shaun0927/codex-superskills/ultraqa
Claude Code and agent skill by shaun0927/codex-superskills
- community
Checking that the SKILL.md file is still in the repository.
QA cycling workflow - test, verify, fix, repeat until goal met
Install
npx vskill@latest install shaun0927/codex-superskills/ultraqaSKILL.md
UltraQA Skill
[ULTRAQA ACTIVATED - AUTONOMOUS QA CYCLING]
Overview
You are now in ULTRAQA mode - an autonomous QA cycling workflow that runs until your quality goal is met.
Cycle: qa-tester → architect verification → fix → repeat
Goal Parsing
Parse the goal from arguments. Supported formats:
| Invocation | Goal Type | What to Check | |
|---|---|---|---|
/superskills:ultraqa --tests | tests | All test suites pass | |
/superskills:ultraqa --build | build | Build succeeds with exit 0 | |
/superskills:ultraqa --lint | lint | No lint errors | |
/superskills:ultraqa --typecheck | typecheck | No TypeScript errors | |
/superskills:ultraqa --custom "pattern" | custom | Custom success pattern in output |
If no structured goal provided, interpret the argument as a custom goal.
Cycle Workflow
Cycle N (Max 5)
- RUN QA: Execute verification based on goal type
--tests: Run the project's test command--build: Run the project's build command--lint: Run the project's lint command--typecheck: Run the project's type check command--custom: Run appropriate command and check for pattern--interactive: Use qa-tester for interactive CLI/service testing:
`` Task(subagent_type="superskills:qa-tester", model="balanced", prompt="TEST: Goal: [describe what to verify] Service: [how to start] Test cases: [specific scenarios to verify]") ` Recommended model tier: balanced`
- CHECK RESULT: Did the goal pass?
- YES → Exit with success message
- NO → Continue to step 3
- ARCHITECT DIAGNOSIS: Spawn architect to analyze failure
`` Task(subagent_type="superskills:architect", model="high-reasoning", prompt="DIAGNOSE FAILURE: Goal: [goal type] Output: [test/build output] Provide root cause and specific fix recommendations.") ` Recommended model tier: high-reasoning`
- FIX ISSUES: Apply architect's recommendations
`` Task(subagent_type="superskills:executor", model="balanced", prompt="FIX: Issue: [architect diagnosis] Files: [affected files] Apply the fix precisely as recommended.") ` Recommended model tier: balanced`
- REPEAT: Go back to step 1
Exit Conditions
| Condition | Action | |
|---|---|---|
| Goal Met | Exit with success: "ULTRAQA COMPLETE: Goal met after N cycles" | |
| Cycle 5 Reached | Exit with diagnosis: "ULTRAQA STOPPED: Max cycles. Diagnosis: ..." | |
| Same Failure 3x | Exit early: "ULTRAQA STOPPED: Same failure detected 3 times. Root cause: ..." | |
| Environment Error | Exit: "ULTRAQA ERROR: [tmux/port/dependency issue]" |
Observability
Output progress each cycle:
State Tracking
Track state in .superskills/ultraqa-state.json:
Cancellation
User can cancel with /superskills:cancel which clears the state file.
Important Rules
- PARALLEL when possible - Run diagnosis while preparing potential fixes
- TRACK failures - Record each failure to detect patterns
- EARLY EXIT on pattern - 3x same failure = stop and surface
- CLEAR OUTPUT - User should always know current cycle and status
- CLEAN UP - Clear state file on completion or cancellation
STATE CLEANUP ON COMPLETION
IMPORTANT: Delete state files on completion - do NOT just set `active: false`
When goal is met OR max cycles reached OR exiting early:
This ensures clean state for future sessions. Stale state files with active: false should not be left behind.
Begin ULTRAQA cycling now. Parse the goal and start cycle 1.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ultraqa/SKILL.md
Popularity
- 7-day trend score
- 0
Refreshed 26 Apr 2026, 6 months ago.
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
[](https://verified-skill.com/skills/shaun0927/codex-superskills/ultraqa)