← 返回 Skills 市场
anyhui

抖音学习流水线

作者 AleeAI · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
72
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install douyin-learning-pipeline
功能描述
抖音链接总控工作流（精简版）：自动区分"下载解析"和"文案提取"两类需求，并在需要时串联完成转写、智能修顺、结构拆解与后置仿写。Use when 用户发送抖音链接，要求"解析抖音""下载无水印""提取抖音文案""抖音转文字""提取口播稿""拆解这条视频""基于这条抖音做仿写"时触发。 固定主链：链接 → 转写 →...
使用说明 (SKILL.md)

douyin-learning-pipeline（精简版）

这是抖音相关任务的总控 skill，负责统一判断任务意图，并完成下载、转写、修顺、拆解与仿写。

零、启动时自检（必须先执行）

每次收到抖音相关任务，先执行环境自检：

自检清单

  1. Python 3 是否可用
  2. ffmpeg 是否已安装
  3. yt-dlp 是否已安装（用于备用下载）
  4. douyin-downloader 是否已部署
  5. SiliconFlow API Key 是否已配置
  6. 飞书文档写入能力 是否可用（如用户要求写飞书）

自检脚本

bash scripts/check_env.sh

自检失败时的处理

  • 缺安装：自动尝试安装（Python包用pip，系统包用apt/brew）
  • 缺配置：直接问用户要，例如：
    • 请提供 SiliconFlow API Key：
    • 请提供抖音 Cookie（msToken, ttwid 等）：
    • 请提供飞书文档目标位置：
  • 无法自动解决：明确告诉用户缺什么、怎么补

一、先做需求分流

A. 下载解析路线

当用户要的是素材文件，走这条：

  • 无水印视频
  • 图集原图
  • 本地文件
  • 真实下载地址

触发词示例：

  • 解析这个抖音
  • 下载这个视频
  • 无水印下载
  • 提取原图
  • 图集下载
  • 给我视频文件

B. 文案提取路线

当用户要的是内容文本，走这条：

  • 提取口播稿
  • 抖音转文字
  • 提取台词/话术
  • 整理成文案稿

触发词示例：

  • 提取这条抖音文案
  • 抖音转文字
  • 提取口播稿
  • 提取这条视频内容
  • 拆话术

C. 混合路线

如果用户同时要下载和提文案，则顺序固定：

  1. 先下载/解析
  2. 再转写/提文案

D. 模糊情况

如果只给链接、目标不明确：

  • 先做轻量识别（视频/图集、能否下载）
  • 若上下文已明确在做文案，则继续文案链路
  • 若仍模糊，只问一句短确认：
    • 这是要我帮你下载无水印，还是提取文案？

二、文案主链（固定顺序）

主链固定为： 链接 → 转写 → 修顺 → 拆解 → 仿写

1. 转写

  • 优先用自带的下载脚本获取音轨
  • 默认 ASR：TeleAI/TeleSpeechASR
  • 备选 ASR：FunAudioLLM/SenseVoiceSmall
  • 不默认回退到本地 Whisper，除非用户明确要求

2. 修顺

  • 默认模型：cpa/gpt-5.4
  • 备选：cpa/claude-sonnet-4-6
  • 输出要明确区分：
    • 原始转写稿
    • 智能纠错修复稿
    • 可能仍有误的片段（如有）

