End-to-end AI QA — generate test cases (from a Figma design or by exploring a live URL), execute them with a selectable engine, track per-case results, and emit an HTML report. Use whenever the user wants to inspect/QA a page or design end to end — "QA 돌려줘", "이 페이지 점검해줘", "피그마로 테스트 만들고 실행까지", "run full QA".
Read aqa-inspect results.csv and create Jira tickets for failed test cases behind a human approval gate. Use this command when the user says "실패한 테스트 지라에 올려줘", "create Jira tickets from QA results", "티켓 생성해줘".
Dry-run merge check against a target branch. Pulls the latest target branch and tests if the current branch can merge cleanly. Use when the user says "머지 가능한지 확인해줘", "merge check", "dry run", "충돌 확인", or wants to check mergeability before creating a PR.
Generate a PR description from current branch changes and create a pull request. Use when the user says "PR 올려줘", "PR 작성해줘", "push PR", "create PR", or asks to ship their work.
End-to-end AI QA — generate test cases (from a Figma design or by exploring a live URL), execute them with a selectable engine (browser-use screenshots or Playwright DOM), track per-case results (pass/fail/needs_discussion, tester, time, reasons) into results.csv, and emit an HTML report. Use whenever the user wants to inspect/QA a page or design end to end — "QA 돌려줘", "이 페이지 점검해줘", "피그마로 테스트 만들고 실행까지", "run full QA".
Read aqa-inspect results.csv and create Jira tickets for failed test cases, behind a human approval gate. Filters status=fail only (pass and needs_discussion excluded), drafts tickets with failure details + screenshots, dedups against existing tickets, and writes the created ticket key back into results.csv. Use when the user says "실패한 테스트 지라에 올려줘", "create Jira tickets from QA results", "티켓 생성해줘".
Dry-run merge check against a target branch. Pulls the latest target branch and tests if the current branch can merge cleanly. Use when the user says "머지 가능한지 확인해줘", "merge check", "dry run", "충돌 확인", or wants to check mergeability before creating a PR.
Generate a PR description from current branch changes and create a pull request. Use when the user says "PR 올려줘", "PR 작성해줘", "push PR", "create PR", or asks to ship their work.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
By Ten — A Claude Code plugin for AI-powered QA automation and Git workflow.
# Step 1: Add to marketplace
/plugin marketplace add ten1010-io/claude-toolkit
# Step 2: Install
/plugin install claude-toolkit@ten1010-io
End-to-end AI QA in one command — generates test cases (from a Figma design or by exploring a live URL), executes them with a selectable engine, tracks per-case results into results.csv, and renders an HTML report. Never creates Jira tickets — filing is handled separately by /aqa-jira.
Usage:
/aqa-inspect [--figma <url> | -f <url>] [--target <url>] [options]
Options:
| Option | Default | Description |
|---|---|---|
--figma <url> / -f <url> | — | Figma file or frame URL — cases generated from the design |
--target <url> | — | Live service URL — required when --figma and --cases are absent (exploration mode); stored as BASE_URL |
--cases <path> | — | Execute an existing cases.yaml directly, skipping generation (cases must carry a case_id) |
--engine browser-use|playwright | browser-use | Execution engine: browser-use (AI screenshots) or playwright (DOM) |
Examples:
/aqa-inspect --target https://app.example.com
/aqa-inspect --figma https://www.figma.com/file/xxx/Login --target https://app.example.com
/aqa-inspect --target https://app.example.com --engine playwright
Output: a report directory containing results.csv (per-case status: pass / fail / needs_discussion, plus tester, time, reasons), summary.json (run metadata + counts), and report.html.
Prerequisites:
FIGMA_ACCESS_TOKEN in .envReads the results.csv produced by /aqa-inspect, drafts a Jira ticket for each failed case (failure details + screenshots), dedups against existing tickets, and — only after explicit human approval — creates the tickets and writes each returned ticket key back into results.csv. Reads status=fail rows ONLY; pass and needs_discussion are never ticketed. This command never runs tests.
Usage:
/aqa-jira (--results <path> | <reports_dir>) [options]
Options:
| Option | Default | Description |
|---|---|---|
--results <path> | — | Path to the results.csv to read |
<reports_dir> (positional) | — | A report directory; locates results.csv inside it (use this OR --results) |
--project <KEY> | ask | Target Jira project key (e.g. PROJ) — asks if absent |
Prerequisites:
results.csv produced by a prior /aqa-inspect runThe two aqa-inspect and aqa-jira commands form a human-gated QA pipeline:
/aqa-inspect → human review → /aqa-jira
(generate → run → (read report.html, (fail rows → Jira
results.csv + confirm fail rows) tickets, approval-gated)
report.html)
/aqa-inspect — generates and runs test cases, writing results.csv (with pass / fail / needs_discussion per case) and an HTML report.fail rows are genuine, and resolves any needs_discussion cases./aqa-jira — reads the fail rows from results.csv and, behind an explicit approval gate, files Jira tickets, writing each ticket key back into results.csv.Analyzes branch changes, generates a PR title and description, then pushes and creates the PR.
Usage:
/pr [options]
Options:
| Option | Default | Description |
|---|---|---|
--base <branch> | auto-detect | Base branch to compare against |
--draft | No | Create as draft PR |
Prerequisites:
gh auth login)Dry-run merge check — fetches the latest target branch and tests if the current branch can merge cleanly.
Usage:
/merge-check [options]
Options:
| Option | Default | Description |
|---|---|---|
--target <branch> | auto-detect | Target branch to merge into |
claude-toolkit/
├── .claude-plugin/
│ ├── plugin.json # Plugin metadata
│ └── marketplace.json # Marketplace catalog
├── commands/
│ ├── aqa-inspect.md
│ ├── aqa-jira.md
│ ├── pr.md
│ └── merge-check.md
└── skills/
├── aqa-inspect/
│ ├── SKILL.md
│ └── references/
├── aqa-jira/
│ ├── SKILL.md
│ └── references/
├── pr/
│ └── SKILL.md
└── merge-check/
└── SKILL.md
MIT
npx claudepluginhub ten1010-io/claude-toolkit --plugin claude-toolkitComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.