wanyi-watermark-skill

wanyi-watermark-skill is a skill for Claude Code, Codex from Wanyi424/wanyi-watermark. It costs 149 tokens per session (1,638 once invoked), scanned A, original, Apache-2.0.

A tool for resolving Douyin, Xiaohongshu, and some other share links into videos, image collections, or transcribed text. It can find direct media links, download resources, and use speech recognition to turn video speech into a Markdown file.

In plain words
What is it for?
Use it to inspect or download videos and image posts, obtain Xiaohongshu images in WebP or PNG, and extract video wording when the required speech-recognition service is configured.
Why use it?
It removes the need to manually identify the platform and content type or retrieve media through each platform's page format.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect or download videos and image posts, obtain Xiaohongshu images in WebP or PNG, and extract video wording when the required speech-recognition service is configured.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wanyi424/wanyi-watermark/wanyi-watermark-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Wanyi424/wanyi-watermark --skill wanyi-watermark-skill
Clone the repo
git clone --depth 1 https://github.com/Wanyi424/wanyi-watermark

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wanyi-watermark-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill/github.svg)](https://agentmods.dev/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill)
Your own site
<a href="https://agentmods.dev/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill"><img src="https://agentmods.dev/badge/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wanyi-watermark-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill"><img src="https://agentmods.dev/badge/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.01638
Opus 5 $0.00075 $0.00819
Sonnet 5 $0.00030 $0.00328
Haiku 4.5 $0.00015 $0.00164

Measured 12d ago against content hash 7c2f58e1e516, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wanyi-watermark-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/media_cli.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

wanyi-watermark-skill/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

抖音/小红书无水印资源下载与文案提取

从抖音、小红书(及未适配平台的通用兜底)分享链接获取无水印视频/图文资源, 下载到本地, 并可使用语音识别提取视频文案保存为 Markdown 文件.

功能概述

  • 智能解析: 自动识别平台(抖音/小红书/通用)与内容类型(视频/图文), 无需手动指定
  • 无水印视频: 解析出无水印视频直链, 可直接下载
  • 图文资源: 解析图文笔记的全部图片; 小红书图片提供 WebP(轻量)与 PNG(高清)双格式
  • 下载资源: 将视频或图集下载到本地指定目录
  • 提取文案: 通过语音识别从视频中提取文字内容(支持阿里云百炼 / 硅基流动双后端)
  • 通用兜底: 遇到未适配平台时, 自动基于页面 og:video / video 标签等通用信息尝试提取

环境要求

依赖安装

本技能依赖 wanyi-watermark 包及其声明的运行依赖. 在 server/mcp-server 目录下:

pip install -e .

API 密钥配置 (仅"提取文案"需要)

文案提取支持两种 ASR 后端,通过 ASR_BACKEND 环境变量切换(默认 dashscope):

方案 A — 阿里云百炼(默认,URL 直传无需 ffmpeg):

export DASHSCOPE_API_KEY="your-dashscope-api-key"

获取 API 密钥: https://help.aliyun.com/zh/model-studio/get-api-key

方案 B — 硅基流动 SenseVoice(需本地 ffmpeg):

export SILICONFLOW_API_KEY="your-siliconflow-api-key"
export ASR_BACKEND="siliconflow"

获取 API 密钥: https://cloud.siliconflow.cn/

链接解析、资源下载均无需 API 密钥; 仅"提取文案"需要.

使用方法

方法一: 使用命令行 (推荐)

技能脚本 scripts/media_cli.py 是对包内 CLI 的轻量封装, 可直接运行:

# 获取信息和无水印直链 (无需 API 密钥, 支持抖音/小红书/通用)
python scripts/media_cli.py --link "分享链接" --action info

# 下载视频或图集到指定目录
python scripts/media_cli.py --link "分享链接" --action download --output ./output

# 提取视频文案(默认百炼,需 DASHSCOPE_API_KEY)
python scripts/media_cli.py --link "分享链接" --action extract --output ./output

# 使用硅基流动 SenseVoice 后端(需 SILICONFLOW_API_KEY + ffmpeg)
python scripts/media_cli.py --link "分享链接" --action extract --backend siliconflow --output ./output

# 提取文案并同时保存视频
python scripts/media_cli.py --link "分享链接" --action extract --output ./output --save-video

若已 pip install -e . 安装本包, 亦可使用模块或控制台入口:

python -m wanyi_watermark.cli --link "分享链接" --action info
# 或
wanyi-watermark-cli --link "分享链接" --action info

输出目录结构

output/
├── 7600361826030865707/        # 视频ID / 笔记ID 为文件夹名
│   ├── transcript.md           # extract 时生成的 Markdown 文案
│   └── 7600361826030865707.mp4 # 使用 --save-video 时保存
├── <note_id>/                  # 图文笔记: 图集逐张保存
│   ├── 01.png
│   └── 02.png
└── ...

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 151 lines · 149 tokens per session scan A 7c2f58e1e516

Subscribe to this mod's changes

wanyi-watermark-skill is a skill published in the GitHub repository Wanyi424/wanyi-watermark (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 149 tokens to every session and 1,638 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens