Zhishuo workflows
把真实项目经验整理成可安装、可检查、可追溯的 Agent Skills｜PDF、视频、文档、项目收口与视觉审美工作流
npx -y skills add zgzdhr/zhishuo-workflows --skill zhishuo-workflowsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use only when the user explicitly invokes zhishuo-workflows to choose among Zhishuo project closeout, PDF knowledge-base, video transcription, or visual-taste application workflows. This is a router, not a general productivity skill.
SKILL.md
2.5 KB, 794 tokens by cl100k_base, as published. Nobody here has run it
智说工作流路由
这个 Skill 只做一件事：把用户的任务路由到一个边界清楚的子 Skill。不要在这里执行完整流程，也不要把尚未支持的任务硬塞进现有 Skill。
路由步骤
- 用一句话复述用户真正要得到的结果，而不是只重复文件类型。
- 对照下表选择一个主 Skill；如果任务包含连续阶段，写明执行顺序。
- 告知用户已选择的 Skill、选择理由和关键边界。
- 读取并执行对应子 Skill。没有匹配项时停止路由，说明当前目录没有覆盖。
完成标准：每个任务只有一个主流程，或有一个明确的多流程顺序；不存在“同时调用所有 Skill”。
路由表
| 用户目标 | 使用 Skill | 稳定锚点 | 不处理 |
|---|---|---|---|
| 项目阶段结束、暂停、归档、交接或检查能否恢复 | zhishuo-close-project | 收口 | 普通开发与修 Bug |
| 大部头或多份 PDF 需要长期检索、拆章和回源 | zhishuo-build-pdf-knowledge-base | 派生链 | 一次性阅读短 PDF、少量普通拆解 |
| 单条或批量 B 站/YouTube 视频、本地视频需要变成可追溯文字 | zhishuo-transcribe-video | 字幕优先 | 视频剪辑与摘要排版 |
| 网页、产品、作品集或演示需要明确视觉方向、设计 token 或审美验收 | zhishuo-apply-visual-taste | 视觉合同 | 复制第三方截图或只做随机美化 |
多阶段任务
- “把视频转写后做 PDF 知识库”：先视频转写，再在用户确认文字资产后评估是否需要 PDF 知识库；不要把视频摘要冒充 PDF 来源。
- “按智说审美做页面并收口项目”：先生成视觉合同并完成真实渲染验收，再执行项目收口。
首发边界
- macOS Apple Silicon 是外部工具真实运行的已验证基线；仓库安装与匿名核心测试覆盖 macOS 和 Windows。
- 视频批量入口支持 B 站 UP 主空间与 YouTube 频道/播放列表，但必须先限制范围并核对清单。
- 证据文档修订计划在 v0.2 发布，本版本不路由也不分发。
- 没有 Agent 的用户可阅读子 Skill 和运行检测脚本，但没有自动路由。
需要核对版本状态时读取 catalog reference。
Gives 0 of the 12 instructions most video audio skills give in 794 tokens
Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07
- read individual rule files for detailed explanationsin 21 of 622, across 10 files
- render final videoin 13 of 622, across 6 files
- Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
- Use this skill when dealing with Remotion codein 11 of 622, across 4 files
- save generated audio to a WAV filein 11 of 622, across 4 files
- handle conversion errors gracefullyin 10 of 622, across 6 files
- add captions to videos alwaysin 10 of 622, across 4 files
- generate music from text descriptions using MusicGenin 9 of 622, across 2 files
- do not skip pipeline layersin 9 of 622, across 3 files
- do not make one tool do everythingin 9 of 622, across 3 files
- use azure document intelligence for complex pdfsin 9 of 622, across 4 files
- never ask the user to paste their full API keyin 9 of 622, across 3 files
Said here and by no other author read
- restate the user's actual desired result in one sentence
- select exactly one primary skill per task
- state the selected skill, selection reason, and key boundaries
- read and execute the corresponding sub-skill
- specify the execution order for multi-stage tasks
- stop routing when no skill matches
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.