菜单
Summarize or extract text/transcripts from URLs, podcasts, and local files. Use when asked to summarize a URL, article, video, or local document.
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
| name | summarize |
| description | Summarize or extract text/transcripts from URLs, podcasts, and local files. Use when asked to summarize a URL, article, video, or local document. |
| version | 1.0.0 |
| author | OctoAgent |
| tags | ["summarize","extract","url","transcript"] |
| tools_required | ["terminal.exec"] |
Fast CLI to summarize URLs, local files, and YouTube links.
summarize "https://example.com" --model google/gemini-3-flash-preview
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto
Best-effort transcript (URLs only):
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract-only
If the transcript is huge, return a tight summary first, then ask which section to expand.
Set the API key for your chosen provider:
OPENAI_API_KEYANTHROPIC_API_KEYGEMINI_API_KEYDefault model is google/gemini-3-flash-preview if none is set.
--length short|medium|long|xl|xxl|<chars>--max-output-tokens <count>--extract-only (URLs only)--json (machine readable)--firecrawl auto|off|always (fallback extraction)--youtube auto (Apify fallback if APIFY_API_TOKEN set)Optional config file: ~/.summarize/config.json
{ "model": "openai/gpt-5.2" }
配置 OctoAgent 的 LLM Provider、模型别名和 Memory 模型绑定。适用于新增 SiliconFlow / OpenRouter / OpenAI 等 Provider、设置 main / cheap / memory aliases，以及说明 Web / CLI / Agent 的正确配置入口与生效方式。
Build, scaffold, and register MCP (Model Context Protocol) servers for OctoAgent. Use when: (1) creating a new MCP server from scratch, (2) adding tools/resources to an existing MCP server, (3) registering an MCP server with OctoAgent's MCP registry, (4) debugging MCP server connectivity. NOT for: using existing MCP tools (those are auto-available), general API integrations without MCP.
Delegate coding tasks to OctoAgent Workers. Use when: (1) building/creating new features, (2) reviewing PRs, (3) refactoring codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use filesystem tools directly).
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub repos, or cloning (use git clone).
View LiteLLM Proxy model usage and cost data. Use when: user asks about model costs, token usage, spending breakdown, or API usage statistics. Queries LiteLLM spend endpoints.
Edit PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to edit, modify, or update PDF content on specific pages.