菜单
Multi-language code quality standards and review for TypeScript, Python, Go, and Rust. Enforces type safety, security, performance, and maintainability. Use when writing, reviewing, or refactoring code. Includes review process, checklist, and Python PEP 8 deep-dive.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/georgekhananaev/claude-skills-vault --skill code-quality命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | code-quality |
| description | Multi-language code quality standards and review for TypeScript, Python, Go, and Rust. Enforces type safety, security, performance, and maintainability. Use when writing, reviewing, or refactoring code. Includes review process, checklist, and Python PEP 8 deep-dive. |
| author | George Khananaev |
| replaces | ["beautiful-code","code-reviewer","pep8"] |
Production-grade code standards and review for TypeScript, Python, Go, and Rust.
| Intent | Sections to Use |
|---|---|
| Write code | Core Rules + Language Standards + AI-Friendly Patterns |
| Review PR | Review Process + references/checklist.md + Severity Levels |
| Setup CI | Config Files + Scripts + Enforcement Strategy |
| Python style | references/python.md (full PEP 8 deep-dive) |
Context loading: For deep reviews, read the relevant file for the language under review.
references/| Language | Type Safety | Linter | Complexity |
|---|---|---|---|
| TypeScript | strict, no any | ESLint + typescript-eslint | max 10 |
| Python | mypy strict, PEP 484 | Ruff + mypy | max 10 |
| Go | staticcheck | golangci-lint | max 10 |
| Rust | clippy pedantic | clippy + cargo-audit | - |
| Level | Description | Action |
|---|---|---|
| Critical | Security vulnerabilities, data loss | Block merge |
| Error | Bugs, type violations, any | Block merge |
| Warning | Code smells, complexity | Must address |
| Style | Formatting, naming | Auto-fix |
_ for err)See: references/typescript.md
// CRITICAL: Never use any
const bad: any = data; // Error
const good: unknown = data; // OK
// ERROR: No type assertions
const bad = data as User; // Error
const good = isUser(data) ? data : null; // OK
// ERROR: Non-null assertions
const bad = user!.name; // Error
const good = user?.name ?? ''; // OK
See: references/python.md
# CRITICAL: All functions must be typed
def bad(data): # Error
return data
def good(data: dict[str, Any]) -> list[str]: # OK
return list(data.keys())
# Use modern syntax
value: str | None = None # OK (not Optional)
items: list[str] = [] # OK (not List)
See: references/go.md
// CRITICAL: Never ignore errors
result, _ := doSomething() // Error
result, err := doSomething() // OK
if err != nil {
return fmt.Errorf("doing something: %w", err)
}
See: references/rust.md
// CRITICAL: No unwrap in production
let value = data.unwrap(); // Error
let value = data?; // OK
let value = data.unwrap_or_default(); // OK
See: references/logging.md
logger.info({ userId, action: 'login' }, 'User logged in'); // TS (pino)
logger.info("user_login", user_id=user_id) # Python (structlog)
log.Info().Str("user_id", userID).Msg("user logged in") // Go (zerolog)
See: references/testing.md
| Metric | Threshold |
|---|---|
| Line coverage | 80% min |
| Branch coverage | 70% min |
| New code | 90% min |
See: references/security.md
See: references/api-design.md
/users/{id}/ordersSee: references/database.md
See: references/async-concurrency.md
Use the checklist at references/checklist.md for thorough reviews covering:
**[SEVERITY] Issue Title**
- File: `path/to/file.ts:line`
- Problem: Clear description
- Impact: What could go wrong
- Fix: Specific code suggestion
# Review staged changes
git --no-pager diff --cached
# Review specific commit
git --no-pager show <commit>
# Review PR diff
gh pr diff <number>
Use severity levels from the table above (Critical / Error / Warning / Style).
# Code Review Summary
## Overview
- Files reviewed: X
- Issues found: Y (X Critical, Y Error, Z Warning)
- Recommendation: [Approve / Request Changes / Needs Discussion]
## Critical Issues
[Security vulnerabilities, data loss - must fix]
## Error Issues
[Bugs, type violations - must fix]
## Warnings
[Code smells, complexity - should address]
## Style
[Formatting, naming - auto-fixable]
## Positive Observations
[Good practices found]
| Element | TypeScript | Python | Go | Rust |
|---|---|---|---|---|
| Variables | camelCase | snake_case | camelCase | snake_case |
| Functions | camelCase | snake_case | camelCase | snake_case |
| Constants | SCREAMING_SNAKE | SCREAMING_SNAKE | MixedCaps | SCREAMING_SNAKE |
| Types | PascalCase | PascalCase | PascalCase | PascalCase |
| Files | kebab-case | snake_case | lowercase | snake_case |
Phase 1: Errors block, Warnings tracked
Phase 2: Strict on NEW files only
Phase 3: Strict on TOUCHED files
Phase 4: Full enforcement
| Mode | Trigger | Behavior |
|---|---|---|
| WIP | Local commit | Warnings only |
| Push | git push | Errors block |
| PR | PR to main | Full strict |
Available in configs/:
typescript/ - ESLint, tsconfig, Prettierpython/ - pyproject.toml, pre-commitgo/ - golangci.yamlrust/ - clippy.toml.pre-commit-config.yaml.gitleaks.tomlAvailable in scripts/:
check_changed.sh - Monorepo-aware incremental lintingcheck_all.sh - Full repository checkcheck_style.py - Python full check (ruff + pycodestyle + mypy)check_pep8.sh - Quick PEP 8 onlycheck_types.sh - Python type hints onlyfix_style.sh - Python auto-fix issuesShapes how every reply to the user gets written - plain everyday words instead of corporate or AI-sounding phrasing, real sentences instead of bullet-heavy formatting, no forced dash punctuation, and at most a rare bit of dry humor when it genuinely fits. Use this for every conversational response written to the user in this project, not only on special request - check it before replying, the same way a person reads over their own message before hitting send.
Safety-first Firebase CLI (firebase-tools v15) skill for full project control — deploy, Hosting (sites/channels/rollback), Cloud Functions (+secrets), Firestore (databases/indexes/backups/delete), Realtime Database, Auth import/export, Remote Config, App Distribution, App Hosting, Extensions, Data Connect, Emulator Suite & MCP server. Classifies every command by risk tier via a deterministic classifier script and gates destructive/irreversible/cost-incurring ops behind AskUserQuestion confirmation; enforces the --non-interactive/--force contract so nothing hangs and nothing is auto-confirmed. Wrong-project preflight prevents deploying to prod by accident. Ships a 3-level self-test (static classifier battery, live read-only, guarded live-write w/ cleanup). Use when running, planning, or debugging any `firebase` command.
Run OpenAI Codex CLI for coding tasks, implementation, reviews, and second-opinion audits with mandatory task-based routing across GPT-5.6-or-newer models. Use when a user asks to run, ask, or use Codex; says "codex prompt"; wants a Codex code/logic/plan audit; or wants Claude to delegate work to OpenAI models. Inspect the live Codex model catalog, explicitly pin an eligible model and reasoning effort on every invocation, route clear high-volume work to Luna, everyday work to Terra, and difficult or high-value work to Sol. Use Sol with max reasoning for plan audits. Never invoke or fall back to GPT-5.5, GPT-5.4, GPT-5.3-Codex-Spark, OSS, or any model older than GPT-5.6.
基于 SOC 职业分类
