mcp skills

14,308 tagged mcp, measured the same way as everything else here.

Browse within: LLM 344agents 268mcp-server 221claude-code-plugin 199antigravity 191agentic-skills 190agent 187ai-workflows 186sdk 168azure 167foundry 167claude-plugin 150agent-marketplace 149skills 117

home-assistant-rest

793

IkarusMK/AIcortex

Skill Claude CodeCodex

Control and query Home Assistant through the connector's callservice tool — REST API patterns, common domains, how to find entities before acting.

not rated 9 3d ago A 32 tokens original Apache-2.0

oen-payment

794

OEN-Tech/oen-payment-skill

Skill Claude Code

An integration guide for Oen Payment, a payment service supporting credit cards, LINE Pay, and convenience-store payments through a REST API and MCP server.

not rated 9 6mo ago A 118 tokens original MIT

heventure-search-mcp

795

HughesCuit/heventure-search-mcp

Skill Claude CodeCodex

Use when: agent needs web search (multi-engine: DuckDuckGo/Bing/Google, free, no API key). Install: pip install heventure-search-mcp.

not rated 9 4mo ago A 41 tokens

gitmem

797

gitmem-dev/gitmem

Skill Claude Code

Institutional memory for AI agents via MCP. Gives your agent persistent memory that survives across sessions — mistakes (scars), successes (wins), decisions, and open threads. Use when you want your agent to stop repeating the same mistakes, carry context between sessions, and learn from experience. Not chat history …

not rated 9 1mo ago A 67 tokens original MIT

using-nilscript

798

nilscript-org/NILScript

Skill Claude CodeCodex

Use when an MCP server exposes nil tools (a NILScript / Network Intent Layer gate to a backend) — teaches the propose→approve→commit→rollback discipline, reversibility tiers, and how to read refusals so an agent drives any NIL backend safely and correctly.

not rated 9 1mo ago A 60 tokens

atrib

799

creatornader/atrib

Skill Claude Code

Use atrib as the verifiable substrate for memory, reasoning, and getting sharper over time, not as instrumentation that observes you from the outside. atrib gives the agent two cognitive verbs: attest (write: sign an observation, mark a past record's importance, or supersede a prior position) and recall (read: look up…

not rated 9 5d ago A SkillSpector: warn 242 tokens original Apache-2.0

codex-harness-mcp

800

chapzin/codex-harness-mcp

Skill Codex

Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits…

not rated 9 4mo ago A 232 tokens original MIT

marianfoo/sap-api-policy-skill

Skill Codex

Evidence-based assessment of whether an SAP API/interface usage scenario aligns with the SAP API Policy (v.4.2026a). Use whenever someone asks whether a way of calling SAP is allowed/compliant — e.g. Published API vs internal/private/"confidential" API status, "Documented Use", whether a third-party tool / iPaaS /…

not rated 9 3mo ago A 228 tokens original MIT

cities2-mod-debugging

802

mayor-modder/Cities2-MCP

Skill Codex

Use when debugging Cities: Skylines II mod build failures, packaging failures, runtime errors, game logs, UI debugger issues, or mod behavior that does not work in game.

not rated 9 20d ago A 41 tokens original MIT

xcatcher

803

lvpiggyqq/xcatcher-mcp-manifest

Skill Claude CodeCodex

Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl…

not rated 9 1mo ago A 86 tokens original MIT

vecfs-memory

804

WazzaMo/vecfs

Skill Claude Code

Gives an agent persistent long-term memory backed by a local sparse-vector file. Use when the agent should recall past context, learn from interactions, or incorporate reinforcement feedback. Relevant for tasks mentioning memory, recall, learning, history, or context retention.

not rated 9 5mo ago A 54 tokens original Apache-2.0

alex-feel/mcp-context-server

Skill Claude CodeCodex

Context retrieval patterns for accessing session context via an MCP-compatible context server. Provides patterns for browse and retrieve, hybrid search, semantic search, and full-text search. Use when you need to retrieve previous context or search for relevant information.

not rated 9 4d ago A 53 tokens

nourish

806

davidmosiah/wellness-nourish

Skill Claude CodeCodex

Local-first nutrition MCP for agents. Intake writes stay gated. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Nourish data or actions through an agent.

not rated 9 14d ago A 41 tokens copy · 83% MIT

claude-code-dsh

807

hootandy321/dsh-Agentlink

Skill Claude CodeCodex

Delegate bounded work from Claude Code to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.

not rated 9 +1 2d ago A 37 tokens original MIT

Sivan757/dsh-agent-plugins-market

Skill Claude CodeCodex

Use before pushing, merging, or claiming a green tree in dsh-agent-plugins-market, to select the smallest checks that cover the outgoing diff instead of reflexively running the full suite.

not rated 9 +1 today A 45 tokens original MIT

cloudflare

809

mnlt/teleport

Skill Claude CodeCodex

Manage Cloudflare DNS zones, Workers, Pages, R2, KV, D1, and analytics via REST API. Use when the user wants to query DNS, deploy a Worker, list R2 buckets, manage KV namespaces, run D1 queries, or check analytics without the Cloudflare MCP installed.

not rated 8 4mo ago B 64 tokens original MIT

bili-content-analysis

810

222wcnm/BiliStalkerMCP

Skill Claude CodeCodex

Deep analysis and tracking of Bilibili creators, videos, dynamics, and articles with BiliStalker MCP tools. Use when users ask for transcript interpretation, timeline reconstruction, theme extraction, behavior analysis, recent shift tracking, or discussion grounded in fetched Bilibili source material.

not rated 8 3d ago A 61 tokens original MIT

eterna-trading-guide

811

EternaHybridExchange/eterna-mcp

Skill Claude CodeCodex

Comprehensive trading guide for the Eterna MCP Gateway. Covers risk management rules, position sizing, deposit flow, and order lifecycle for Bybit perpetual futures trading via executecode + eterna. SDK.

not rated 8 1mo ago A 45 tokens original MIT

elijeangilles/revops-skills

Skill Claude CodeCodex

Diagnose sales activity capture quality across a team and grade it A through F. Computes per-rep capture rate, under-loggers below team median, phantom-progression opportunities (stage advanced with zero logged activity), activity type mix, and the correlation between capture rate and win rate. Use when the user asks…

not rated 8 3mo ago A 93 tokens original MIT

seoul-subway

813

kyopark2014/sam-project

Skill Claude Code

Seoul Subway assistant for real-time arrivals, route planning, and service alerts (Korean/English).

not rated 8 1mo ago A 26 tokens original Apache-2.0

a275618631/codex-antigravity-collaboration

Skill Claude CodeCodex

A set of rules for choosing where project deliverables are stored in Google Drive or GitHub, how they are named, and how they are checked after saving.

not rated 8 3d ago A SkillSpector: pass 68 tokens original MIT

better-skill-builder

815

gmickel/better-skill-builder

Skill Claude CodeCodex

Build SKILL.md files for Claude Code, Codex, Amp, OpenCode. Production examples and patterns for skill structure, scripts, distribution, and making CLI tools AI-native.

not rated 8 8mo ago A 41 tokens original MIT

skill-search

816

sowhan/skill-search

Skill Claude CodeCodex

Find the right skills for a task before acting. Use at the start of any multi-step or unfamiliar request to retrieve relevant skills by meaning, not name. Triggers when the user asks to build, set up, design, deploy, fix, or automate something and the right skill isn't obvious.

not rated 8 2mo ago A 62 tokens original MIT

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: