---
name: skill-bloat-auditor-yashu
description: 检查指定技能文档中的废话文字并输出诊断报告。激活条件：用户消息须包含以下关键词之一：`检查技能废话`、`这个技能文档有没有多余内容`、`清理技能文档废话`、`审查技能文档废话`、`清理技能文档历史说明`。
agent_created: true
title: skill-bloat-auditor-yashu
canonical_url: https://skilld.dev/gh/steelan9199/wechat-publisher/skill-bloat-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/bloat-patterns.md](https://skilld.dev/api/skills-raw/steelan9199/wechat-publisher/skill-bloat-auditor-yashu/references/bloat-patterns.md).
>
> If the user asked to install this Skill, run `npx skilld install steelan9199/wechat-publisher/skill-bloat-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/skill-bloat-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/skill-bloat-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/skill-bloat-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/skill-bloat-auditor-yashu --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/skill-bloat-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.

# 技能文档废话检查器

## 概述

扫描一个指定技能目录下的文档，识别并报告其中不构成"当前生效规则"的废话文字。废话分两类：历史/已废除/更正类（高置信，应删），以及导言/规则原理/自包含属性类（中置信，供人工确认）。只读、只报告，绝不修改目标文件。

## 工作流程

### 1. 定位目标技能

用户必须指定要检查的技能名，不能省略。

- 如果用户只给了技能的名字，那么就看系统提供的技能列表中有没有这个技能。
- 若用户给的是绝对路径，直接使用。
  确认目录存在；不存在则向用户报错并列出可用技能。

### 2. 确定扫描文件

扫描以下文件（用 Grep 工具，`output_mode=content` 带行号）：

- `<skill-dir>/SKILL.md`
- `<skill-dir>/references/*.md`（全部）

不扫描 `scripts/`、`assets/` 及非 `.md` 文件。

### 3. 匹配废话模式

加载 `references/bloat-patterns.md` 中的模式清单，分两类匹配：

- **A 类（高置信）**：历史/已废除/更正类关键词与短语（含"不再设/取消限制"等隐含历史变更的写法）。命中所在行整行上报。
- **B 类（中置信）**：导言/规则原理/自包含属性类正则模式（含"自包含""不依赖外部命令""所有知识都在本文件+示例内"等同族变体）。命中行上报，标注「中置信·请人工确认」。

匹配时注意 `bloat-patterns.md` 末尾的「减少误报注意事项」与「冗余与重复表述」原则：不把单独「为了/因为」作关键词；跳过代码块、SVG `<text>`、注释；对"自包含/不依赖外部命令"等主张做跨行去重，重复出现的只建议留一处。

命中后做二次过滤：判断该文字去掉后，所在规则是否仍完整可执行--是->判为废话；否->规则本体，保留。这是"以是否构成当前生效规则为准"原则的可执行落地，避免关键词命中后被粗放归组为"规则本体"而漏报。

### 4. 生成报告（只报告，不改文件）

输出结构化报告，格式：

```
## 废话检查报告：<skill-name>
扫描文件：<列出已扫文件>
命中总数：<n>

### A 类（高置信 · 建议删除）
- 文件：<path> 行 <n>  [类型：历史/已废除]
  原文：<命中行原文>
  说明：<一句为什么是废话>

### B 类（中置信 · 请人工确认）
- 文件：<path> 行 <n>  [类型：导言/原理/自包含]
  原文：<命中行原文>
  说明：<提示用户判断>

（若无命中，写明「未发现废话」）
```

报告末尾给出总结建议（如「A 类可直接删除；B 类请按需保留；重复的自包含/不依赖外部命令主张只留一处」）。

### 5. 绝不修改

本技能只产出报告。删除/修改动作由用户另行决定，或由用户显式要求后才执行。

## 资源

- `references/bloat-patterns.md`：废话模式清单（A/B 两类、关键词、正则、误报注意）。

## 设计原则

- 只读诊断，不写文件，避免误删有用内容。
- 废话判定以"是否构成当前生效规则"为准，而非文风偏好。
- 中置信条目必须标注，交人工判断，不替用户做删留决定。
