Menu
Use when finishing an edit to source files — runs format, typecheck, and console.log detection before moving to the next task.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when starting any creative work — creating features, components, or functionality, modifying behavior, or solving ambiguous problems — before design or implementation. Covers product discovery, competitive research, feature analysis, technical design, and capability spec writing. Applies to every project; routes to writing-plans (non-UI) or design-workflow (UI).
Use when implementation of a bug fix or feature task is complete — dispatches the appropriate language and global reviewers and returns a binary APPROVE/BLOCK verdict.
Use when about to git commit — validates commit message format, lints staged files, and scans staged content for secrets and debug artifacts.
Use when reaching the design-workflow V2-4 hard gate — adversarially reviews design artifacts (token coverage, contract completeness, artifact consistency, accessibility docs, responsive coverage, DESIGN.md compliance) against docs/designs/<feature>/ before development handoff.
Use when a task involves UI — new pages, components, visual interactions, or design tokens — including work in docs/designs/, *.pen files, or with Pencil MCP tools. Skip for backend-only, config-only, or refactoring without visual impact. Routes to writing-plans on completion.
Use when building Django features involving authentication, authorization, user input, sessions, or deployment — covers CSRF, SQL injection, and XSS prevention plus secure production configuration.
| name | code-quality-gate |
| description | Use when finishing an edit to source files — runs format, typecheck, and console.log detection before moving to the next task. |
| origin | ECC |
Run this skill after editing source files to catch formatting issues, type errors, and debug artifacts before they accumulate.
Auto-format all modified files using the project's configured formatter.
JavaScript / TypeScript
# Biome (preferred if biome.json exists)
npx biome format --write <files>
# Prettier (fallback)
npx prettier --write <files>
Python
# Ruff (preferred)
ruff format <files>
# Black (fallback)
black <files>
Go
gofmt -w <files>
Run the linter on modified files and fix auto-fixable issues.
JavaScript / TypeScript
# Biome
npx biome lint --write <files>
# ESLint
npx eslint --fix <files>
Python
ruff check --fix <files>
Go
golangci-lint run <files>
Run the type checker across the project (not just modified files, since changes can affect other modules).
TypeScript
npx tsc --noEmit
Python (mypy)
mypy <module_or_path>
Scan modified files for debug statements that should not be committed.
Patterns to detect:
console.log(, console.debug(, console.warn( (JS/TS)print(, pprint(, breakpoint() (Python, unless in test files)debugger; (JS/TS)[TEMP-INSTR] (temporary diagnostic instrumentation from investigate Phase 2c/2d — must be removed before commit)TODO:, FIXME:, HACK: (flag only, do not block)Action: Remove or replace with proper logging before proceeding.
All checks must pass before the quality gate is considered satisfied:
| Check | Pass Condition |
|---|---|
| Format | No formatting changes remain after auto-fix |
| Lint | Zero errors (warnings allowed) |
| Typecheck | Zero type errors |
| Debug artifacts | No console.log / debugger / breakpoint() / [TEMP-INSTR] in non-test files |
@ts-ignore or type: ignore unless absolutely necessary and commented.logger.debug(...), logging.debug(...), etc.).Run checks only on files modified in the current response or task. Do not run full-project linting unless the task explicitly requires it, to keep feedback fast.