3. 拆解

默认可做：

  • 结构拆解
  • 钩子提炼
  • 平台改写

4. 仿写（后置步骤）

只有在以下情况才做：

  • 用户明确要仿写
  • 或者用户明确要模板/套写版本

仿写应基于已经提取和修顺好的内容进行，不要擅自和原始转写混写。

三、自带脚本

1. 环境自检脚本

scripts/check_env.sh

  • 检查所有依赖
  • 缺什么补什么
  • 无法自动补的就问用户

2. 抖音下载脚本

scripts/download_douyin.sh

  • 支持短链解析
  • 支持视频/图集下载
  • 支持音轨提取
  • 自动处理 Cookie

3. ASR 转写脚本

scripts/transcribe.sh

  • 默认用 TeleAI/TeleSpeechASR
  • 支持备选 SenseVoiceSmall
  • 自动调用 SiliconFlow API

四、配置管理（缺就问）

必需配置项

  1. SiliconFlow API Key

    • 环境变量：SILICONFLOW_API_KEY
    • 缺失时问用户：请提供 SiliconFlow API Key：

  2. 抖音 Cookie

    • 文件：assets/douyin-downloader/config.yml
    • 缺失时问用户：请提供抖音 Cookie（msToken, ttwid, odin_tt, passport_csrf_token, sid_guard）：

  3. 飞书文档目标

    • 可选，默认不写飞书
    • 如需写入，问用户：请提供飞书文档链接或token：

配置存储

  • 分发包只保留模板：assets/config.template.json
  • 用户真实配置写入本地文件：local/config.json
  • 首次运行时自动引导用户配置

五、依赖安装（缺就装）

Python 依赖

requests
yt-dlp

自动用 pip 安装

系统依赖

  • ffmpeg：音轨提取必需
    • Ubuntu/Debian: apt install ffmpeg
    • macOS: brew install ffmpeg
    • 缺失时先提示用户确认，再执行高权限安装

douyin-downloader

  • 如果未部署，自动克隆： 
    git clone https://github.com/jiji262/douyin-downloader.git
  • 引导用户配置 Cookie

六、默认交付规则

  • 定稿、长文、成体系内容：优先写飞书文档（如已配置）
  • 聊天里只回：链接 + 一句结论
  • 本 skill 不自建知识库 / 不自建索引
  • 如果宿主系统本身有知识库、记忆、归档能力，优先调用宿主本体能力
  • 如果宿主没有，就只完成当前任务结果，不额外做入库动作

七、迁移到其他系统

最小要求

  1. Python 3.8+
  2. 能联网
  3. 有 SiliconFlow 账号

迁移步骤

  1. 复制整个 douyin-learning-pipeline 目录
  2. 运行 scripts/check_env.sh
  3. 按提示补齐配置
  4. 开始使用

一键安装

# 下载 skill
git clone \x3Cskill-repo> douyin-learning-pipeline
cd douyin-learning-pipeline
# 自检并补依赖
bash scripts/check_env.sh
# 配置
python scripts/setup_config.py

