PhilRobinluo/ai-coevolution-skills / skills/lls-skill-lifecycle-manager
lls-skill-lifecycle-manager
Verified管理相互隔离的私有 Skill 母库与公开 Skill 分享库。用于在选定仓库内新建、升级、查重、审计、打包、发布或恢复 Skill,并维护该仓库自己的版本、来源、许可证、GitHub Release、飞书说明、WorkBuddy 与 SkillHub 状态。两库各自是真源,公开版只能独立创作和审核;不建立复制、镜像、同步、自动导出或一键公开链路。
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 3.7 KB |
| SKILL.md | skill md | 13.6 KB |
| agents/openai.yaml | config | 341 B |
| references/licensing-strategy.md | markdown | 1.9 KB |
| references/operating-checklists.md | markdown | 1.8 KB |
| references/provenance-and-trust.md | markdown | 1.2 KB |
| references/repository-architecture.md | markdown | 1.6 KB |
| references/test-scenarios.md | markdown | 1.5 KB |
| scripts/audit-repository.pyexecutable | script | 3.0 KB |
references/operating-checklists.md
View on GitHub# 运行检查表
## 选库与隔离
- [ ] 已明确本轮唯一写入库:私有母库或公开分享库
- [ ] 没有把另一仓库设为复制源、构建输入或脚本参数
- [ ] 没有子模块、共享 worktree、符号链接、镜像或一键公开
- [ ] 公开任务仅使用公开资料和公开版测试夹具
## 新建或升级
- [ ] 在选定仓库内查重并决定新建、升级、合并或跳过
- [ ] 确认 slug、显示名、用户、来源类型和真实任务
- [ ] 只修改当前仓库自己的真源
- [ ] 更新该仓库自己的版本和变更说明
- [ ] 校验 SKILL.md、references、scripts 和 agents
## 许可证
- [ ] 原创内容标为 `CC-BY-NC-SA-4.0`
- [ ] 含实质 `scripts/` 时同时标为 `PolyForm-Noncommercial-1.0.0`
- [ ] 第三方或改编内容保留上游许可证与来源
- [ ] 企业内部额外许可和商业授权入口清楚
- [ ] 历史 MIT 版本边界已记录
## 打包
- [ ] 敏感信息扫描通过
- [ ] ZIP 只含当前 Skill 运行文件与许可证
- [ ] ZIP 根目录为 `<slug>/SKILL.md`
- [ ] 解压测试和代表性脚本测试通过
- [ ] SHA256 已记录
## GitHub、飞书与 SkillHub
- [ ] 当前目录和 remote 都属于公开分享库
- [ ] 公开 registry 的来源、许可证和版本正确
- [ ] push 后 Actions 成功
- [ ] Release tag、ZIP、SHA256 和源码版本一致
- [ ] 飞书页面写后读回
- [ ] SkillHub 最终提交仍保留逐版本确认
## 对账与恢复
- [ ] 平台副本按所属真源分类
- [ ] 以所属仓库正式版本做三方比较
- [ ] 独有修改先进入恢复区
- [ ] 没有跨库覆盖或批量倒灌
- [ ] 更新运行副本前已准备回滚,更新后已触发测试
## 最终报告
- [ ] PASS / REWORK / UNCOVERED / BLOCKED 清楚
- [ ] 每个 PASS 有命令、链接、日志或读回
- [ ] 残余风险真实
- [ ] 下一次升级动作明确
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |