koubo SKILL.md skillC
koubo from 398894496-arch/tdharness-coding is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 398894496-arch/tdharness-coding/koubo@git:20261006.35f859bPins git:20261006.35f859b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 14 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 398894496-arch/tdharness-coding
- Path
server/koubo/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261006.35f859b, committed Oct 6, 2026
- Size
- 22,093 bytes
- Repository stars
- 37
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 口播短视频制作（koubo） 把一条口播素材做成一条包装好的剪映草稿。五步按顺序做，每一步有产出、有检查，上一步没过不做下一步。 ``` 1 对齐声画 → 2 转写 → 3 写脚本 → 4 找证据和素材 → 5 包装出草稿 → 看预览自查 ``` 命令是 `koubo`（Windows 上是本文件夹里的 `koubo.cmd`）。所有文件放在视频旁边的 `<视频名>.koubo` 文件夹（下面叫「工作文件夹」）。 出的是剪映草稿，不是成片：人在剪映里看过、导出。不要说「成片已完成」。 长什么样由**风格文件**定（字体、配色、字号、什么角色用什么包装、音效、美颜）。你只负责判断内容：留哪些句子、每句是什么角色、哪里分章节、哪些词是重点。不要自己发明包装。 --- ## 第 1 步 对齐声画 口播常常另外用领夹麦或录音笔录人声。有单独的人声文件就必须用它。 ``` koubo align "<视频>" --audio "<人声文件>" ``` - 输出 `AUDIO_MATCH_SCORE`（对得上的把握）和 `AUDIO_OFFSET`（差几秒）。 - 报 `audio-does-not-match-video`：这条录音不是这条视频的。停下来问用户，不要换一条硬对。 - 文件夹里有几条视频、几条录音，按文件名和时长配对；配不上就问。 - 没有单独的人声文件：跳过这步。但如果转写后发现现场有两个人的声音混在一起（见第 2 步），回来问用户要录音。 **过关**：有人声文件时，对齐成功。 ## 第 2 步 转写 ``` koubo transcribe "<视频>" [--audio "<人声文件>"] ``` 转写用这台机器上的识别模型，四分钟的口播大约一分钟，长素材按比例等，不要中途重跑。 工作文件夹里得到 `transcript.txt`（给你读）和 `transcript.json`（给工具用）。每行一句： ``` [12] 00:19.75–00:20.61 近 -11dB 衰老评估 [14] 00:22.07–00:23.57 远 -24dB 持续寻访监呃 ``` - `[12]` 句子编号，后面都用它。 - `近` 是出镜的人自己说的；`远` 是镜头外的人说的（提词的人先念一句、出镜的人再复述一句，是最常见的录法；也可能是提问或现场其他人）。工具先用声纹把声音分开，再看哪个声音响起时画面里的人在动。输出里 `VOICES=` 一行是结果；出现「分不出哪个是出镜的人」的 WARN 时，先问用户再往下做。 - `⏸2.1s` 这句前面停了多久。 **过关**：完整读完 `transcript.txt`，知道这条素材讲了什么、哪些是提词、哪些是重说。 ## 第 3 步 写脚本 …
Read the whole file at its exact version.
How to install
mdr add 398894496-arch/tdharness-coding/koubo@sha256:4a2b26199384402eThe line at the top of this page pins the label git:20261006.35f859b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_5p2y6nhxlq2gfjuf)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 6, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (22093 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
398894496-arch/tdharness-coding · 37 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5p2y6nhxlq2gfjuf GET https://markdownregistry.com/api/v1/resolve?ref=398894496-arch/tdharness-coding/koubo GET https://markdownregistry.com/api/v1/blob/4a2b26199384402e9c88df2376e41421b8460de7c3046cbfce113212c7eb5fc4
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.