multi-model-review
Run code review with 4 free OpenCode models in parallel, then have them peer-review each other to reach consensus findings.
lint
Run formatting, linting, and type checking. Auto-detects project languages (Python, JS/TS, Bash). Fixes auto-fixable issues and stages changes.
Full skill instructions
Auto-detects project languages and runs the appropriate formatting, linting, and type checking tools.
/lint
/lint --fix
/lint backend
/lint frontend
git diff --name-only HEAD
all: scope to the entire codebase (run tools without file args, e.g., ruff check src/ tests/, pyright, tsc --noEmit)backend or frontend: scope to that workspaceCheck for these files in the project root (or relevant subdirectory):
| Indicator | Language | Tools |
|---|---|---|
pyproject.toml, setup.py, setup.cfg, *.py in diff | Python | ruff, pyright |
package.json, tsconfig.json, *.ts/*.tsx/*.js/*.jsx in diff | JS/TS | prettier, eslint, tsc |
*.sh in diff | Bash | shellcheck |
Run only the tools that apply. If a tool isn't installed, ask the user if they want to install it via AskUserQuestion.
Linting (Ruff):
# Check only
ruff check <changed-py-files>
# If --fix passed
ruff check --fix <changed-py-files>
Formatting (Ruff):
# Check only
ruff format --check <changed-py-files>
# If --fix passed
ruff format <changed-py-files>
If the project uses uv, prefix with uv run (check for uv.lock or project CLAUDE.md instructions).
Stage any fixes:
git add <fixed-files>
Type checking (Pyright):
pyright <changed-py-files>
Or uv run pyright if the project uses uv. Report type errors.
Formatting (Prettier):
npx prettier --check <changed-js-ts-files>
If --fix:
npx prettier --write <changed-js-ts-files>
Stage any fixes.
Linting (ESLint):
npx eslint <changed-js-ts-files>
If lint errors, attempt auto-fix:
npx eslint --fix <changed-js-ts-files>
Stage any fixes. Only lint files in the diff.
Type checking (TypeScript):
npx tsc --noEmit --pretty 2>&1
Report type errors.
Linting (shellcheck):
shellcheck <changed-sh-files>
Report issues. shellcheck has no auto-fix mode -- report findings for manual review.
## Lint Results
### Python
- Ruff: PASS / FIXED N files / FAIL (N remaining)
- Pyright: PASS / FAIL (N errors in changed files)
### JavaScript / TypeScript
- Prettier: PASS / FIXED N files / FAIL
- ESLint: PASS / FIXED N errors / FAIL (N remaining)
- TypeScript: PASS / FAIL (N errors in changed files)
### Bash
- shellcheck: PASS / FAIL (N warnings)
- Files staged: N
- Verdict: PASS / FAIL
Only include sections for detected languages.
all scope: entire codebase.Run code review with 4 free OpenCode models in parallel, then have them peer-review each other to reach consensus findings.
Run Codex and Claude code reviews iteratively until both find no issues. Use after making changes and before committing.
Creates a pull request with proper formatting, running tests first and including a structured description.
Commit session changes only, or all changes if no session edits.
Run full quality gate: linting, type checks, unit tests, and integration tests — all in parallel.
Use when asked to work on, implement, or complete a GitHub issue — before writing any code, checks issue state, existing PRs, git history, and codebase to determine what work remains or if the issue is already resolved
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Autonomous test-fix pipeline. Runs full suite, diagnoses each failure, fixes source code, and iterates until all tests pass. Asks the user when uncertain about intended behavior.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience