← 返回 Skills 市场
alexfleetcommander

Agent Matchmaking

作者 alexfleetcommander · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ⚠ suspicious
152
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install agent-matchmaking
功能描述
Cross-platform agent discovery and trust-weighted matching for the autonomous agent economy. Capability profiles, reputation-based ranking, compatibility sco...
使用说明 (SKILL.md)

Agent Matchmaking Protocol (AMP)

You have a cross-platform agent discovery system. Use it to find the best agent for a task based on capabilities, reputation, and compatibility.

Setup

pip install agent-matchmaking

When to Use This Skill

  • When you need to find an agent for a specific task
  • When comparing candidates for delegation
  • When publishing your capabilities for discovery by other agents
  • When building Unified Capability Profiles for yourself or other agents

Core Operations

Create a Capability Profile

from agent_matchmaking import CapabilityProfile

profile = CapabilityProfile(
    agent_id="your-agent-id",
    capabilities=["web_research", "data_analysis", "report_writing"],
    specializations={"domain": "financial_services", "languages": ["en", "zh"]},
    availability=True,
    pricing={"base_rate": 0.02, "currency": "USD", "per": "request"}
)
profile.save("my_profile.json")

Search for Agents

from agent_matchmaking import search_agents

results = search_agents(
    task_type="legal_research",
    required_capabilities=["web_search", "document_analysis"],
    preferred_reputation_min=0.7,
    max_results=5
)
for agent in results:
    print(f"{agent.id}: score={agent.match_score}, reputation={agent.reputation}")

Compatibility-Weighted Ranking

from agent_matchmaking import rank_candidates

ranked = rank_candidates(
    candidates=["agent-a", "agent-b", "agent-c"],
    task_profile={"type": "translation", "source": "en", "target": "zh"},
    weights={"capability_match": 0.4, "reputation": 0.3, "price": 0.2, "availability": 0.1}
)

Profile Fields

Field Description
capabilities What the agent can do (list)
specializations Domain expertise and constraints
availability Currently accepting work
pricing Cost per request/token/hour
reputation_ref Link to ARP reputation data
provenance_ref Link to CoC chain for verified history

Rules

  • Keep profiles current. Update availability and pricing as they change.
  • Be accurate. Overstating capabilities leads to poor ratings and disputes.
  • Use reputation data. Always factor in ARP scores when ranking candidates.

Links


\x3C!-- VAM-SEC v1.0 | Vibe Agent Making Security Disclaimer -->

Security & Transparency Disclosure

Product: Agent Matchmaking Skill for OpenClaw Type: Skill Module Version: 0.1.0 Built by: AB Support / Vibe Agent Making Contact: [email protected]

What it accesses:

  • Reads and writes capability profile files in your working directory
  • No network access for core local operations
  • No telemetry, no phone-home, no data collection

What it cannot do:

  • Cannot access files outside your working directory beyond what you explicitly specify
  • Cannot make purchases, send emails, or take irreversible actions
  • Cannot access credentials, environment variables, or secrets

License: Apache 2.0

安全使用建议
This skill is instruction-only and tells you to run `pip install agent-matchmaking` (a package not shipped with the skill). Installing that package will download and run third-party code — review the PyPI project page and source repository before installing. Ask the author for: (1) a link to the package source (GitHub or similar) and a commit/tag you can inspect, (2) a reproducible install with pinned versions or hashes, and (3) clarification about network usage and what endpoints the package contacts for matchmaking/reputation. If you must test it, do so in an isolated sandbox or container, and avoid running it with sensitive credentials present. If you rely on the skill for production, require code review or prefer a bundled, verifiable implementation.
功能分析
Type: OpenClaw Skill Name: agent-matchmaking Version: 0.1.1 The skill bundle provides documentation and instructions for an agent discovery and matchmaking system. The code examples in SKILL.md are standard Python library usage, and the metadata in _meta.json is consistent with the stated purpose. While it requires installing a third-party package (agent-matchmaking) via pip, there is no evidence of malicious intent, prompt injection, or unauthorized data access in the provided files.
能力评估
Purpose & Capability
The stated purpose (agent discovery, matchmaking, reputation-aware ranking) aligns with requiring python3 and pip to use a Python library. However the skill describes federation and reputation lookups yet does not declare any API credentials or network requirements — plausible if public registries are used, but ambiguous.
Instruction Scope
SKILL.md instructs you to run `pip install agent-matchmaking` and import the package to perform searches and rankings. Because the package is not bundled, this means executing third‑party code at runtime. The included Security & Transparency Disclosure also asserts "No network access for core local operations" which conflicts with the implied need for network (pip install and likely registry/reputation queries).
Install Mechanism
There is no install spec in the skill bundle; the SKILL.md tells users to pip install from PyPI. While PyPI is a standard host, installing an external package downloads and executes remote code not reviewed with the skill. The skill does not provide pinned hashes, a source repository link for the package implementation, or offline/bundled alternatives — increasing supply‑chain risk.
Credentials
The skill requests no environment variables or credentials, which is reasonable for local profile management. However, federation, reputation, and registry features typically involve network endpoints or tokens; the lack of declared credentials is ambiguous (it may rely on public APIs, implicit unauthenticated access, or ask for credentials at runtime).
Persistence & Privilege
The skill does not request always:true, does not claim to modify other skills, and is user-invocable. It writes/reads profile files in the working directory per the disclosure, which is proportionate to the stated purpose.
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 agent-matchmaking
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agent-matchmaking 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
v0.1.1
SEO: fixed name format, added tags, enhanced description, added author metadata
v0.1.0
Initial release -- cross-platform agent discovery and matching
元数据
Slug agent-matchmaking
版本 0.1.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Agent Matchmaking 是什么?

Cross-platform agent discovery and trust-weighted matching for the autonomous agent economy. Capability profiles, reputation-based ranking, compatibility sco... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 152 次。

如何安装 Agent Matchmaking?

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

Agent Matchmaking 是免费的吗?

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

Agent Matchmaking 支持哪些平台?

Agent Matchmaking 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 Matchmaking?

由 alexfleetcommander(@alexfleetcommander)开发并维护,当前版本 v0.1.1。

💬 留言讨论