---
name: self-contained-auditor-yashu
description: '评审一个技能是否「自包含」——即其知识、经验、规范是否全部内置在技能文件内（SKILL.md + references/），不依赖特定 AI 客户端专有的知识接口命令（如 read_me / modules: / show_widget / Visualizer）去外部拉取，也不硬编码某个 AI 软件的私有路径（如 .workbuddy）。同时检查工具依赖（node、浏览器、命令行）是否仅作为用户自备工具声明、未写死私有路径。当用户要求「评审这个技能是否自包含 / 独立」「检查技能知识是否内置」「审查技能的独立性 / 可移植性」「audit / review a skill for self-containment」时触发。产出评审报告：结论（自包含 / 不独立）+ 问题清单（文件:行号 + 引用的外部依赖 + 为何影响独立性）+ 整改建议。'
title: self-contained-auditor-yashu
canonical_url: https://skilld.dev/gh/steelan9199/wechat-publisher/self-contained-auditor-yashu
last_updated: 2026-10-07T07:20:50.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/checklist.md](https://skilld.dev/api/skills-raw/steelan9199/wechat-publisher/self-contained-auditor-yashu/references/checklist.md), [references/report-template.md](https://skilld.dev/api/skills-raw/steelan9199/wechat-publisher/self-contained-auditor-yashu/references/report-template.md).
>
> If the user asked to install this Skill, run `npx skilld install steelan9199/wechat-publisher/self-contained-auditor-yashu`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/self-contained-auditor-yashu`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/steelan9199/wechat-publisher/self-contained-auditor-yashu) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/self-contained-auditor-yashu`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/self-contained-auditor-yashu --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/self-contained-auditor-yashu --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# 自包含技能评审器

对一个指定技能做静态评审，判断它是否「自包含」：知识、经验、规范全部写死在技能自身文件里，不依赖宿主 AI 客户端的专有知识接口，也不写死某个 AI 软件的私有路径。本技能只读取目标技能的文件做分析，不实际运行目标技能。

## 何时使用

- 用户要求「评审这个技能是否自包含 / 独立」「检查技能知识是否内置」「审查技能独立性 / 可移植性」「audit / review a skill for self-containment」。
- 也可在交付或接收一个新技能前做自检。

## 评审的两个维度

1. **知识自包含（核心）**：规范、经验、领域知识是否全部在技能文件内（SKILL.md + references/）。若技能需要调用宿主专有命令去「拉取」规范 / 设计系统 / 知识，则知识未内置 → 不独立。
2. **宿主绑定**：是否硬编码了某个特定 AI 客户端专有的命令或私有路径（如 `.workbuddy`、其他软件的专属目录）。写死则技能无法在其他客户端使用 → 不独立（破坏可移植性）。

**工具依赖不算不独立**：Node.js、Python、浏览器、命令行工具等属于「用户自备工具」。要求仅在于：技能里应声明这些工具由用户提供，且不应硬编码某个软件的私有路径来指向它们。

## 工作流

1. **定位技能目录。** 用户会给出技能路径或技能名。定位其目录，确认存在 `SKILL.md`，以及可能存在的 `references/`、`scripts/`。

2. **读取全部文件。** 用 Read 工具读取：
   - `SKILL.md`（全文）
   - `references/` 下每个文件
   - `scripts/` 下每个文件（至少扫一遍，看是否引用宿主私有路径）
   若文件很多，先读 SKILL.md，再按需读 references / scripts。

3. **按评审清单逐项核对。** 加载 `references/checklist.md`，逐项检查：
   - 是否出现宿主专有「知识接口」命令（read_me、modules:、show_widget、Visualizer 等）且用于获取规范 / 知识。
   - references / 是否存在且内容完整（而非占位或仅指向外部）。
   - 是否写死某个 AI 软件的私有路径（`.workbuddy`、其他软件目录）。
   - 工具依赖是否声明为「用户自备」，未写死私有路径。
   - 是否有「若 X 不可用则回退到 references」之类的措辞（说明首选外部、内置只是兜底）。

4. **记录每条发现**，含：文件路径、行号（尽量精确到行）、引用的原文片段、属于哪个维度、为何影响独立性、严重度（阻断 / 建议）。

5. **给出结论与整改建议**，按 `references/report-template.md` 的结构输出报告。结论为「自包含」或「不独立（N 处问题）」。每条问题给出具体改法（例如：把被 read_me 拉取的设计系统复制进 `references/design-system.md`，第 1 步改为读该文件）。

## 判定原则

- 仅当**两个维度都通过**才判「自包含」。
- 知识靠外部命令拉取 = 阻断级不独立。
- 写死宿主私有路径 = 阻断级不独立（除非该路径是「用户需自行替换的占位」并在文中明确说明）。
- 工具依赖但声明清楚、无私有路径 = 通过。

## 自带资源

- `references/checklist.md`——自包含评审清单（知识内置检查项、宿主绑定检查项、工具依赖豁免项）。
- `references/report-template.md`——评审报告模板。
