维护者工具包
- 作者仓库星标 0
- 作者仓库 skills-registry
- 领域
- 效率工具
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @tomevault-io · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- 未检出明确要求
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
./install.sh --project --target /path/to/repo --yes
./install.sh --global --yes
python3 scripts/init_skill.py issue-triage
python3 scripts/quick_validate.py .codex/skills/issue-triage
# Codex OSS Maintainer Toolkit
Use this skill to turn an open-source repository into a Codex-friendly maintainer workspace.
## Quick Start
```bash
./install.sh --project --target /path/to/repo --yes
./install.sh --global --yes
python3 scripts/init_skill.py issue-triage
python3 scripts/quick_validate.py .codex/skills/issue-triage
```
## What This Skill Optimizes
- project-level `AGENTS.md`
- maintainer-focused Codex skills
- issue triage and bug-investigation workflows
- PR review and release-note prompts
- reusable verification commands
- cross-session dev docs for long-running tasks
## Recommended Workflow
1. **Audit the repository**
- Identify maintainer bottlenecks: issue triage, review latency, release friction, repeated debugging.
- Map the folders that need project-specific instructions.
2. **Write AGENTS.md close to the work**
- Keep global instructions short.
- Add repo-specific rules, validation commands, and ownership notes.
- Prefer operational guidance over abstract philosophy.
3. **Move repeatable tasks into skills or scripts**
- Use `scripts/init_skill.py` for reusable task playbooks.
- Put durable procedures in `references/`.
- Put deterministic checks in `templates/automation/` or project scripts.
4. **Design for maintainers, not demos**
- Prioritize issue triage, review, release, dependency updates, and regression checks.
- Keep verification commands next to the workflow that needs them.
5. **Validate before shipping**
- Run targeted checks.
- Search for stale branding or paths.
- Keep templates and examples in sync.
## Maintainer Workflow Patterns
### Issue Triage
- summarize the report
- classify bug vs feature vs support request
- link affected paths and owners
- propose the next maintainer action
### PR Review
- inspect diff boundaries first
- check architecture, tests, rollback risk, and release notes
- produce actionable comments instead of generic praise
### Debugging
- reproduce first
- inspect the failing path before editing
- test one hypothesis at a time
- verify both the fix and the absence of regressions
### Release Notes
- group changes by user-facing impact
- capture migrations, flags, or rollout constraints
- link verification commands and rollback notes
## Files to Read When Needed
- `references/workflows.md`: multi-step maintainer workflow patterns
- `references/output-patterns.md`: structured output formats for triage, review, and release communication
- `templates/AGENTS.md`: project bootstrap template
- `templates/automation/README.md`: helper script usage
## Validation Checklist
- [ ] `AGENTS.md` matches the repository layout
- [ ] public docs use Codex/OpenAI terminology consistently
- [ ] skills are concise and validated
- [ ] automation scripts have explicit inputs and outputs
- [ ] examples and templates stay synchronized
---
> Source: [ComeOnOliver/skillshub](https://github.com/ComeOnOliver/skillshub) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-05-23 -->
章节与文件索引
按说明文件中的顺序排列。
该技能优化了什么
推荐工作流程
问题分类
公关审查
调试
文件/命令 -> AGENTS.md · scripts/init_skill.py · references/ · templates/automation/ · references/workflows.md · references/output-patterns.md · templates/AGENTS.md · templates/automation/README.md
内容校验值 -> f2de5528f66f
当前原文的自动摘译,尚未人工审校。
该技能优化了什么
项目级
AGENTS.md以维护人员为中心的 Codex 技能问题分类和错误调查工作流程 PR 审查和发布说明提示 可重用的验证命令推荐工作流程
审核存储库 识别维护者瓶颈:问题分类、审查延迟、释放摩擦、重复调试。映射需要特定于项目的说明的文件夹。将 AGENTS.md 写在靠近工作的地方 保持全局指令简短。
问题分类
总结报告,对错误、功能和支持请求进行分类,链接受影响的路径,所有者提出下一个维护者行动
公关审查
检查差异边界,首先检查架构、测试、回滚风险和发行说明,生成可操作的评论,而不是一般的赞扬
调试
重现 在编辑之前首先检查失败的路径 一次测试一个假设 验证修复和不存在回归