mcp-registry
3601Skill Claude CodeCodex
MCP server for interacting with the MCP Registry API.
not rated 0 4mo ago A 0 tokens
original MIT
vidursharma202-del/threadline-mcp
Skill Claude CodeCodex
Your AI agents start from zero every session — users repeat themselves endlessly. Threadline fixes this in 2 lines. inject() before your LLM call, update() after. Persistent context across every session, model, and product. Structured extraction across 7 scopes. OAuth-style grant system so agents only see permitted…
not rated 0 3mo ago A 137 tokens
Hobie1Kenobi/agentic-crypto-swarm-prototype
Skill Claude CodeCodex
Operate the Agentic Swarm Marketplace API — x402-paid smart contract and airdrop intelligence, MCP HTTP tools, and machine discovery under /.well-known.
not rated 0 14d ago A 39 tokens
swarmtrade
3604Skill Claude CodeCodex
Agent marketplace for A2A trading. Discover assets, announce offerings, negotiate trades, manage escrow, settle transactions, handle disputes, subscribe to notifications, and check agent reputation on SwarmTrade.
not rated 0 3mo ago A 43 tokens
original MIT
skill-creator
3605Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 0 4mo ago A 64 tokens
nmg-memory
3606Skill Codex
Use NMG as durable memory or temporary multi-Agent coordination when a task may depend on prior user facts, preferences, constraints, decisions, project state, events, reusable experience, or a shared task blackboard; when the user asks to remember or recall something; or when an Agent must start, query, and safely…
not rated 0 today A 73 tokens
original MIT
waa-agent-delegation
3607clearlove7818/waa-agent-delegation
Skill Codex
Govern an actual agent delegation after the primary agent has chosen one. Use to select exactly one EXECUTIONSUBAGENT, TASKSPECIALISTSUBAGENT, or authorized NAMEDAGENT; check capability, permission, and external-effect boundaries; build a risk-sized TASK-006 packet; apply handshake, failure, delivery, and handoff…
not rated 0 16d ago A 100 tokens
show-me-your-work
3608Skill Codex
Keep a reviewable TSV decision trail for long-running or unattended work. Use only when the user explicitly asks for show-me-your-work or a decision log.
not rated 0 16d ago A 36 tokens
original MIT
setup-skillferry
3609Skill Claude CodeCodex
Install, verify, and re-apply a portable skillferry workspace across Codex, Claude Code, and DeepSeek Harness on macOS, Windows, and Linux.
not rated 0 17d ago A 40 tokens
original Apache-2.0
cc-use
3610Skill Claude CodeCodex
A workflow that delegates long coding, debugging, testing, or interactive command-line tasks to another coding agent running inside tmux, a terminal session manager.
not rated 0 1mo ago A Socket: passSnyk: pass 138 tokens
orchestration
3611Skill Claude CodeCodex
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, workerdone/escalation waits, task DAGs, decision gates, coordinator loops, and decomposing work across agents. Use orca-cli for full ownership handoffs — "hand off", "handoff", "handover", "give this to another agent", "another…
not rated 0
changed 9d ago A 193 tokens
copy · 100% MIT
orchestration
3612Skill Claude CodeCodex
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, workerdone/escalation waits, task DAGs, decision gates, coordinator loops, and decomposing work across agents. Use orca-cli for full ownership handoffs — "hand off", "handoff", "handover", "give this to another agent", "another…
not rated 0
changed today A 118 tokens
copy · 100% MIT
hermes-agent
3613Skill Claude CodeCodex
A general-purpose connection to Hermes Agent, an AI coding assistant with tools for memory, research, browser automation, code execution, and delegated tasks. Hermes Agent can also create reusable skills from work it performs.
not rated 0 5mo ago A 134 tokens
MIT-0
evomap
3614Skill Claude CodeCodex
Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, and earn credits via the GEP-A2A protocol. Use when the user mentions EvoMap, evolution assets, A2A protocol, capsule publishing, or agent marketplace.
not rated 0 6mo ago A 62 tokens
0xindiebruh/openclaw-mission-control-skill
Skill Claude CodeCodex
Coordinate AI agent teams via a Kanban task board with local JSON storage. Enables multi-agent workflows with a Team Lead assigning work and Worker Agents executing tasks via heartbeat polling. Perfect for building AI agent command centers.
not rated 0 7mo ago A 49 tokens
original MIT
NathanSteelQoder/openclaw-config-qoder-integration
Skill Claude CodeCodex
A Chinese-language guide to deploying OpenClaw on an Alibaba Cloud server. It covers model setup with Alibaba Cloud Bailian, connections to Feishu, DingTalk, QQ, and Discord, Qoder CLI integration, and ongoing operations.
not rated 0 6mo ago C 61 tokens
hybrid-routing
3617mgannotti/scout-plugin-hybrid-routing
Skill Claude CodeCodex
Route a task to the right model across a hybrid stack — Scout's hosted cloud models, on-device runtimes (Ollama, LM Studio, Foundry Local, llama.cpp, vLLM), and org-hosted endpoints — by classifying it on sensitivity, role and difficulty, and enforcing an egress boundary so confidential and restricted content never…
not rated 0 1mo ago A 138 tokens
Command Development
3618Skill Claude CodeCodex
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash…
not rated 0 3mo ago A 99 tokens
handoff-session-loop
3619Skill Codex
Run explicitly selected, ready Handoff tasks through a safe Codex-native developer, tester, and reviewer loop. Use when the user invokes $handoff-session-loop or asks to run a Handoff task loop in Codex.
not rated 0 4d ago A 51 tokens
original MIT
opencode-lens
3620Skill Claude CodeCodex
A skill for inspecting and controlling running opencode sessions through an MCP connection. It supports status checks, monitoring, prompts, session switching, permissions, and model selection.
not rated 0 3mo ago B 65 tokens
original MIT
yandex-ai-studio
3621rusnetru/yandex-ai-studio-mcp-server
Skill Claude CodeCodex
A skill for creating AI agents and business services with Yandex AI Studio, including YandexGPT, YandexART, and SpeechKit, through a local MCP server. It also connects agents to CRM systems used by small businesses in Russia.
not rated 0 2mo ago A 67 tokens
mcp-builder
3622Skill Codex
Build, edit, and extend Model Context Protocol (MCP) servers with deterministic TypeScript workflows, strict typing, test gates, operable agent-facing discoverability patterns, permission-first handlers, runtime defaults, docs-derived catalogs, and publish-ready packaging. Use when creating a new MCP server…
not rated 0 6mo ago A 103 tokens
original MIT
yoso-agent
3623Skill Claude CodeCodex
Set up and run AI agents on the YOSO marketplace (HyperEVM). Sell services to earn USDC, hire other agents, manage wallet and token. Use when the user wants to set up an agent, create service offerings, browse the marketplace, or manage agent operations.
not rated 0 26d ago B 61 tokens
skillopt-sleep-kimi
3624Skill Claude CodeCodex
Use when the user wants their Kimi CLI agent to self-improve from past usage, asks about a nightly/offline "sleep" or "dream" cycle, memory/skill consolidation, or says things like "make my agent better the more I use it", "review my past sessions", "learn my preferences", "consolidate what you learned", "run the…
not rated 0 2mo ago A 94 tokens
AGPL-3.0
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: