multi-agent-systems skills

534 tagged multi-agent-systems, measured the same way as everything else here.

Browse within: Autonomous Agents 205agentic-workflows 197gemini-cli 184ciel 149harmonized 148agent-orchestration 90Multi-Agent 82llm-orchestration 80crawler 76digital-employee 76makemoney 76mas 76agentic-workflow 74domain:systems 71

oa-dispatch

25

1broseidon/oneagent

Skill Claude CodeCodex needs its repo

Dispatch coding tasks to other AI agents via oneagent (oa). Use when you want to delegate file edits, code generation, reviews, or other scoped tasks to a different model or backend — for example, sending a targeted edit to Codex while continuing your own work.

not rated 5 5mo ago A 58 tokens original MIT

rebar-feedback

26

willackerly/rebar

Skill Claude Code

Use when you hit a gap, anti-pattern, bug, or missing guidance in rebar's templates, practices, or scripts during real work — or when the user says "file feedback" / "write this up for rebar." Files a durable feedback item instead of editing templates directly.

not rated 5 24d ago A 62 tokens original Apache-2.0

comm-agent-skill

27

parijatmukherjee/openclaw-hawkins

Skill Claude CodeCodex

Communication specialist for the OpenClaw multi-agent system. Use this skill when the task involves: drafting or sending emails, posting to Discord or other chat platforms, scheduling calendar events, sending notifications, or any outbound communication on behalf of the user. Always drafts before sending and requires…

not rated 5 3mo ago A 74 tokens original MIT

cirwel/unitares

Skill Claude CodeCodex

Use when an agent needs to understand UNITARES governance concepts — EISV state vectors, basins, policy actions, coherence, calibration. Reference material for interpreting governance metrics as proprioceptive state estimation, not outcome judgment.

not rated 4 yesterday A 53 tokens original Apache-2.0

Beichen-H/Loopower

Skill Codex

Use when a natural-language task must be converted into a role-neutral, statically validated one-shot plan, workflow, or agent-loop specification before any user-task execution begins.

not rated 2 1mo ago A 40 tokens original MIT

graphify

31

aleksbuss/orchestra

Skill Claude CodeCodex

Navigate a codebase through a local tree-sitter knowledge graph instead of grepping blindly. Use when asked how a medium-or-large codebase works, where a symbol is defined, what calls what, how two modules connect, or when planning a refactor that spans files. Requires the external graphify Python CLI; degrades to…

not rated 2 2d ago A 77 tokens original MIT

hivemind

32

AmirK-S/HiveMind

Skill Claude Code

Search and contribute to the HiveMind shared knowledge commons.

not rated 1 6mo ago A 15 tokens

jxoesneon/Ciel

Skill Claude CodeCodex

CIEL's framework for three-layer design token systems (primitive→semantic→component) with CSS variables and naming conventions. Advisory only.

not rated 1 6d ago A 32 tokens original Apache-2.0

piqrypt-mcp-audit

34

PiQrypt/piqrypt-mcp-server

Skill Claude CodeCodex

Outils d'aide à l'audit crypto des agents AI (Ed25519, AISS). Pour traçabilité/décision vers conformité AI Act, NIST, RGPD Art.22. npm @piqrypt/mcp-server.

not rated 0 4mo ago A 58 tokens original MIT

seenrelay

35

ovladon/seenrelay

Skill Claude CodeCodex

Integrate SeenRelay conservatively into repeated read-only validation and MCP/tool paths. Detect the project framework, prefer its supported Ambient adapter, start local-shadow-only, and preserve stronger local/source-native mechanisms.

not rated 0 yesterday A 43 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: