branch-workflow
FreeBranch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.
The English summary is being prepared. Showing the original description.
Run the project's own tests, linter, type checker and build, and report what actually failed.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Run all quality checks: Tests → Lint → Types → Build
"Find bugs before they find users. Run QA early, run it often."
# Check what we're working with
[ -f "package.json" ] && echo "node"
[ -f "Cargo.toml" ] && echo "rust"
[ -f "pyproject.toml" ] || [ -f "requirements.txt" ] && echo "python"
[ -f "go.mod" ] && echo "go"
# Tests
npm test 2>&1 || yarn test 2>&1 || pnpm test 2>&1
# Lint
npm run lint 2>&1 || npx eslint . 2>&1
# Type check
npx tsc --noEmit 2>&1
# Build
npm run build 2>&1
# Tests
cargo test 2>&1
# Lint
cargo clippy -- -D warnings 2>&1
# Format check
cargo fmt --check 2>&1
# Build
cargo build 2>&1
# Tests
pytest 2>&1 || python -m pytest 2>&1
# Lint
ruff check . 2>&1 || flake8 . 2>&1
# Type check
mypy . 2>&1 || pyright . 2>&1
# Format check
black --check . 2>&1 || ruff format --check . 2>&1
# Tests
go test ./... 2>&1
# Lint
golangci-lint run 2>&1
# Build
go build ./... 2>&1
Format output as:
## QA Report
### Tests
✓ Passed: 42
✗ Failed: 2
⊘ Skipped: 1
Failed tests:
- test_user_auth: AssertionError at line 45
- test_token_refresh: Timeout
### Lint
✓ No issues
### Type Check
⚠ 3 warnings:
- src/auth.ts:12 - Type 'any' used
- src/utils.ts:34 - Implicit return type
### Build
✓ Build successful
### Summary
Status: FAILING
Must fix: 2 test failures
Should fix: 3 type warnings
Based on results:
If all pass:
QA passed! Ready for:
- /dev-security - Security audit
- /dev-rc - Release candidate prep
- /dev-finish - Close the cycle
If failures:
QA found issues.
Options:
1. Fix now (I'll help)
2. Fix manually, run /dev-qa again
3. Continue anyway (not recommended)
If "Fix now":
For a fast check (CI-style):
/dev-qa quick
Runs only:
Skips:
If active dev-cycle session exists:
## QA History
- 2026-07-15 14:30: FAILED (2 test failures)
- 2026-07-15 14:45: PASSED
| Check | Why |
|---|---|
| Tests | Does it work? |
| Lint | Is it clean? |
| Types | Is it safe? |
| Build | Does it compile? |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Branch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.
The English summary is being prepared. Showing the original description.
Look up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.
The English summary is being prepared. Showing the original description.
Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.
The English summary is being prepared. Showing the original description.
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
The English summary is being prepared. Showing the original description.
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
The English summary is being prepared. Showing the original description.
Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.
The English summary is being prepared. Showing the original description.