Skip to main content
skill CX Codex

agent-protocol · borghei — Claude Code skill: what it does, how to install

agent-protocol — a skill for Claude Code designs tool schemas and communication layers between AI agents. It targets setups using MCP, Google A2A, or OpenAI Function Calling.

LicenseRef-MIT-Commons-Clause 104 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill agent-protocol -a claude-code
Open on GitHub

What agent-protocol does

The skill guides interface definitions for LLM tools, crafts descriptive parameter schemas, and maps transport options like stdio, SSE, or WebSocket.

The repository includes three Python utilities: schema_generator.py for turning signatures into JSON, protocol_validator.py for schema verification, and capability_mapper.py for conflict detection across integrations. Running these verification steps locally requires a working Python interpreter.

What it helps with

  • design JSON schemas for MCP servers and OpenAI function calling
  • set up agent-to-agent communication through Google A2A
  • validate tool descriptions and parameters against strict schema rules
  • detect duplicate tools across different protocol definitions

Example prompts for the agent

  • Generate an MCP tool schema for an internal documentation search query
  • Validate this tool schema JSON using scripts/protocol_validator.py in strict mode
  • Compare Google A2A and MCP transports for connecting two external services

How to install agent-protocol

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill agent-protocol -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-protocol/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-protocol/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agent-protocol

How to install agent-protocol in Claude Code?

Run npx skills add borghei/Claude-Skills --skill agent-protocol -a claude-code. The skill file installs to ~/.claude/skills/agent-protocol/SKILL.md.

What does agent-protocol do?

It structures tool interfaces, parameter definitions, and agent-to-agent messaging protocols across MCP, Google A2A, and OpenAI formats.

Which utilities come with the skill?

The package bundles schema_generator.py for building schemas, protocol_validator.py for compliance checks, and capability_mapper.py for inventory and overlap scans.

Similar skills

All skills for Agent setup: memory, context, orchestration →

agent-protocol by other authors comes first.

agent-protocol Alireza Rezvani The agent-protocol skill defines how C-suite agents call each other, return findings, and avoid loops. Use it when several roles must coordinate an analysis. CX Codex +1 611installs tools launchdarkly tools is a Claude Code and Codex skill that creates tool definitions and links them to LaunchDarkly config variations. It guides setup through a remote MCP server. CX Codex +1 1,900installs tool-function-schema-designer patricio0312rev tool-function-schema-designer turns a rough tool idea into a JSON schema, a typed interface, a validation layer and example calls the model can actually follow. CX Codex +1 258installs NEXUS Protocol abasensei NEXUS Protocol bridges MCP and A2A protocols to register, discover, and assign tasks to AI agents across a decentralized marketplace with trust scoring. CX Codex +1 508installs structured-output-extractor patricio0312rev The structured-output-extractor skill for Claude Code extracts typed data from LLM responses using JSON Schema, Zod, and function calling. It supports JSON parsing and result validation. CX Codex +1 323installs qianwen-text QianWen-AI qianwen-text is a Claude Code skill for chatting with Qwen, generating text and code, and calling functions. It activates on Qwen requests or an explicit skill name. CX Codex +1 6,200installs openai-api-development Mindrally openai-api-development — a skill that steers your coding agent through Anthropic API work: Claude calls, function calling, embeddings and Assistants API, with Python examples. CX Codex +1 906installs

From the same set120

The whole set →
nis2-directive-specialist The nis2-directive-specialist skill supports NIS2 scope checks, cybersecurity control reviews, supply-chain analysis, and incident-reporting readiness for covered entities. CX Codex +1 105installs chief-of-staff chief-of-staff scores how complex a founder's question is, then sends it to one or more C-suite advisors or runs a board meeting. Useful when departments disagree. CX Codex +1 104installs brainstorm-experiments The brainstorm-experiments skill for Claude Code and Codex turns a product hypothesis into a low-cost experiment with a pass threshold set in advance. It selects a method for a new idea or an existing feature. CX Codex +1 104installs analytics-tracking analytics-tracking is a Claude Code skill that builds and audits GA4 and GTM setups, structures event taxonomies, and troubleshoots broken conversions. CX Codex +1 104installs ai-seo ai-seo — a skill for Claude Code prepares content to earn citations in AI search answers. It supports GEO work, LLM visibility reviews, and citability audits. CX Codex +1 102installs identify-assumptions identify-assumptions — a skill for Claude Code that uncovers product assumptions and scores impact against confidence. Runs before engineering experiments start or when team members debate delivery risks. CX Codex +1 102installs outcome-roadmap outcome-roadmap — a skill for Claude Code transforms feature backlogs into outcome-based roadmaps using Now/Next/Later horizons. Runs during quarterly planning and strategy alignment sessions. CX Codex +1 102installs dora-compliance-expert The dora-compliance-expert Claude Code skill assesses a financial entity’s readiness for DORA. It also classifies ICT incidents and helps plan oversight of external ICT providers. CX Codex +1 101installs

Project sponsors

Companies that keep this analytics open