create-unit-test
Create and run unit tests following the project's architecture and guidelines (Robolectric, naming, location).
write-e2e-cases
Use when adding or updating Rsbuild end-to-end tests in `e2e/cases`, including new feature coverage, bug reproduction, and regression prevention.
review-and-simplify-changes
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".
test-with-spanner
Run unit tests that require the Spanner emulator. Use this skill when the user wants to run tests in packages like satellite/metabase, satellite/metainfo, or any other tests that interact with Spanner. Automatically handles checking for and configuring the Spanner emulator environment.
test-with-postgres
Run unit tests that require PostgreSQL. Use this skill when the user wants to run tests with PostgreSQL database backend. Automatically handles checking for and configuring a PostgreSQL Docker container.
browser-test
Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.
test-cli-usability
Write scenario tests that verify your CLI tool is usable by AI agents. Ensures commands work non-interactively, provide clear output, and don't hang on prompts. Use when you want to prove your CLI is agent-friendly.
test-compliance
Test that your AI agent stays observational and doesn't give prescriptive advice in regulated domains (healthcare, finance, legal). Creates scenario tests for boundary enforcement and red team tests for adversarial probing. Use when your agent advises but must not prescribe.
scenarios
Test your AI agent with simulation-based scenarios. Covers writing scenario test code (Scenario SDK), creating platform scenarios (MCP), and red teaming for security vulnerabilities. Auto-detects whether to use code or platform approach based on context.
code-review-expert
Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.
token-audit
Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
atopile-skills
How to write and maintain `.claude/skills/*/SKILL.md` files: source-of-truth-first process, verification steps, and conventions.
