菜单
Clip URLs, PDFs, arXiv pages, WeChat articles, and technical blog posts into llm-wiki raw notes with localized images and source metadata.
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
Delegate coding tasks to the OpenAI Codex CLI agent for implementation, refactoring, PR review, batch issue fixing, and autonomous repository work.
Configure, troubleshoot, and extend Hermes Agent itself: CLI setup, config, tools, skills, gateway, providers, plugins, MCP, cron, memory, and agent development.
Codex built-in skill for structural code search with ast-grep when queries depend on AST shapes, call patterns, decorators, scopes, or required child nodes.
Codex curated GitHub skill for general GitHub app workflows: repository metadata, issues, pull requests, comments, and connector-backed context.
Codex curated Hugging Face skill for preparing, running, and packaging community evaluation tasks and benchmark submissions.
Codex curated GitHub skill for addressing pull request review comments, resolving threads, applying requested changes, and reporting verification.
| name | clip |
| description | Clip URLs, PDFs, arXiv pages, WeChat articles, and technical blog posts into llm-wiki raw notes with localized images and source metadata. |
| tags | ["clipping","url","pdf","arxiv","llm-wiki","raw-notes"] |
Use when the user gives a URL, PDF, arXiv link, web article, or blocked tech blog and wants it saved as a raw llm-wiki note.
Do not use for a broad wiki maintenance pass or thesis writing after the source has already been captured.
A source URL or local PDF plus the llm-wiki raw note destination.
