AGENT SKILL
lint-and-validate
暂无简介
使用场景代码审查
- License 许可
- Apache-2.0
- 所属仓库
- yqecea/gem-swarm
- 最近更新
- 2026-04-26
- Stars
- ★ 1
- Forks
- 1
02 资源文件 2
- 脚本scripts/lint_runner.py5.3 KB
- 脚本scripts/type_coverage.py6.3 KB
03 SKILL.md 正文
Lint and Validate Skill
MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.
Procedures by Ecosystem
Node.js / TypeScript
- Lint/Fix:
npm run lintornpx eslint "path" --fix - Types:
npx tsc --noEmit - Security:
npm audit --audit-level=high
Python
- Linter (Ruff):
ruff check "path" --fix(Fast & Modern) - Security (Bandit):
bandit -r "path" -ll - Types (MyPy):
mypy "path"
The Quality Loop
- Write/Edit Code
- Run Audit:
npm run lint && npx tsc --noEmit - Analyze Report: Check the "FINAL AUDIT REPORT" section.
- Fix & Repeat: Submitting code with "FINAL AUDIT" failures is NOT allowed.
Error Handling
- If
lintfails: Fix the style or syntax issues immediately. - If
tscfails: Correct type mismatches before proceeding. - If no tool is configured: Check the project root for
.eslintrc,tsconfig.json,pyproject.tomland suggest creating one.
Strict Rule: No code should be committed or reported as "done" without passing these checks.
Scripts
| Script | Purpose | Command |
|---|---|---|
scripts/lint_runner.py |
Unified lint check | python scripts/lint_runner.py <project_path> |
scripts/type_coverage.py |
Type coverage analysis | python scripts/type_coverage.py <project_path> |
04 同仓库更多 Skills
validation
Cross-cutting validation methodology for verifying phase outputs and project integrity
★ 1
session-management
Manages orchestration session state, tracking, and resumption
★ 1
implementation-planning
Generates detailed implementation plans from finalized designs
★ 1
execution
Phase execution methodology for orchestration workflows with error handling and completion protocols
★ 1
design-dialogue
Guides structured design conversations for complex engineering tasks
★ 1
delegation
Agent delegation best practices for constructing effective subagent prompts with proper scoping
★ 1