八、与旧 skill 的关系

下面三个能力现在视为这个总控 skill 的子能力来源：

  • douyin-copy-extractor
  • transcript-polisher
  • script-analyzer

但这个精简版已经内嵌了它们的核心能力，可以独立运行。

安全使用建议
This skill contains a full Douyin downloader and related scripts and will ask for and store sensitive data (Douyin cookies, SiliconFlow API key, optionally Feishu/OPENAI tokens), auto-install Python packages and system tools, and fetch remote configuration/endpoint data. Before installing: 1) Verify the source / GitHub repo and publisher (the package has no homepage listed). 2) Do not supply full account cookies to untrusted code — prefer limited tokens or ephemeral credentials. 3) Run the skill in an isolated environment (VM/container) if you will allow automatic installs or execution. 4) Inspect scripts referenced by SKILL.md (scripts/check_env.sh, download_douyin.sh, transcribe.sh, setup_config.py) before running them, and decline automatic apt/brew sudo installs if unsure. 5) If you must use it, limit network access (or monitor outgoing connections) and consider sandboxing; restrict any Feishu tokens or other document tokens to least privilege. The primary red flags are the manifest/metadata mismatch about required secrets and the skill's ability to fetch remote configs and perform privileged installs — these make it reasonable to treat the package as potentially risky until you verify its origin and code.
功能分析
Type: OpenClaw Skill Name: douyin-learning-pipeline Version: 1.0.0 The skill bundle is classified as suspicious due to instructions in SKILL.md and scripts/check_env.sh that direct the AI agent to perform high-privilege system modifications, including 'sudo apt install' for ffmpeg and 'git clone' for external repositories (e.g., jiji262/douyin-downloader). While these actions are aligned with the stated goal of a self-configuring pipeline, they represent a significant security risk by allowing the agent to execute arbitrary code fetched from the internet and modify the host system's software. Additionally, assets/douyin-downloader/auth/ms_token_manager.py fetches remote configuration files from a third-party GitHub repository (Johnserf-Seed/f2) at runtime, introducing a supply-chain vulnerability.
能力标签
cryptorequires-wallet
能力评估
⚠ Purpose & Capability
The skill's code and SKILL.md implement a full Douyin downloader + transcription + postprocessing pipeline — that matches the name/description. However the registry metadata claims no required env vars or credentials while SKILL.md and the bundled code clearly require a SiliconFlow API key, Douyin cookies (msToken, ttwid, odin_tt, passport_csrf_token, sid_guard) and optionally document tokens (Feishu/OPENAI). The omission of these required secrets from the declared metadata is an inconsistency that reduces transparency.
⚠ Instruction Scope
Runtime instructions direct the agent to run environment checks and to auto-install missing dependencies (pip, apt, brew), to clone/execute downloader code, to ask the user for secrets (SiliconFlow API key and Douyin cookies) and to write local config and cookie files. It also calls external services (SiliconFlow API, optional mssdk endpoints via ms_token_manager using a remote conf URL, and could write to Feishu if configured). Asking for full account cookies and performing network calls are within the downloader's purpose, but the broad, automatic install-and-fetch behavior and the mismatch with declared requirements are scope and privacy concerns.
ℹ Install Mechanism
There is no formal install spec in the registry (instruction-only), but the package includes many code files and helper scripts. The SKILL.md instructs pip installs and system package installs (apt/brew) and may clone an external GitHub repo (https://github.com/jiji262/douyin-downloader.git). Cloning a public GitHub repo and pip/apt/brew installs are expected for this tooling, but they add risk because arbitrary code will be placed on disk and executed; the ms_token_manager also fetches remote YAML from raw.githubusercontent.com and may POST to a configured mssdk endpoint. This is moderate risk but not automatically malicious.
⚠ Credentials
The skill requests sensitive credentials in its instructions (SiliconFlow API key, Douyin cookie values, optional Feishu token, possibly OPENAI_API_KEY for transcription) but the registry metadata declares no required environment variables or primary credential. Requesting Douyin cookies is functionally required for no-watermark downloads and some msToken flows, but the absence of these requirements in the manifest is an incoherence. Users should treat provided cookies and API keys as high-value secrets.
ℹ Persistence & Privilege
The skill does not request persistent 'always' inclusion and does not claim to modify other skills. It will write local files (local/config.json, .cookies.json, download_manifest.jsonl, dy_downloader.db) and may run package managers requiring elevated privileges (apt/brew) if the environment is missing system dependencies — the auto-install behavior can perform privileged actions after user confirmation, which is a notable privilege-related surface but not an explicit persistent elevation of platform privileges.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install douyin-learning-pipeline
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /douyin-learning-pipeline 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug douyin-learning-pipeline
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

抖音学习流水线 是什么？

抖音链接总控工作流（精简版）：自动区分"下载解析"和"文案提取"两类需求，并在需要时串联完成转写、智能修顺、结构拆解与后置仿写。Use when 用户发送抖音链接，要求"解析抖音""下载无水印""提取抖音文案""抖音转文字""提取口播稿""拆解这条视频""基于这条抖音做仿写"时触发。 固定主链：链接 → 转写 →... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 72 次。

如何安装 抖音学习流水线？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install douyin-learning-pipeline」即可一键安装，无需额外配置。

抖音学习流水线 是免费的吗？

是的，抖音学习流水线 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

抖音学习流水线 支持哪些平台？

抖音学习流水线 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 抖音学习流水线？

由 AleeAI（@anyhui）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论