Agent skill · gstack
/qa Find, reproduce and fix bugs with regression tests
The QA skill tests a web page, API, CLI, job or webhook, records a baseline report, then fixes bugs in severity order. Each fix starts with a regression test that fails, then a minimal change, a re-test and its own commit. It stops to check in every five fixes, after two reverts or after touching an unrelated file, with a hard cap of fifty fixes.
Works with
- Claude Code
- Codex, Cursor, OpenCode, Gemini CLI and other agents
Used forTesting and TDD
When to use it
- A staging site or local app needs a real click-through before release.
- A CLI, API or webhook behaves wrongly and you want each bug reproduced first.
- You want each fix to ship with its own regression test and commit.
How it works
- 1Set up
The agent parses target, tier and mode, asks you to commit or stash if the tree is dirty, and creates a fresh report folder.
- 2Run the baseline
It explores the chosen surfaces using any test plan from earlier reviews and reports findings before fixing anything.
- 3Write the failing test
For each bug it writes a regression test that fails for the right reason, matching nearby test style.
- 4Fix, re-test, commit
It makes the smallest fix, re-runs the test and nearby happy path, and commits only verified changes.
- 5Report
The final report lists verified, best-effort, reverted and deferred issues, with a browser health score where relevant.
What it steers the agent away from
- Fixes committed without proof that the bug is gone.
- Weakening existing tests or editing CI configuration.
- Fix loops that sprawl across unrelated files.
Install this skill
It installs with the gstack pack.
Claude CodeThe README wraps this command in a prompt you paste into Claude Code, which also adds a short gstack section to CLAUDE.md.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setupClaude Code (team mode for a shared repo)Run inside your repo; it commits a bootstrap so teammates get gstack with auto-updates, and needs Node.js for the required hook.
(cd ~/.claude/skills/gstack && ./setup --team) && ~/.claude/skills/gstack/bin/gstack-team-init required && git add .claude/ CLAUDE.md && git commit -m "require gstack for AI-assisted work"Codex, Cursor, OpenCode, Gemini CLI and other agentsUse --host auto for every detected agent or name one host; non-Claude hosts are listed as experimental.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack && ./setup --host auto # or: ./setup --host codex
./setup --status # one row per install: host, tier, scope, version, pathCommands come from the author’s README; check it for changes before you run them.
Questions
Which bugs get fixed?
It depends on the tier: quick fixes critical and high, standard adds medium, exhaustive adds low and cosmetic issues.
Can it test something without a web page?
Yes. It probes APIs, CLIs, jobs, workers and webhooks with the repo's own tools and reports contract results instead of a score.
More guides from gstack
/csoRun a security audit that keeps evidence separate from claimsAudits code, infrastructure, supply chain or skills for exploitable defects, challenges each finding and can reproduce fixes in Docker.Read the guide →/office-hoursPressure-test an idea before your agent writes any codeQuestions your idea in startup or builder mode, challenges premises, compares two or three approaches and writes a design doc, with no code.Read the guide →/plan-ceo-reviewReview a plan for scope and ambition like a founderReviews a plan as a founder would, in expansion, selective, hold or reduction mode, and asks before adding or cutting any scope.Read the guide →/plan-eng-reviewLock architecture, edge cases and tests before you buildLocks a plan's architecture, data flow, edge cases and test coverage, with ASCII diagrams and a review report appended to the plan.Read the guide →/reviewCatch production bugs in a diff before it mergesReviews a branch diff for bugs that pass CI, dispatches specialist and adversarial passes, auto-fixes obvious issues and asks about the rest.Read the guide →/shipTake a branch from finished code to an open PRMerges the base branch, runs tests and reviews, bumps VERSION and CHANGELOG, verifies the frozen content, pushes and opens a PR.Read the guide →
Also in this pack
/autoplanRuns the CEO, design, developer experience and engineering reviews in sequence and brings only taste decisions to you.↗/benchmarkMeasures page load timings, Core Web Vitals and resource sizes in a real browser and compares them with a saved baseline.↗/canaryWatches a live URL after a deploy for console errors, failed pages and visual changes against baseline screenshots.↗/carefulWarns before destructive commands such as recursive deletes, dropped tables or force pushes, and hard-blocks the riskiest ones.↗/codexGets an independent review, challenge or consultation from the OpenAI Codex CLI and presents its output unedited.↗/design-consultationResearches your product space and proposes a full design system, written to a DESIGN.md file with font and colour previews.↗/design-htmlTurns an approved mockup into production HTML and CSS with computed text layout, detecting React, Svelte or Vue.↗/design-reviewAudits a live site for spacing, hierarchy and generated-looking patterns, then fixes them with atomic commits and before and after screenshots.↗/design-shotgunProduces several AI design mockups side by side in a browser board, collects your feedback and iterates until you pick a direction.↗/devex-reviewTests a developer product live by following its docs and getting-started flow, timing each step and comparing against the plan's scores.↗/diagramTurns an English description into a mermaid source, an editable Excalidraw file and rendered SVG and PNG, offline.↗/document-releaseChecks project docs against what changed in a release and updates the facts, asking about subjective edits.↗
Summary by trendhub. The skill itself lives in garrytan/gstack/qa by Garry Tan (MIT); read the full, current text there.