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.
npx skills add Wanyi424/wanyi-watermark --skill wanyi-watermark-skillgit clone --depth 1 https://github.com/Wanyi424/wanyi-watermarkWrote 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.
[](https://agentmods.dev/skills/wanyi424/wanyi-watermark/wanyi-watermark-skill)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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
└── ...
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.
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.
- 12d ago First seen · 151 lines · 149 tokens per session scan A 7c2f58e1e516
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…