菜单
Describe images in detail using Claude Code CLI. Use when you need a detailed description of an image's content, especially when the standard image analysis tools are unavailable. Works with local image files (jpg, png, etc.) by spawning Claude Code with the image path.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Apple Calendar.app integration for macOS. CRUD operations for events, search, and multi-calendar support.
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
Fetch and summarize YouTube video transcripts. Use when asked to summarize, transcribe, or extract content from YouTube videos. Handles transcript fetching via residential IP proxy to bypass YouTube's cloud IP blocks.
Fetch the OpenClaw changelog from GitHub and return it in markdown form. Use when the user asks about OpenClaw updates, what's new, recent changes, release notes, version history, or the changelog itself.
Deep research methodology for sub-agents and spawn tasks. Use when spawning research tasks, investigating claims, comparing products/services, or gathering comprehensive information on any topic. Ensures source diversity, cross-referencing, bias detection, and confidence assessment. Automatically applied to research-type spawns.
Semantic search and memory retrieval using txtai. Use when searching through workspace files, finding relevant documents, or answering questions about prior work, decisions, or content stored in the workspace. Provides semantic search across all indexed text files (markdown, code, configs, etc.).
| name | claude-image-analyzer |
| description | Describe images in detail using Claude Code CLI. Use when you need a detailed description of an image's content, especially when the standard image analysis tools are unavailable. Works with local image files (jpg, png, etc.) by spawning Claude Code with the image path. |
Describes images in detail using the Claude Code CLI as a fallback when standard image analysis APIs are unavailable.
image tool failsscripts/claude-image-analyzer.sh <image-path>
When an image is downloaded (e.g., from Discord attachments):
# Image is saved to media inbound directory (see SKILLS.md for path)
IMAGE_PATH="<media-inbound-dir>/image.jpg"
# Describe it
scripts/claude-image-analyzer.sh "$IMAGE_PATH"
claude) to be installed and on PATHIf this skill is unavailable or too slow, consider:
image tool with different models