TypeScript and JavaScript development standards for modern web and Node.js development. Covers strict TypeScript configuration, type safety patterns, ESM modules, async/await, testing with Jest/Vitest, and security best practices. Use when working with .ts, .tsx, .js, .mjs files, package.json, tsconfig.json, or when asking about TypeScript/JavaScript best practices.
Analyze Flutter and mobile applications for OWASP Mobile Top 10 (2024) security compliance. Use this skill when performing security audits, vulnerability assessments, or compliance checks on mobile applications. Performs automated scans for hardcoded secrets, insecure storage, weak cryptography, network security issues, and provides detailed remediation guidance.
Python development standards for code review and generation. Covers Python 3.12+ patterns, type hints, async/await, testing with pytest, package management with uv, AWS Lambda/boto3 patterns, and Pydantic validation. Use when working with .py files, pyproject.toml, requirements.txt, Lambda functions, or when asking about Python best practices, code review, or generation.
Run Codex subagents in parallel. Main sandbox can be read-only / workspace-write / danger-full-access; children stay read-only or workspace-write and each requires an absolute working dir (workspace-write children must stay under the main cwd unless main is danger).
Expert testing and quality engineer for Vitest (running on Bun). Use when user needs test creation, test strategy, code quality setup, E2E testing, or debugging test failures. Examples - "write tests for this function", "create E2E tests with Playwright", "help me test this API route", "setup testing infrastructure", "why is this test failing?", "improve code quality with Biome".
Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning
Operate agentpack safely (doctor/update/preview/diff/deploy/status/explain/evolve/rollback). Prefer --json.
Toolkit for testing and automating web applications. Prioritizes Claude Code Chrome integration for real browser testing. Falls back to Playwright scripts for CI/CD or headless scenarios.
WHEN to auto-invoke: Creating CI/CD pipelines, GitHub Actions workflows, Docker/containerization, Vercel/Netlify deployment, infrastructure as code, environment variables, deployment configurations. WHEN NOT to invoke: Application code changes, UI development, database schema design, testing application logic.
Manage stacked Git branches with Stackit. Use when creating/managing stacked branches, submitting PRs for branch stacks, navigating branch trees, rebasing stacks, syncing with main/trunk, troubleshooting stack issues, absorbing changes, resolving rebase conflicts, or any workflow involving dependent Git branches. Keywords stackit, stacked changes, stacked PRs, branch stack, restack, absorb, git stack.
AI-powered validation of knowledge notes against current codebase. Detects stale content by comparing documented knowledge with actual files.
Creates Docker configurations and compose files. Use when containerizing apps, setting up Docker dev environment, writing Dockerfile/compose.yaml, or building multi-stage images.
Stage files, hunks, or specific lines in git non-interactively.
Update main/master from origin, rebase current branch on it, resolve conflicts, and push.
CLAUDE.md/AGENTS.md等のコアルールファイルの保守・更新を対話で行い、3環境同期と整合性を維持したまま反映する。CLAUDE.md更新、コアルール変更、ルール追加、パス辞書更新、ワークフロー索引更新を依頼されたときに使用する。
Sets up local CI with Justfile task runner. Use when setting up lint/test/format automation, writing pre-commit hooks, or running E2E tests with containers.
Create well-formatted commits following conventional commits style with proper atomic commits and descriptive messages
Restructure branch into clean, reviewer-friendly commits. Analyzes total diff since main, groups files by concern, and rewrites with conventional commit messages.
