CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Video Analyzer

zrong/skills
655 installs2 stars
Summary

This pulls frames from video files or URLs and sends them to vision models for analysis. You can point it at local files, direct video URLs, or even YouTube and Bilibili links (uses yt-dlp under the hood). It supports models like Doubao and OpenAI's vision APIs, with configurable frame extraction (default 10 frames, max dimension 720px). The workflow is straightforward: confirm the video source, clarify what the user wants to know, run the analyze.py script with your prompt, and show the results. Useful when you need to understand video content without watching it yourself, though keep in mind more frames mean better analysis but higher API costs.

Install to Claude Code

npx -y skills add zrong/skills --skill video-analyzer --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.mdView on GitHub

Video Analyzer

通过视觉/视频大模型分析视频内容,支持本地视频文件和互联网视频。

使用场景

  • 用户要求分析、理解或描述一段视频
  • 用户提供视频文件路径或 URL,希望了解视频内容
  • 用户需要对视频进行问答

配置

环境变量

根据使用的模型设置对应的 API Key 环境变量:

# 火山引擎(豆包)
export ARK_API_KEY="your-api-key"

# OpenAI
export OPENAI_API_KEY="your-api-key"

模型配置

编辑项目根目录的 agent_config.toml,在 [video-analyzer] 分区中配置模型:

[video-analyzer]
default_model = "doubao-vision"

[video-analyzer.models.doubao-vision]
base_url = "https://ark.cn-beijing.volces.com/api/v3"
api_key = "your-api-key"             # 直接填写(优先)
api_key_env = "ARK_API_KEY"          # 或从环境变量读取(api_key 为空时生效)
model = "doubao-seed-1-6-vision-250815"
api_type = "responses"
supports_video = false

每个模型需要:

  • base_url — API 地址
  • api_key — API Key(直接填写,优先读取)
  • api_key_env — 环境变量名(api_key 为空时 fallback)
  • model — 模型 ID
  • api_type — responses 或 chat_completions
  • supports_video — 是否支持原生视频输入

API Key 读取优先级:CLI --api-key > 配置文件 api_key > 环境变量 api_key_env

配置文件查找优先级:CWD → Skill 目录 → Git 根目录。可参考 agent_config.example.toml。

工作流程

  1. 确认视频来源:获取用户提供的视频路径或 URL。
  2. 确认分析需求:明确用户想了解什么(如概括内容、回答问题、描述场景等)。如果 $ARGUMENTS 非空,将其作为分析提示词。
  3. 选择模型:默认使用 models.json 中的 default_model,用户也可指定。
  4. 执行分析:运行脚本(在 scripts/ 目录下执行):
    uv run analyze.py --video <视频路径或URL> --prompt "<分析提示词>"
    
    可选参数:
    • --model <名称> — 指定模型(对应 models.json 中的 key)
    • --frames <数量> — 抽帧数量(默认 10)
    • --max-size <像素> — 帧最大边长(默认 720)
    • --json — 要求模型返回 JSON 并解析(自动附加视频帧数/帧率/时长到 prompt,便于返回帧序号);解析失败时降级打印原文
  5. 展示结果:将模型返回的分析结果展示给用户。

CLI 参考

# 本地视频
uv run analyze.py --video /path/to/video.mp4 --prompt "描述视频内容"

# 互联网直接视频 URL
uv run analyze.py --video https://example.com/video.mp4 --prompt "分析视频"

# 视频站点 URL(YouTube、Bilibili 等)
uv run analyze.py --video https://www.youtube.com/watch?v=xxxxx --prompt "总结视频"

# 指定模型和抽帧数
uv run analyze.py --video video.mp4 --model doubao-vision --frames 20 --prompt "分析"

# 结构化输出(要求 JSON,自动附视频帧数/帧率/时长,便于返回帧序号)
uv run analyze.py --video video.mp4 --prompt "用 JSON 描述视频的关键时刻" --json

# 典型用例:为 spritesheet 分析循环动画区间(prompt 模板见 references/loop-analysis.md)
uv run analyze.py --video animation.mp4 --prompt "<循环分析模板>" --json

注意事项

  • 视频站点 URL 下载依赖 yt-dlp,已作为 Python 依赖自动安装
  • 抽帧模式下,帧数越多分析越详细,但 API 调用成本也越高
  • 大视频文件下载可能需要较长时间,请耐心等待
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
First SeenMay 16, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k