SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

open-agent-hub

guanyang/open-agent-hub

A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).

打开仓库Open repository

怎么装：Install: npx skills@latest add guanyang/open-agent-hub

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.1%+0.1%

973 → 974 stars · 5 个快照973 → 974 stars · 5 snapshots

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

SKILLS-CLI

$

README 里给出的安装方式。The installation method given in the README.

SKILLS-CLI

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/guanyang/open-agent-hub
原始数据哈希Raw data hash: 14f7d8f3241f3392246984739923e459
解析时间Parsed at: 2026-10-07T23:29:09.707Z
最后一次验证Last verified: 2026-10-07T22:10:25.670Z
增长测量时间Growth measured: —
发现查询Discovery queries: focus:token:repo:topic-context-engineering
分类来源Category source: rules
焦点Focus: token (5)

静态扫描STATIC SCAN

01控制浏览器Controls a browserskills/baoyu-danger-gemini-web/SKILL.md

This is a best-effort CDP session reuse path, not the Chrome DevTools MCP prompt-based `--autoConnect` flow described in Chrome's official d

02读取 API KeyReads an API keyskills/baoyu-image-gen/SKILL.md

If `--provider openai --model gpt-image-2.5-flare` fails because `OPENAI_API_KEY` is missing but the current runtime has a native image-gene

03读取 API KeyReads an API keyskills/baoyu-imagine/SKILL.md

If `--provider openai --model gpt-image-2` fails because `OPENAI_API_KEY` is missing but the current runtime has a native image-generation b

04控制浏览器Controls a browserskills/baoyu-markdown-to-html/SKILL.md

**Mermaid rendering**: Code blocks fenced as ` ```mermaid ` are rendered to PNGs via headless Chrome (CDP) and cached at `imgs/.mermaid-cach

05需要系统权限Needs system permissionsskills/baoyu-wechat-summary/SKILL.md

- **wx-cli reinit**. If `wx history` suddenly returns nothing after a WeChat restart, the keys may be stale. Tell the user to run `sudo wx i

06读写本地文件Reads and writes local filesskills/filesystem-context/SKILL.md

Write plans to the filesystem because long-horizon tasks lose coherence when plans fall out of attention or get summarized away. The agent r

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude-plugin/"
    },
    {
      "agent": "gemini-cli",
      "evidence": "readme: …~/.gemini/antigravity/` | | **Gemini CLI** | CLI | ✅ Full | `.gemini/`…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …| `.trae/` | `~/.trae/` | | **OpenCode** | CLI | ✅ Full | `.opencode…"
    },
    {
      "agent": "claude-ai",
      "evidence": "skills/algorithmic-art/SKILL.md: …ile that works immediately in claude.ai artifacts or any browser. Sta…"
    },
    {
      "agent": "vscode",
      "evidence": "skills/baoyu-electron-extract/SKILL.md: …/ Cursor / Discord / Slack / VS Code / Notion / Obsidian / ChatGPT…"
    },
    {
      "agent": "codex",
      "evidence": "skills/baoyu-image-gen/SKILL.md: …-model gpt-image-2.5-flare # Codex CLI (uses logged-in Codex subscri…"
    }
  ],
  "apiKey": "ent variables** (preferred): `X_AUTH_TOKEN`, `X_CT0` 2. **Chrome login** (fallback",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 2,
      "dev-tools": 3,
      "indie-web": 0,
      "skill-agent": 6,
      "productivity": 3
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "ference infrastructure level (vLLM, TGI, or cloud provider APIs) - Product",
  "skillMdTotal": 113,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 1,
    "media": 0,
    "design": 10,
    "browser": 0,
    "devtool": 4,
    "security": 2,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 1007 markdown files",
      "weight": 0.75
    },
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    },
    {
      "signal": ".mcp.json (configures servers it uses)",
      "weight": 0.3
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "skills/academy-guide/SKILL.md",
    "skills/advanced-evaluation/SKILL.md",
    "skills/algorithmic-art/SKILL.md",
    "skills/baoyu-article-illustrator/SKILL.md",
    "skills/baoyu-comic/SKILL.md",
    "skills/baoyu-compress-image/SKILL.md",
    "skills/baoyu-cover-image/SKILL.md",
    "skills/baoyu-danger-gemini-web/SKILL.md",
    "skills/baoyu-danger-x-to-markdown/SKILL.md",
    "skills/baoyu-diagram/SKILL.md",
    "skills/baoyu-electron-extract/SKILL.md",
    "skills/baoyu-format-markdown/SKILL.md",
    "skills/baoyu-image-cards/SKILL.md",
    "skills/baoyu-image-gen/SKILL.md",
    "skills/baoyu-imagine/SKILL.md",
    "skills/baoyu-infographic/SKILL.md",
    "skills/baoyu-markdown-to-html/SKILL.md",
    "skills/baoyu-post-to-wechat/SKILL.md",
    "skills/baoyu-post-to-weibo/SKILL.md",
    "skills/baoyu-post-to-x/SKILL.md",
    "skills/baoyu-slide-deck/SKILL.md",
    "skills/baoyu-translate/SKILL.md",
    "skills/baoyu-url-to-markdown/SKILL.md",
    "skills/baoyu-wechat-summary/SKILL.md",
    "skills/baoyu-xhs-images/SKILL.md",
    "skills/baoyu-youtube-transcript/SKILL.md",
    "skills/bdi-mental-states/SKILL.md",
    "skills/brainstorming/SKILL.md",
    "skills/brand-guidelines/SKILL.md",
    "skills/canvas-design/SKILL.md",
    "skills/claude-academy-guide/SKILL.md",
    "skills/claude-api/SKILL.md",
    "skills/composition-patterns/SKILL.md",
    "skills/context-compression/SKILL.md",
    "skills/context-degradation/SKILL.md",
    "skills/context-fundamentals/SKILL.md",
    "skills/context-optimization/SKILL.md",
    "skills/defuddle/SKILL.md",
    "skills/diagnosing-superpowers/SKILL.md",
    "skills/discernment-nudge/SKILL.md",
    "skills/dispatching-parallel-agents/SKILL.md",
    "skills/doc-coauthoring/SKILL.md",
    "skills/docx/SKILL.md",
    "skills/evaluation/SKILL.md",
    "skills/executing-plans/SKILL.md",
    "skills/filesystem-context/SKILL.md",
    "skills/finishing-a-development-branch/SKILL.md",
    "skills/frontend-design/SKILL.md",
    "skills/harness-engineering/SKILL.md",
    "skills/hosted-agents/SKILL.md",
    "skills/internal-comms/SKILL.md",
    "skills/json-canvas/SKILL.md",
    "skills/knap/SKILL.md",
    "skills/latent-briefing/SKILL.md",
    "skills/long-horizon-prompting/SKILL.md",
    "skills/mcp-builder/SKILL.md",
    "skills/mediabunny/SKILL.md",
    "skills/memory-systems/SKILL.md",
    "skills/multi-agent-patterns/SKILL.md",
    "skills/notebooklm/SKILL.md"
  ],
  "skillMdFetched": 60
}