ultraqa
An autonomous agent skill that iteratively performs quality checks and fixes until the target project state is satisfied.
Install
mkdir -p .claude/skills/ultraqa && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4563" && unzip -o skill.zip -d .claude/skills/ultraqa && rm skill.zipInstalls to .claude/skills/ultraqa
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
QA cycling workflow - test, verify, fix, repeat until goal metKey capabilities
- →Executes autonomous QA cycles
- →Performs build, lint, and test checks
- →Resolves linting errors iteratively
- →Verifies typecheck status
- →Uses a deterministic fix-and-retry loop
How it works
Runs an automated feedback loop where commands are executed, results parsed, and failures addressed until the exit criteria are met.
Inputs & outputs
When to use ultraqa
- →Automating test suite verification
- →Running build checks after code changes
- →Resolving linting errors programmatically
About ultraqa
Coordinates an automated feedback loop between testing, building, and linting. It performs verification steps autonomously and repeats the process until pre-defined quality conditions are achieved.
QA cycling workflow - test, verify, fix, repeat until goal met
When not to use it
- →Non-automated environments
- →Manual exploratory testing
Prerequisites
Limitations
- →Limited to a maximum of 5 cycles
- →Requires well-defined error conditions
How it compares
Functions as a continuous sub-loop that persists until quality conditions are satisfied, unlike a one-off command runner.
Compared to similar skills
ultraqa side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ultraqa (this skill) | 1 | 4mo | Review | Advanced |
| dev | 2 | 7mo | Review | Advanced |
| overnight-development | 1 | 2mo | Review | Intermediate |
| nx-run-tasks | 1 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by Yeachan-Heo
View all by Yeachan-Heo →You might also like
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
overnight-development
jeremylongshore
Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
deepgram-ci-integration
jeremylongshore
Configure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pipelines, automated testing, or deployment workflows for Deepgram integrations. Trigger with phrases like "deepgram CI", "deepgram CD", "deepgram pipeline", "deepgram github actions", "deepgram automated testing".
gsd-add-tests
phorde
Generate tests for a completed phase based on UAT criteria and implementation
spec-driven-workflow
CafeSemCafeina
The build workflow for avaliador-tech-recruiter — risk-ordered tiers with a protected mock-mode floor, a Ready spec required before any unit is implemented, eval gates (L0 contract / L1 policy / L2 fixtures) as the merge filter, package partitioning for parallel agents, atomic Conventional Commits,