Feature Evolution
v1.0.0功能变更管理。当用户对一个已有规划（或已开发完成）的功能提出修改、补充或扩展需求时触发。覆盖两种场景：1）功能已开发完成，事后想迭代；2）功能开发进行中，中途想加东西或调整方向。触发词如'这个功能我想加一个XX'、'这里的逻辑需要调整'、'开发到一半发现还需要XX'、'想给XX功能扩展一下'。注意：如果功能连需求...
⭐ 0· 73·1 current·1 all-time
byp1866@cping6
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description describe managing incremental feature changes; SKILL.md only asks to read project spec files, optionally read a technical plan and project context, analyze impact, update docs, and generate an incremental task plan using the included template — all coherent with the stated purpose.
Instruction Scope
Instructions direct the agent to read and update files under specs/ and to search related code files and PROJECT-CONTEXT.md. This is expected for a change-management assistant, but the file-search scope is somewhat vague ("搜索相关代码文件"). It's reasonable, but users should be aware the skill will read repository files and write the generated change-task markdown to specs/features/{功能名}_变更任务_{CR序号}.md.
Install Mechanism
No install steps or external downloads — instruction-only skill. Nothing is written to disk by an installer; only the agent's runtime actions (reading/writing project files) are required.
Credentials
No environment variables, credentials, or config paths are requested. The skill operates on repository files and included template only, which is proportionate to its function.
Persistence & Privilege
always is false and the skill does not request system-wide privileges or modify other skills. It will write generated docs into the project (normal for this role). Autonomous invocation is allowed by default but is not combined with other concerning privileges.
Assessment
This skill appears coherent and limited to project documentation work, but before installing: ensure you want an agent that can read and write files in your repo (it will read specs/, search code, and create specs/features/{功能名}_变更任务_{CR序号}.md). Back up important docs, run the skill in a sandbox or test branch first, review generated change files before merging, and avoid granting the agent access to unrelated directories or secrets — the SKILL.md's "search related code files" is intentionally broad and could read any repo files it can access.Like a lobster shell, security has layers — review code before you run it.
latestvk972wfjptxmh4b3811recaena983khys
License
MIT-0
Free to use, modify, and redistribute. No attribution required.