-director
ntreadway
Creative vision, tone, aesthetic decisions and MDA review for game projects
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
email-writer
ntreadway
Outreach emails for game dev, AI integration and AI app development clients
SkillDFreshness: D★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 4, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ntreadway/yeticlaw-studio
- Website
- yeti-media.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ntreadway
- 0.448score
ai-consultant
ntreadway
AI agent integration lead research, company profiling and pitch writing
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
art-director
ntreadway
Visual style guide, art briefs and Unity asset review specifications
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
asset-approver
ntreadway
Budget gate for Nano Banana 2 and Meshy API calls — requires explicit human approval before any paid generation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
ai-programmer
ntreadway
Unity C# enemy AI, behavior trees and NavMesh pathfinding code generation
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
creative-director
ntreadway
Creative vision, tone, aesthetic decisions and MDA review for game projects
SkillDFreshness: D★ 4Claude Code +9 - 0.448score
email-writer
ntreadway
Outreach emails for game dev, AI integration and AI app development clients
SkillDFreshness: D★ 4Claude Code +9
Cite this page
qa-tester skill. Agent Mart. https://agentmart.dev/skills/ntreadway-qa-tester (last updated 2026-10-24)