douyin-video-distiller SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 5 indexed copies. Same content hash, so the same checks give both the same grade.
douyin-video-distiller from 3378925604-a11y/douyin-video-distiller is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add 3378925604-a11y/douyin-video-distiller/douyin-video-distiller@git:20261021.64c824ePins git:20261021.64c824e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- 3378925604-a11y/douyin-video-distiller
- Path
.opencode/skills/douyin-video-distiller/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261021.64c824e, committed Oct 21, 2026
- Size
- 8,726 bytes
- Repository stars
- 3
- License
- MIT
抖音视频蒸馏 Skill。用户提供抖音链接、视频文件或要求把短视频提炼成知识卡片、摘要、时间线、证据、行动项、Wiki 内容或第二大脑资料时使用；也适用于"帮我把这个视频真正变成可检索知识"等未明确说蒸馏的请求。 English triggers: turn a Douyin or Chinese short-video link into knowledge cards, summarize a video with timestamps, extract transcript and burned-in on-screen text from a short video, distill a video into second-brain notes with evidence grading.
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
# 抖音视频蒸馏 ## 核心原则 把视频处理成可复用知识，而不是只生成泛泛摘要。必须区分视频明确说出/展示的内容、模型归纳、用户可能需要确认的推测，并尽量保留时间戳。下载失败、视频不可访问或视觉模型不支持完整视频时，要如实报告并停止冒充已完成。**覆盖校验（强制）**：对照 `ffprobe` 拿到的视频总时长检查输出时间戳，模型没覆盖到的时间段必须显式标注"未分析"，不得把"模型没看"当成"视频里没有"；输出尾部出现复读或角色标签幻觉（`Human:` 等）时截断采信并在"待确认"注明截断点。 ## 输入与权限 支持抖音链接、本地视频和用户提供的转录文本。链接下载需要用户已有访问权限；不绕过验证码、登录墙、访问控制或平台限制。Cookie、API Key 和账号信息只从本机安全配置读取，不显示、不写入输出、不上传到 Wiki。 ## 第 0 步：环境自检与分析通道选择（必做，别直接开跑） 按顺序探测，走第一个能跑的通道；全部不通就向用户要转录文本，**不得凭链接内容瞎编蒸馏结果**： 1. **通道 A · 本地模型**：检查环境变量 `OMNI_MODEL_PATH` 指向的目录里有没有 `config.json` + safetensors 权重，且本机有 ≥8GB 显存（`nvidia-smi`）。三者齐备 → 用 `scripts/analyze_omni.py`。缺权重 → 引用本 skill README「获取模型权重」一节的直链与命令（hf 官方 / aifasthub / hf-mirror / ModelScope 四选一），权重就绪后回到本步；缺显存 → 下一通道。 2. **通道 B · 用户提供文本**：A 不通时，请用户粘贴抖音自带的图文转录或第三方转文字结果，走纯文本蒸馏流程（质量降级，需在输出里注明"仅基于文本，无画面证据"）。 下载同理：链接一律按 `douyin-video-download` skill 里的「CDP 登录态提取法」执行（该 skill 唯一路径）；不要尝试 yt-dlp/纯 HTTP 解析/cookie 导出等已被抖音反爬淘汰的做法，用户手动给来本地视频路径则直接进分析。 ## 执行流程 1. 判断输入类型。链接先解析并保存原始链接信息；本地视频记录文件路径、大小、时长和格式；文本直接进入转录蒸馏流程。 2. 处理抖音链接时，调用已安装的 `douyin-video-download` skill（CDP 登录态提取法），按其文档步骤下载视频到临时目录。不要复制下载器源码，也不要输出视频签名直链、Cookie 或凭据。 …
Read the whole file at its exact version.
How to install
mdr add 3378925604-a11y/douyin-video-distiller/douyin-video-distiller@sha256:e1fbf8971d42e906The line at the top of this page pins the label git:20261021.64c824e, 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_tak5ejmgy777ufzq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 21, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8726 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
Source
3378925604-a11y/douyin-video-distiller · 3 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tak5ejmgy777ufzq GET https://markdownregistry.com/api/v1/resolve?ref=3378925604-a11y/douyin-video-distiller/douyin-video-distiller GET https://markdownregistry.com/api/v1/blob/e1fbf8971d42e906a91884eb96927949836980f710e18f9ea0e3063a705a9ae8
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.
More from 3378925604-a11y/douyin-video-distiller
Every file in 3378925604-a11y/douyin-video-distiller