GhassenAZZOUZ/claude-qa-agent
Eighteen QA workflows for Claude Code: Playwright-BDD UI, API, integration and multi-service tests, exploratory testing, bug filing, fix verification, PR test impact, flaky triage, release readiness, load tests. Works with GitLab, GitHub, J
field: Cloud & infrastructure workflow: Testing & TDDPlanning & specsCI/CD & deployGit & commitsFrontend & design runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~8.2k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add gitlab -e GITLAB_API_URL=YOUR_GITLAB_API_URL -e GITLAB_PERSONAL_ACCESS_<redacted> -e GITLAB_TOOLS=YOUR_GITLAB_TOOLS -e GITLAB_TOOLSETS=YOUR_GITLAB_TOOLSETS -- npx -y @zereight/mcp-gitlab@2.2.1 $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude ./rig-claude-qa-agent # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add gitlab -e GITLAB_API_URL=YOUR_GITLAB_API_URL -e GITLAB_PERSONAL_ACCESS_<redacted> -e GITLAB_TOOLS=YOUR_GITLAB_TOOLS -e GITLAB_TOOLSETS=YOUR_GITLAB_TOOLSETS -- npx -y @zereight/mcp-gitlab@2.2.1 $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/api-session .claude/skills/api-session $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/benchmark .claude/skills/benchmark $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/bug-report .claude/skills/bug-report $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/ci-test-setup .claude/skills/ci-test-setup $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/diagnose-ci .claude/skills/diagnose-ci $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/e2e-session .claude/skills/e2e-session $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/enhance-story .claude/skills/enhance-story $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/explore-session .claude/skills/explore-session $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/flaky-triage .claude/skills/flaky-triage $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/gap-stories .claude/skills/gap-stories $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/heal-tests .claude/skills/heal-tests $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/integration-tests .claude/skills/integration-tests $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/load-test .claude/skills/load-test $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/mr-impact .claude/skills/mr-impact $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/provider-azure-devops .claude/skills/provider-azure-devops $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/provider-bitbucket .claude/skills/provider-bitbucket $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/provider-github .claude/skills/provider-github $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/provider-gitlab .claude/skills/provider-gitlab $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/provider-jira .claude/skills/provider-jira $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/qa-setup .claude/skills/qa-setup $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/quick-bug .claude/skills/quick-bug $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/release-readiness .claude/skills/release-readiness $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/requirements-analysis .claude/skills/requirements-analysis $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/review-plan .claude/skills/review-plan $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/session-report .claude/skills/session-report $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/test-plan .claude/skills/test-plan $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/traceability .claude/skills/traceability $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/tracker .claude/skills/tracker $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/user-story-format .claude/skills/user-story-format $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/verify-fix .claude/skills/verify-fix $ npx degit GhassenAZZOUZ/claude-qa-agent/.claude/skills/write-tests .claude/skills/write-tests
$ curl -fsSL --create-dirs -o .claude/agents/benchmark-gap-story-writer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/benchmark-gap-story-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ci-diagnostician.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/ci-diagnostician.md $ curl -fsSL --create-dirs -o .claude/agents/competitor-benchmark.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/competitor-benchmark.md $ curl -fsSL --create-dirs -o .claude/agents/exploratory-tester.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/exploratory-tester.md $ curl -fsSL --create-dirs -o .claude/agents/load-test-writer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/load-test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/mr-test-impact.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/mr-test-impact.md $ curl -fsSL --create-dirs -o .claude/agents/test-execution-agent.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/test-execution-agent.md $ curl -fsSL --create-dirs -o .claude/agents/test-healer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/test-healer.md $ curl -fsSL --create-dirs -o .claude/agents/test-plan-reviewer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/test-plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/user-story-enhancer.md https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/main/.claude/agents/user-story-enhancer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| @zereight/mcp-gitlab · "gitlab" env: GITLAB_API_URL, GITLAB_PERSONAL_ACCESS_TOKEN, GITLAB_TOOLS, GITLAB_TOOLSETS | npm | 2.5k |
Skills (31)
api-sessionbenchmarkbug-reportci-test-setupdiagnose-cie2e-sessionenhance-storyexplore-sessionflaky-triagegap-storiesheal-testsintegration-testsload-testmr-impactprovider-azure-devopsprovider-bitbucketprovider-githubprovider-gitlabprovider-jiraqa-setupquick-bugrelease-readinessrequirements-analysisreview-plansession-reporttest-plantraceabilitytrackeruser-story-formatverify-fixwrite-tests
Subagents (11)
| benchmark-gap-story-writer | Use to read a `competitor-benchmark` report, rank the benchmarked competitors with a transparent weighted score to pick the leader to match, extract the features the leader has that the target lacks ( |
| ci-diagnostician | Use to fetch and analyze a failed CI run on GitLab, GitHub Actions, Azure Pipelines or Bitbucket Pipelines (jobs, failed steps, raw logs, linked MR/PR diff) and identify the root cause — classifies fa |
| competitor-benchmark | Use to find apps that solve the same problem as a target app — given as a URL, a name/description, or a Git repository (GitHub/GitLab URL or local path) — and produce a sourced benchmark: target finge |
| exploratory-tester | Use to explore a running web app live in a real browser, with no written requirements, against a charter (mission + scope + action budget). Drives Chromium through a Playwright MCP server scoped to th |
| load-test-writer | Use to generate and (for the smoke profile) run k6 load-test scripts from an OpenAPI spec or endpoint list — profiles smoke / load / stress / spike / soak with p95 latency and error-rate thresholds. R |
| mr-test-impact | Use to map a merge request / pull request's changes (GitLab, GitHub, Azure DevOps, Bitbucket) to the existing test suite — fetches the change and its diff, matches changed files/routes/endpoints/label |
| test-execution-agent | Single execution agent for every `playwright-bdd` test `test-writer` produces — browser tests (WAY 1) and API tests (WAY 2). Runs real `npx playwright test`, not a live-driven MCP session. Replaces th |
| test-healer | Use when a UI test fails because a locator no longer matches (failure_kind locator, e.g. "waiting for getByRole(''button'', { name: ''Submit'' })"). Reads Playwright''s error-context.md page snapshot |
| test-plan-reviewer | Use to review a test plan (the `test-plan` skill format) independently of the agent that wrote it — scores it out of 100 on nine dimensions with evidence, and proposes test cases to ADD, REMOVE, MERGE |
| test-writer | Single canonical test-authoring agent for the whole project — designs the test plan from requirements (per the shared requirements-analysis skill, `plan` mode, WAY 19) and writes UI E2E, API, API inte |
| user-story-enhancer | Use to score a user story and produce (1) an enhanced issue body with Gherkin acceptance criteria, Missing Information and Definition of Done (original preserved verbatim) and (2) a QA analysis commen |
Similar rigs
John99101/claude-code-project-template
Self-configuring Claude Code setup: install into a project or onto your machine, and Claude detects your stack, asks about your preferences, and writes CLAUDE.md, rules, commands, skills, agents, hooks and MCP config.
Pragmatist 637 tok · · Q0
vitoleonardo/agentic-development-template
Claude Code plugins and templates for agentic software delivery: spec-driven workflow kit with guard hooks and CI gates, a read-only delivery assessment (repo-check), and a contract-first Next.js template.
Fort Knox 19.0k tok · · Q39
mloning/dotfiles
My configuration files
YOLO Cowboy 1.7k tok · · Q29
smirnovalex-qa/qa-skills
QA skills for AI coding agents — test design, automation, audits, and defect management from a single source.
Skill Collector 2.5k tok · · Q0