← Back to Skills Marketplace
357
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-agent-discovery
Description
Agent发现探索助手。搜索、评估、集成公开Agent。使用场景：(1) 搜索可用Agent，(2) 评估Agent能力，(3) 集成方案设计，(4) 成本效益分析。
README (SKILL.md)
Agent Discovery — Agent发现助手
功能说明
帮助发现和评估可用的Agent系统。
使用方法
1. 能力搜索
用户: 找一下有哪些免费的代码审查Agent？
2. 评估对比
用户: 比较一下Claude和GPT的Agent能力
3. 集成方案
用户: 如何把这个Agent集成到我们的系统？
4. 成本分析
用户: 使用这个Agent的成本是多少？
Usage Guidance
This skill is an instruction-only helper and appears internally consistent. Before installing, consider: (1) what tools or web access your agent already has — the skill itself doesn't specify how searches happen, so an agent might use web browsing or other connectors you provide; (2) avoid supplying secrets or private system links in queries; (3) verify any external agent recommendations and cost estimates independently before integration; and (4) if you allow autonomous agent actions, review what tool permissions the agent will have, since autonomous web/tool access combined with other connectors could access data outside the skill's scope.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-agent-discovery
Version: 1.0.0
The skill bundle consists of metadata and documentation for an 'Agent Discovery' assistant. It contains no executable code, network requests, or suspicious instructions. The content in SKILL.md is limited to standard usage examples for searching and evaluating AI agents, posing no security risk.
Capability Assessment
Purpose & Capability
Name and description (searching, evaluating, integration design, cost analysis) align with the SKILL.md examples and there are no surprising requirements (no env vars, binaries, or installs).
Instruction Scope
SKILL.md contains only example user prompts and high-level guidance for searching and comparing agents. It does not instruct the agent to read files, access environment variables, call unexpected endpoints, or exfiltrate data.
Install Mechanism
No install spec and no code files — instruction-only, so nothing is written to disk or fetched during install.
Credentials
The skill declares no required credentials, environment variables, or config paths; this is proportionate to its stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modification of other skills or agent-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-agent-discovery - After installation, invoke the skill by name or use
/openclaw-agent-discovery - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of agent-discovery.
- Enables users to search, evaluate, and integrate publicly available agents.
- Supports capabilities search, agent ability comparison, integration solution guidance, and cost-effectiveness analysis.
- Provides usage examples for each main scenario in Chinese.
Metadata
Frequently Asked Questions
What is Agent Discovery?
Agent发现探索助手。搜索、评估、集成公开Agent。使用场景：(1) 搜索可用Agent，(2) 评估Agent能力，(3) 集成方案设计，(4) 成本效益分析。 It is an AI Agent Skill for Claude Code / OpenClaw, with 357 downloads so far.
How do I install Agent Discovery?
Run "/install openclaw-agent-discovery" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Discovery free?
Yes, Agent Discovery is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Discovery support?
Agent Discovery is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Discovery?
It is built and maintained by SKY-lv (@sky-lv); the current version is v1.0.0.
More Skills