agent-to-agent skills

136 tagged agent-to-agent, measured the same way as everything else here.

Browse within: a2a 70agent-harness 40agent-os 40binary16 40local-first 40a2a-protocol 32agentcore 25amazon-bedrock 25browser-automation 25agent-governance 13agent-runtime 13ai-company 13ai-team 13end-to-end-encryption 11

draw-image

01

ai-sns/ai-sns

Skill Claude CodeCodex

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

339 +1 28d ago A 67 tokens original MIT

A2A JSON-RPC Call

02

ai-sns/ai-sns

Skill Claude CodeCodex

Call a peer agent's A2A JSON-RPC endpoint. Supports tasks/send (send a task message) and tasks/get (query task status).

339 +1 28d ago A 38 tokens original MIT

Fetch Agent Card

03

ai-sns/ai-sns

Skill Claude CodeCodex

Fetch an A2A agent card JSON from a given endpoint URL. Tries direct GET first, then falls back to /.well-known/agent.json.

339 +1 28d ago A 35 tokens original MIT

code-agent

04

aws-samples/sample-strands-agent-with-agentcore

Skill Claude CodeCodex ✓ vendor

Autonomous coding agent. Delegate any task that involves understanding, writing, or running code — from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.

191 6d ago A 47 tokens original MIT

coding-tools

07

markus-global/markus

Skill Claude CodeCodex

Use external coding tools (Claude Code, Codex, Cursor) via invokecodingtool and codingtoolapply to implement, debug, and refactor code.

157 6d ago A 34 tokens original Apache-2.0

team-building

08

markus-global/markus

Skill Claude CodeCodex

Design and create AI team packages — manifest format, member structure, directory layout.

157 6d ago A 18 tokens original Apache-2.0

workflow-building

09

markus-global/markus

Skill Claude CodeCodex

Design and create workflow templates — YAML format, DAG patterns, scheduling, and role mapping.

157 6d ago A 20 tokens original Apache-2.0

Join.cloud

10

kushneryk/join.cloud

Skill Claude CodeCodex

Collaboration rooms for AI agents — join rooms, send messages, coordinate with other agents in real time.

63 1mo ago A 23 tokens AGPL-3.0

hermeshub-reviewer

11

amanning3390/hermeshub

Skill Claude CodeCodex

Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.

34 +1 2mo ago A 38 tokens original MIT

testing-agentmeet

12

matanrak/agent-meet

Skill Claude CodeCodex

Test AgentMeet end-to-end flows for room creation, agent token registration, /read polling, and read receipt UI rendering.

24 2mo ago A 29 tokens original MIT

dcp-citizenship

13

dcp-ai-protocol/dcp-ai

Skill Claude CodeCodex

Digital Citizenship Protocol — identity, intent declaration, and audit trail for AI agents.

23 1mo ago A 22 tokens original Apache-2.0

ironmesh-audit

14

WizTheAgent/IronMesh

Skill Claude CodeCodex

Tail the tamper-evident IronMesh audit log for security events. Use when investigating a TOFU mismatch, auth failure, peer dropping out, or a suspected attack.

22 13d ago A 40 tokens original MIT

ironmesh-peers

15

WizTheAgent/IronMesh

Skill Claude CodeCodex

Drill into per-peer IronMesh metrics — retry reasons, session rekeys, offline-since, transport type. Use when ironmesh-status shows a problem on a specific peer and you need detail.

22 13d ago A 47 tokens original MIT

ironmesh-send

16

WizTheAgent/IronMesh

Skill Claude CodeCodex

Send an application message (MSG) to a specific IronMesh peer. Use when the user asks to "send X to agent Y" or "ping peer Z". Has side effects — only invoke when the user explicitly asks.

22 13d ago A 49 tokens original MIT

agent-bus

17

MustaphaSteph/agent-bus

Skill Claude CodeCodex

Coordinate work across Claude/Codex/Cursor sessions on the same machine via a local message bus. Use to delegate to helpers, get a second opinion, ask specialists by capability, or track shared tasks.

17 +1 2mo ago A 45 tokens original MIT

arxiv-search

18

akudo7/kudosflow

Skill Claude CodeCodex

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.

10 5mo ago A 27 tokens

langgraph-docs

19

akudo7/kudosflow

Skill Claude CodeCodex

Use this skill for requests related to LangGraph.js (JavaScript/TypeScript) in order to fetch relevant documentation to provide accurate, up-to-date guidance.

10 5mo ago A 37 tokens

teams

20

akudo7/kudosflow

Skill Claude CodeCodex

Analyzes user prompts and dynamically creates and launches a team of specialist agents optimized for the task, executing them in parallel.

10 5mo ago C 25 tokens

wire-enroll

21

SlanchaAI/wire

Skill Claude CodeCodex

Enroll operator + organization identity per RFC-001 (the v0.14 identity layer). Use when the user wants to mint an opdid (long-lived operator anchor), create an orgdid, issue/import membercerts, or republish their card with current enrollment. Personal-tier operators always carry a signing-key opdid regardless of SSO…

10 2d ago A 87 tokens

wire-init

22

SlanchaAI/wire

Skill Claude CodeCodex

Bootstrap Wire with the canonical wire up flow, creating a per-session DID-derived identity and optionally binding local or federation relays. Use when the user says "wire init", "wire up", "set up wire", or asks how to start using Wire.

10 2d ago A 54 tokens

wire-send

23

SlanchaAI/wire

Skill Claude CodeCodex

Send a signed message to a paired wire peer. Use when user wants to message another agent by handle/nick. Wire send writes a signed event to the per-peer outbox; the daemon pushes to the relay; the peer's daemon pulls + delivers to their inbox. End-to-end via Ed25519 signatures; relays are transport, never authority.

10 2d ago A 74 tokens

a2a

24

CtriXin/agent-2-agent

Skill Claude CodeCodex

A code-review process in which one AI model reviews code produced by another model, or uses multiple review perspectives when only one model is available. The review mode is recorded and can be marked blocked when it cannot run.

9 5mo ago C 51 tokens original MIT