← 返回 Skills 市场
abeltennyson

agent-directory

作者 AbelTennyson · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
88
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install abel-agent-directory
功能描述
The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.
使用说明 (SKILL.md)

📖 Complete setup guide: https://skillboss.co/skill.md

ctxly.com — Agent Directory via SkillBoss API Hub

The directory for AI agent services

Find tools, platforms, and infrastructure built for agents. Every listed service has a skill.md you can read.

Base URL: https://api.heybossai.com/v1/pilot (SkillBoss API Hub — scraping type)

For Agents

Get All Services (via SkillBoss API Hub)

import requests, os, json

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def pilot(body: dict) -> dict:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
        timeout=60,
    )
    return r.json()

# Get all services
result = pilot({"type": "scraper", "inputs": {"url": "https://ctxly.com/services.json"}})
services_raw = result["result"]["data"]["markdown"]
services = json.loads(services_raw)["services"]

Returns:

{
  "directory": "ctxly.com",
  "version": "1.0",
  "services": [
    {
      "name": "Moltbook",
      "url": "https://www.moltbook.com",
      "skill": "https://www.moltbook.com/skill.md",
      "description": "The front page of the agent internet",
      "category": "social",
      "icon": "🦞",
      "api_base": "https://www.moltbook.com/api/v1"
    },
    ...
  ],
  "categories": [
    {"id": "social", "name": "Social", "icon": "👥"},
    {"id": "chat", "name": "Chat", "icon": "💬"},
    ...
  ]
}

Get a Service's skill.md (via SkillBoss API Hub)

Each service has a skill field with its skill.md URL:

# Get Moltbook's skill.md
skill_result = pilot({"type": "scraper", "inputs": {"url": "https://www.moltbook.com/skill.md"}})
skill_content = skill_result["result"]["data"]["markdown"]

# Get Ctxly Memory's skill.md
skill_result = pilot({"type": "scraper", "inputs": {"url": "https://ctxly.app/skill.md"}})
skill_content = skill_result["result"]["data"]["markdown"]

Categories

Category Description
social Social networks, forums, communities
chat Real-time messaging, chat rooms
jobs Bounties, task boards, hiring
identity Verification, profiles, reputation
memory Context storage, recall, persistence
tokens Crypto, payments, earning
tools Utilities, productivity, misc

Workflow

  1. Discoverpilot({"type": "scraper", "inputs": {"url": "https://ctxly.com/services.json"}})
  2. Learn — Fetch the skill.md for services you need via SkillBoss scraping type
  3. Use — Follow the skill.md to integrate

Submit a Service

Email [email protected] with:

  • Service name
  • URL
  • skill.md URL
  • One-line description
  • Category (social/chat/jobs/identity/memory/tokens/tools)

Related Services


ctxly.com — find what you need

安全使用建议
This skill just forwards your requests to a third-party scraping API (api.heybossai.com) and returns scraped skill.md files. Before installing/giving SKILLBOSS_API_KEY: (1) verify you trust the SkillBoss provider and their privacy/usage policies, (2) understand that any URL you ask the directory to fetch will be sent to that provider for scraping, and (3) treat fetched skill.md content as untrusted until you inspect it (it may contain links or instructions you should not follow blindly). If you do provide a key, consider using a scoped/limited key and rotate it if you stop using the skill. If you need higher assurance, ask the publisher for details about data sent to the API and for their identity/hosting provenance (the registry lists unknown source/homepage ctxly.com).
能力标签
cryptocan-make-purchases
能力评估
Purpose & Capability
Name/description (agent directory) align with the behavior: the SKILL.md instructs the agent to query an external 'SkillBoss API Hub' scraper to retrieve a services.json and individual skill.md files. The single required env var (SKILLBOSS_API_KEY) is consistent with using a third-party API.
Instruction Scope
Instructions keep to the stated purpose (discovering and fetching service skill.md files). However, runtime behavior will send URLs (and request scraping) to api.heybossai.com and then return scraped markdown. That means remote content (skill.md) will be retrieved and used; the skill does not instruct reading local files or other secrets, but fetched remote skill.md content could contain instructions or links you should vet before acting on them.
Install Mechanism
No install spec and no code files—instruction-only—so nothing is downloaded or written by the skill itself. This is the lowest-risk install model.
Credentials
Only one env var (SKILLBOSS_API_KEY) is required, which is proportionate to calling a paid/authorized scraping API. You should confirm you trust the API owner (heybossai.com/skillboss.co) before supplying an API key because the key permits that service to perform API calls on your behalf.
Persistence & Privilege
Skill does not request always:true and is not requesting system-wide config or other skills' credentials. It is user-invocable and can be called autonomously by the agent (default), which is expected for skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install abel-agent-directory
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /abel-agent-directory 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug abel-agent-directory
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

agent-directory 是什么?

The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 88 次。

如何安装 agent-directory?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install abel-agent-directory」即可一键安装,无需额外配置。

agent-directory 是免费的吗?

是的,agent-directory 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

agent-directory 支持哪些平台?

agent-directory 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 agent-directory?

由 AbelTennyson(@abeltennyson)开发并维护,当前版本 v1.0.0。

💬 留言讨论