agentleFS
lza6lza6/claw-code-tingfeng/skills/ultraqa/SKILL.md

ultraqa

Skill5 starsChanged 17 days agoMITView on GitHub

QA cycling workflow - test, verify, fix, repeat until goal met

5 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default to concise, evidence-dense progress and completion reporting unless the user or risk level requires more detail.

    line 14
  2. Distinctive:

    Treat newer user task updates as local overrides for the active workflow branch while preserving earlier non-conflicting constraints.

    line 15
  3. Distinctive:

    If correctness depends on additional inspection, retrieval, execution, or verification, keep using the relevant tools until the QA cycle is …

    line 16
  4. Distinctive:

    If no structured goal provided, interpret the argument as a custom goal.

    line 35
  5. Very specific:

    Use omx_state MCP tools for UltraQA lifecycle state.

    line 101
  6. Distinctive:

    PARALLEL when possible: - Run diagnosis while preparing potential fixes

    line 130
  7. Very specific:

    When goal is met OR max cycles reached OR exiting early, run $cancel or call:

    line 138
  8. Distinctive:

    Use MCP state cleanup rather than deleting files directly.

    line 142

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UltraQA Skill

[ULTRAQA ACTIVATED - AUTONOMOUS QA CYCLING]

Overview

GPT-5.4 Guidance Alignment

  • Default to concise, evidence-dense progress and completion reporting unless the user or risk level requires more detail.
  • Treat newer user task updates as local overrides for the active workflow branch while preserving earlier non-conflicting constraints.
  • If correctness depends on additional inspection, retrieval, execution, or verification, keep using the relevant tools until the QA cycle is grounded.
  • Continue through clear, low-risk, reversible next steps automatically; ask only when the next step is materially branching, destructive, or preference-dependent.

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:

InvocationGoal TypeWhat to Check
/ultraqa --teststestsAll test suites pass
/ultraqa --buildbuildBuild succeeds with exit 0
/ultraqa --lintlintNo lint errors
/ultraqa --typechecktypecheckNo TypeScript errors
/ultraqa --custom "pattern"customCustom success pattern in output

If no structured goal provided, interpret the argument as a custom goal.

Cycle Workflow

Cycle N (Max 5)

  1. 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:
      delegate(role="qa-tester", tier="STANDARD", task="TEST:
      Goal: [describe what to verify]
      Service: [how to start]
      Test cases: [specific scenarios to verify]")
  2. CHECK RESULT: Did the goal pass?
    • YES → Exit with success message
    • NO → Continue to step 3
  3. ARCHITECT DIAGNOSIS: Spawn architect to analyze failure
    delegate(role="architect", tier="THOROUGH", task="DIAGNOSE FAILURE:
    Goal: [goal type]
    Output: [test/build output]
    Provide root cause and specific fix recommendations.")
  4. FIX ISSUES: Apply architect's recommendations
    delegate(role="executor", tier="STANDARD", task="FIX:
    Issue: [architect diagnosis]
    Files: [affected files]
    Apply the fix precisely as recommended.")
  5. REPEAT: Go back to step 1

Exit Conditions

ConditionAction
Goal MetExit with success: "ULTRAQA COMPLETE: Goal met after N cycles"
Cycle 5 ReachedExit with diagnosis: "ULTRAQA STOPPED: Max cycles. Diagnosis: ..."
Same Failure 3xExit early: "ULTRAQA STOPPED: Same failure detected 3 times. Root cause: ..."
Environment ErrorExit: "ULTRAQA ERROR: [tmux/port/dependency issue]"

Observability

Output progress each cycle:

[ULTRAQA Cycle 1/5] Running tests...
[ULTRAQA Cycle 1/5] FAILED - 3 tests failing
[ULTRAQA Cycle 1/5] Architect diagnosing...
[ULTRAQA Cycle 1/5] Fixing: auth.test.ts - missing mock
[ULTRAQA Cycle 2/5] Running tests...
[ULTRAQA Cycle 2/5] PASSED - All 47 tests pass
[ULTRAQA COMPLETE] Goal met after 2 cycles

State Tracking

Use omx_state MCP tools for UltraQA lifecycle state.

  • On start: state_write({mode: "ultraqa", active: true, current_phase: "qa", iteration: 1, started_at: "<now>"})
  • On each cycle: state_write({mode: "ultraqa", current_phase: "qa", iteration: <cycle>})
  • On diagnose/fix transitions: state_write({mode: "ultraqa", current_phase: "diagnose"}) state_write({mode: "ultraqa", current_phase: "fix"})
  • On completion: state_write({mode: "ultraqa", active: false, current_phase: "complete", completed_at: "<now>"})
  • For resume detection: state_read({mode: "ultraqa"})

Scenario Examples

Good: The user says continue after the workflow already has a clear next step. Continue the current branch of work instead of restarting or re-asking the same question.

Good: The user changes only the output shape or downstream delivery step (for example make a PR). Preserve earlier non-conflicting workflow constraints and apply the update locally.

Bad: The user says continue, and the workflow restarts discovery or stops before the missing verification/evidence is gathered.

Cancellation

User can cancel with /cancel which clears the state file.

Important Rules

  1. PARALLEL when possible - Run diagnosis while preparing potential fixes
  2. TRACK failures - Record each failure to detect patterns
  3. EARLY EXIT on pattern - 3x same failure = stop and surface
  4. CLEAR OUTPUT - User should always know current cycle and status
  5. CLEAN UP - Clear state file on completion or cancellation

STATE CLEANUP ON COMPLETION

When goal is met OR max cycles reached OR exiting early, run $cancel or call:

state_clear({mode: "ultraqa"})

Use MCP state cleanup rather than deleting files directly.


Begin ULTRAQA cycling now. Parse the goal and start cycle 1.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.