免费在 GitHub 公开

review

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

中文简介正在准备中。当前显示原文说明。

PyModel/pythinker-code

查看安装方法

包含的文件（1）

SKILL.md2.7 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Review sub-skills (`sub-skill.review`)

Analyze the current skill inventory and identify candidate groups that could be consolidated into sub-skill bundles. This sub-skill is read-only: it produces a proposal for the user to review before any file changes are made by sub-skill.consolidate.

When to use

The user asks to review, reorganize, or audit the skill inventory.
There are many loosely-related skills that might benefit from hierarchical grouping.
The user wants to evaluate whether a new skill should be a sub-skill of an existing parent.

Process

List the current inventory. Use the skill registry (or scan the configured skill roots) to get a full list of skill names, descriptions, and source scopes.
Categorize by domain. Group skills by functional domain — e.g. file operations, web tools, collaboration, observability.
Detect coupling. Identify skills that are frequently used together or share similar whenToUse conditions.
Flag granularity issues. Call out skills that are too fine-grained (e.g. one skill per CLI flag) or too broad to land in any single domain.
Propose sub-skill structures. For each candidate group, list:
- The parent skill name and a one-line description.
- The children that should move under it.
- Any documentation, reference, example, asset, or template directories that must move with each child so the final directory layout stays aligned.
- Whether the parent needs has-sub-skill: true (it does, if children should be discovered).
Output a summary report. Present findings as a concise grouped list with rationale, and stop. Do not edit any file — that's sub-skill.consolidate's job.

Criteria for a good sub-skill grouping

Shared context. Children operate within the same domain or workflow.
Composable entry point. The parent gives a natural top-level handle; children handle specifics.
Shallow nesting. Prefer 2 levels (parent → child). Avoid 3+ unless strictly necessary.
Backward compatibility. Existing skill names should ideally remain discoverable.

Example output format

Proposed sub-skill: web-research
  - Parent: web-research (has-sub-skill: true)
  - Children:
    - web-search    → move under web-research/search
    - fetch-url     → move under web-research/fetch
  - Documentation alignment: move each child's references/examples/assets with that child.
  - Rationale: Both deal with online information retrieval and are often chained together.

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

同一仓库的技能

agent-browser

免费

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

中文简介正在准备中。当前显示原文说明。