Ultraqa
Run autonomous test–verify–fix cycles until build, lint, typecheck, or custom QA gates pass in Claude Code workflows.
Overview
UltraQA is an agent skill most often used in Ship (also Build integrations) that cycles test, verify, and fix until declared QA goals such as tests, build, lint, or typecheck pass.
Install
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill ultraqaWhat is this skill?
- Autonomous QA cycle: qa-tester → architect verification → fix → repeat
- Goal parsing for --tests, --build, --lint, --typecheck, and --custom patterns
- Coordinates with /goal, Ralph, Team, and Ultragoal without claiming conflicting loop authority
- Deterministic conflict policies: refuse, adopt_existing, artifact_only
- Level-3 skill oriented to visible command evidence when a behavior target is already defined
- Level-3 skill in oh-my-claudecode taxonomy
Adoption & trust: 618 installs on skills.sh; 36k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent stops after one red test run instead of iterating until build, lint, typecheck, or custom checks actually pass.
Who is it for?
Indie developers using Claude Code who already know the target behavior and need relentless gate cycling with architect-style verification.
Skip if: Early ideation, security audits without runnable gates, or sessions where another loop (Ralph/Team) forbids competing automation—follow refuse/adopt_existing rules.
When should I use this skill?
Target behavior is known and you need repeated QA until tests, build, lint, typecheck, or a custom check pattern succeeds.
What do I get? / Deliverables
You get repeated QA cycles with fixes applied until the parsed goal is met or safely recorded as artifact-only evidence under Ultragoal policies.
- Passing quality gates or documented artifact-only QA evidence
- Fix iterations applied from failed verification cycles
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
UltraQA is shelved under Ship because its core loop is quality-gate verification before release. Repeated test and fix cycling is canonical testing work, not one-off launch checklist tasks.
Where it fits
After wiring an API client, cycle tests and typecheck until the integration suite is green.
Before tagging a release, run UltraQA with --tests and --lint until all gates pass.
Use architect verification in the loop to catch design regressions surfaced by failing tests.
Re-run custom --custom patterns when production fixes need the same verify-fix cycle.
How it compares
Autonomous QA sub-loop for agent sessions—not a one-shot linter skill or manual test-plan template.
Common Questions / FAQ
Who is ultraqa for?
Solo builders on Claude Code (oh-my-claudecode) who want autonomous test-build-lint cycling until quality goals clear.
When should I use ultraqa?
In Ship (testing) before release; in late Build (integrations) when wiring features that must pass tests, build, lint, or typecheck; after behavior is defined, not while still scoping features.
Is ultraqa safe to install?
It can run shell commands (tests, builds)—review Security Audits on this page and supervise permissions in your agent environment.
SKILL.md
READMESKILL.md - Ultraqa
# 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 ## Relationship to `/goal`, Ralph, Team, and Ultragoal UltraQA owns repeated quality-gate cycling only. Use the deterministic conflict policies `refuse`, `adopt_existing`, and `artifact_only` rather than non-deterministic warning handling. Use it after the target behavior is known and the remaining question is whether tests, build, lint, typecheck, or another explicit QA condition passes. If Claude Code `/goal` is active, UltraQA may produce visible command evidence for that goal, but must not describe the `/goal` evaluator as independently running commands or reading files. If Ralph or Team is active, UltraQA is a verification/fix sub-loop under that authority rather than a competing session loop. If no active loop is safe, record QA expectations and evidence in artifact-only Ultragoal notes instead of claiming automatic execution. ## Goal Parsing Parse the goal from arguments. Supported formats: | Invocation | Goal Type | What to Check | | ---------------------------------------------- | --------- | -------------------------------- | | `/oh-my-claudecode:ultraqa --tests` | tests | All test suites pass | | `/oh-my-claudecode:ultraqa --build` | build | Build succeeds with exit 0 | | `/oh-my-claudecode:ultraqa --lint` | lint | No lint errors | | `/oh-my-claudecode:ultraqa --typecheck` | typecheck | No TypeScript errors | | `/oh-my-claudecode: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) 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: ``` Task(subagent_type="oh-my-claudecode:qa-tester", model="sonnet", prompt="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 ``` Task(subagent_type="oh-my-claudecode:architect", model="opus", prompt="DIAGNOSE FAILURE: Goal: [goal type] Output: [test/build output] Provide root cause and specific fix recommendations.") ``` 4. **FIX ISSUES**: Apply architect's recommendations ``` Task(subagent_type="oh-my-claudecode:executor", model="sonnet", prompt="FIX: Issue: [architect diagnosis] Files: [affected files] Apply the fix precisely as recommended.") ``` 5. **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: ..."