Delegate independent tasks to specialized agents working concurrently with isolated context.
295.4K 206.3K
View 
Run Quality Gate
run-quality-gate
Run full quality gate: linting, type checks, unit tests, and integration tests — all in parallel.
SKILL.md
Full skill instructions
Run Quality Gate
Runs the full verification pipeline for high-confidence changes. All gates run in parallel via background agents for maximum speed.
Usage
/run-quality-gate
Execution Strategy
IMPORTANT: Run all 6 gates in parallel as background agents in a single message. Do not run them sequentially. Each gate is independent — spawn all 6 agents at once and wait for results.
Gate 1: Lint/format (Python)
# Auto-detect: if project has uv.lock, use uv run
uv run ruff check --fix src/ tests/ && uv run ruff format src/ tests/
# If ruff --fix made changes, stage them
Agent prompt: "Run ruff check --fix and ruff format on src/ and tests/. Stage any auto-fixed files. Report errors that couldn't be auto-fixed."
Gate 2: Python type checking
uv run pyright src/
Agent prompt: "Run pyright on src/. Report all type errors with file:line locations."
Gate 3: TypeScript type checking
cd frontend && npx tsc --noEmit
Agent prompt: "Run tsc --noEmit in the frontend/ directory. Report all type errors."
Gate 4: Python unit tests
uv run pytest tests/ -q
Agent prompt: "Run the full pytest suite. Report pass/fail counts and any failures with tracebacks."
Gate 5: Frontend unit tests (Jest)
cd frontend && npx jest --no-coverage
Agent prompt: "Run the full Jest test suite in frontend/. Report pass/fail counts and any failures."
Gate 6: E2E tests (Playwright)
cd frontend && npm run test:e2e:safe
This runs playwright test --grep-invert @mutation (read-only, skips mutation tests).
Agent prompt: "Run Playwright E2E tests via npm run test:e2e:safe in frontend/. Report pass/fail counts and any failures."
After All Gates Complete
- Collect results from all 6 agents
- Present the summary table
- If ANY gate failed, fix the errors — do not just report them
- Re-run only the failed gates after fixing
- Repeat until all gates pass
Enforcement
- Any failing gate means overall failure.
- Fix ALL errors — lint, type, and test failures must be fixed regardless of when they were introduced. "Pre-existing" is not a valid reason to skip.
- Do not skip failing suites to force a pass.
- Do not report errors and move on — fix them before claiming the gate passed.
Output Format
## Quality Gate Results
| Gate | Result | Details |
|------|--------|---------|
| Ruff lint/format | PASS/FAIL | N errors |
| Pyright | PASS/FAIL | N errors |
| TypeScript | PASS/FAIL | N errors |
| Pytest | PASS/FAIL | N passed, N failed |
| Jest | PASS/FAIL | N passed, N failed |
| Playwright E2E | PASS/FAIL | N passed, N failed |
| **Final verdict** | **PASS/FAIL** | |
More Other skills
Other
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
179.7K 100.1K
View Other
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
179.7K 89.5K
View Other
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
179.7K 76.1K
View Fundamental design principles for writing maintainable, testable Python code.
40.2K 21.9K
View 
Other
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
40.2K 20K
View Generate Playwright tests from scenarios using interactive browser exploration and validation.
39.7K 18.2K
View Automated website exploration and test case generation using Playwright.
39.7K 14.9K
View Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
40.2K 14.7K
View Other
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
40.2K 14.3K
View Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
40.2K 13.5K
View 
Other
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
39.7K 13K
View