standards by boshu2/agentops
npx skills add https://github.com/boshu2/agentops --skill standards按需加载的特定语言编码标准,供其他技能使用。
这是一个库技能——它不独立运行,而是提供标准参考,供其他技能根据处理的文件类型加载。
| 标准 | 参考文件 | 加载者 |
|---|---|---|
| 技能结构 | references/skill-structure.md | vibe(技能审计)、doc(技能创建) |
| Python | references/python.md | vibe、implement、complexity |
| Go | references/go.md | vibe、implement、complexity |
| Rust | references/rust.md |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| vibe、implement、complexity |
| TypeScript | references/typescript.md | vibe、implement |
| Shell | references/shell.md | vibe、implement |
| YAML | references/yaml.md | vibe |
| JSON | references/json.md | vibe |
| Markdown | references/markdown.md | vibe、doc |
技能声明 standards 为依赖项:
skills:
- standards
然后根据文件类型加载相应的参考文件:
# 标准加载的伪代码
if file.endswith('.py'):
load('standards/references/python.md')
elif file.endswith('.go'):
load('standards/references/go.md')
elif file.endswith('.rs'):
load('standards/references/rust.md')
# 等等。
对于全面审计,技能可以从 vibe/references/*-standards.md 加载扩展标准,这些文件包含完整的合规性目录。
| 标准 | 大小 | 使用场景 |
|---|---|---|
| 第 1 层(本技能) | 每个约 5KB | 常规验证 |
| 第 2 层(vibe/references) | 每个约 15-20KB | 深度审计,--deep 标志 |
使用标准的技能:
/vibe - 根据更改的文件类型加载/implement - 为正在修改的文件加载/doc - 加载 Markdown 标准/bug-hunt - 为根本原因分析加载/complexity - 为重构建议加载用户说: /vibe(检测到更改的 Python 文件)
发生的情况:
auth.pystandards/references/python.md结果: Python 代码根据特定语言标准进行验证,无需手动加载参考。
用户说: /implement ag-xyz-123(问题修改了 Go 文件)
发生的情况:
server.gostandards/references/go.md 以获取上下文结果: 生成的 Go 代码符合标准,减少了实施后的 vibe 发现的问题。
| 问题 | 原因 | 解决方案 |
|---|---|---|
| 标准未加载 | 文件类型未检测到或缺少标准技能 | 检查文件扩展名是否与参考文件匹配;验证依赖项中是否包含标准 |
| 加载了错误的标准 | 文件类型识别错误(例如,.sh 误认为 .bash) | 手动指定标准;更新文件类型检测逻辑 |
| 缺少深度标准 | Vibe 需要扩展目录,但未找到 | 检查 vibe/references/*-standards.md 是否存在;使用 --deep 标志 |
| 标准冲突 | 同一变更集中包含多种语言 | 加载所有相关标准;按主要语言确定优先级 |
每周安装数
192
仓库
GitHub 星标数
197
首次出现
2026年2月2日
安全审计
安装于
claude-code190
codex190
opencode189
github-copilot188
kimi-cli188
gemini-cli188
Language-specific coding standards loaded on-demand by other skills.
This is a library skill - it doesn't run standalone but provides standards references that other skills load based on file types being processed.
| Standard | Reference | Loaded By |
|---|---|---|
| Skill Structure | references/skill-structure.md | vibe (skill audits), doc (skill creation) |
| Python | references/python.md | vibe, implement, complexity |
| Go | references/go.md | vibe, implement, complexity |
| Rust | references/rust.md | vibe, implement, complexity |
| TypeScript | references/typescript.md | vibe, implement |
| Shell | references/shell.md | vibe, implement |
| YAML | references/yaml.md | vibe |
| JSON | references/json.md | vibe |
| Markdown | references/markdown.md | vibe, doc |
Skills declare standards as a dependency:
skills:
- standards
Then load the appropriate reference based on file type:
# Pseudo-code for standard loading
if file.endswith('.py'):
load('standards/references/python.md')
elif file.endswith('.go'):
load('standards/references/go.md')
elif file.endswith('.rs'):
load('standards/references/rust.md')
# etc.
For comprehensive audits, skills can load extended standards from vibe/references/*-standards.md which contain full compliance catalogs.
| Standard | Size | Use Case |
|---|---|---|
| Tier 1 (this skill) | ~5KB each | Normal validation |
| Tier 2 (vibe/references) | ~15-20KB each | Deep audits, --deep flag |
Skills that use standards:
/vibe - Loads based on changed file types/implement - Loads for files being modified/doc - Loads markdown standards/bug-hunt - Loads for root cause analysis/complexity - Loads for refactoring recommendationsUser says: /vibe (detects changed Python files)
What happens:
auth.py in changesetstandards/references/python.md automaticallyResult: Python code validated against language-specific standards without manual reference loading.
User says: /implement ag-xyz-123 (issue modifies Go files)
What happens:
server.go in implementation scopestandards/references/go.md for contextResult: Go code generated conforming to standards, reducing post-implementation vibe findings.
| Problem | Cause | Solution |
|---|---|---|
| Standards not loaded | File type not detected or standards skill missing | Check file extension matches reference; verify standards in dependencies |
| Wrong standard loaded | File type misidentified (e.g., .sh as .bash) | Manually specify standard; update file type detection logic |
| Deep standards missing | Vibe needs extended catalog, not found | Check vibe/references/*-standards.md exists; use --deep flag |
| Standard conflicts | Multiple languages in same changeset | Load all relevant standards; prioritize by primary language |
Weekly Installs
192
Repository
GitHub Stars
197
First Seen
Feb 2, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
claude-code190
codex190
opencode189
github-copilot188
kimi-cli188
gemini-cli188
agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试
140,500 周安装
GrepAI MCP 与 Claude Code 集成指南:为AI编程助手启用语义代码搜索
241 周安装
Tailwind CSS 开发指南:v3 特性、深色模式、Flexbox/Grid 布局与最佳实践
241 周安装
Tailwind CSS 最佳实践指南:10条核心规则提升前端开发效率与代码质量
241 周安装
UI设计技能包 - Claude技能库中的UI设计与用户体验工具
241 周安装
阿里云AI图像编辑测试技能 - 通义千问图像编辑最小可行测试验证
242 周安装
阿里云AI技能测试指南:alicloud-ai-misc-crawl-and-skill-test 最小化验证与错误排查
242 周安装