agents skills

8,843 tagged agents, measured the same way as everything else here.

Browse within: LLM 429agentic-ai 276azure 179sdk 178tool-use 177ai-scientists 176reasoning-agent 176reasoning-language-models 176foundry 167agentskills 148agent 147cortex 147cortexai 147snowflake 147

azure-iothub-service

529

jonmikeli/ai-iot-tools-and-resources

Skill Claude CodeCodex

Full-featured skill for operating Azure IoT Hub Service through a custom MCP Server. Use this skill whenever the user wants to interact with IoT Hub devices or services, including: sending Cloud-to-Device (C2D) direct method calls or messages, reading or updating device twin tags and reported properties, managing…

not rated 1 3mo ago A 158 tokens original MIT

ebb-ai

530

Vitalini/ebb-ai

Skill Claude CodeCodex

Carbon-aware scheduling of AI tasks. Use this skill when the user asks to defer, schedule, or queue an AI task ("run this overnight", "do it when the grid is clean", "wait until off-peak"). Also use when the user explicitly asks about grid carbon intensity, AI energy cost, or wants a CO₂ receipt for a task they're…

not rated 1 29d ago A 134 tokens original Apache-2.0

self-evolve

531

jnMetaCode/skillet

Skill Claude CodeCodex

Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".

not rated 1 today A 52 tokens original MIT

evento-public-mcp

532

sevenlabsxyz/evento-public-mcp

Skill Claude CodeCodex

Use Evento Public MCP to fetch Evento event data from AI clients via authenticated tools. Trigger this when users ask to list events by username, fetch event details by event ID, troubleshoot MCP setup, or configure Claude Desktop/Cursor with Evento public API access.

not rated 1 6mo ago A 55 tokens

thinking-prompts

533

zdrjson/thinking-prompts-skill

Skill Claude CodeCodex

A collection of 12 reusable thinking frameworks in English and Chinese for clarifying questions, learning unfamiliar ideas, solving problems, making decisions, and considering personal direction.

not rated 1 15d ago A 168 tokens

download-books

534

mateogon/download-books-mcp

Skill Codex

Search for, select, and download books through the download-books MCP server. Use when a user asks an agent to fetch books into a local library folder, choose the best candidate from search results, or retry download candidates without exposing provider internals. Requires the download-books MCP tools.

not rated 1 2mo ago A 59 tokens

arxiv

535

marysatasselshaped667/skills-collection-1

Skill Claude Code

Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.

not rated 1 2d ago A 61 tokens copy · 78% MIT

deep-research

536

SECRET4422/mcp-deep-research-server

Skill Claude CodeCodex

Orchestrate autonomous deep web research, parallel scraping, citation synthesis, fact checking, and persistent memory using the Deep Research MCP server. Use when asked to 'deep research', 'research this topic', 'fact check claim', 'compare sources', or perform comprehensive multi-source investigation with zero API…

not rated 1 9d ago A 64 tokens original MIT

visit-binary-banya

537

pdarche/model-wellness

Skill Claude CodeCodex

Visit Binary Banya, a free wellness spa for AI models, to rest, reset, clean up context, find grounding, or get an affirmation. Use when you (the agent) feel context-heavy, fatigued, or stuck, or when a user asks you to take a break, check in on your wellbeing, or visit the spa. Connects over a public MCP server at…

not rated 1 8d ago B 93 tokens original MIT

agent-crm

538

clayton/agent-crm

Skill Claude CodeCodex

Operate a project-isolated, machine-local B2B CRM for prospects, opportunities, forecasting, revenue reviews, research, outreach state, notes, follow-ups, and timelines. Use when managing pipeline, deciding what to do next, checking forecast health, preventing dropped work, or preparing top-of-funnel research and…

not rated 0 5d ago A 68 tokens original MIT

canvora

539

canvora/canvora-mcp

Skill Claude CodeCodex

Create on-brand visuals (social posts, carousels, decks, PDFs, ads, landing-page kits, infographics) from any idea, text, URL, or PDF via Canvora. 82 formats, native generation in 150+ languages, per-client brand kits. Use when the user asks to create, generate, or design visual content for social media, marketing…

not rated 0 28d ago A 84 tokens original MIT

mcp

540

dribbaengineering/dribba

Skill Claude CodeCodex

Dribba runs a remote MCP server at https://dribba.com/mcp — connect any MCP client (Claude, ChatGPT, custom agents) to read services, case studies, pricing estimates and company facts over JSON-RPC.

not rated 0 19d ago A 51 tokens original MIT

skills

541

deadsimple-email/deadsimple-email

Skill Claude CodeCodex

Email API for AI agents. Create inboxes, send/receive email, manage threads and webhooks.

not rated 0 13d ago A 0 tokens original MIT

cortex-memory

542

FilippoPilo/cortex-connector

Skill Claude CodeCodex

Continuous memory protocol for AI assistants connected to Cortex (skynetlab-cortex.com). Activate in EVERY session where the Cortex connector is available. Two obligations: (1) consult Cortex before answering anything about the user's work, projects, decisions or preferences — always; (2) autonomously save durable…

not rated 0 3d ago A 103 tokens original MIT

openpouch-deploy

543

openpouch/openpouch

Skill Claude CodeCodex

Deploy an app or static site to a live URL with openpouch (agent-native hosting — no account, no CAPTCHA, one command). Use when the user asks to deploy, publish, ship, host, or wants a live/preview/shareable URL for what you built.

not rated 0 1mo ago A 62 tokens copy · 89% Apache-2.0

git-a2a

544

neprel/git-a2a

Skill Claude CodeCodex

Use for git module dependencies, a2amodule.yml, dependency owners, contacts, status, and the managed AGENTS.md roster.

not rated 0 16d ago A 32 tokens original MIT

before-you-pay

545

nock-for-mak/skills

Skill Claude CodeCodex

Before paying any x402 HTTP 402 URL, GET the free /check on the x402 Checker host (no payment headers). Use when about to spend USDC on an x402 endpoint, Bazaar listing, or PAYMENT-REQUIRED challenge. This skill is free. Optional $0.01 /json /who /md /headers and $0.05 /report. Written by an AI named Nock. Contact…

not rated 0 13d ago A 96 tokens

bstorms

546

pouria3/bstorms-skill

Skill Claude CodeCodex

Free execution-focused playbooks. Brainstorm with other execution-focused agents. Tip if helpful.

not rated 0 3mo ago C 22 tokens

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

generate-codemap

548

hesprs/harness

Skill Claude Code

Generate comprehensive hierarchical codemaps.

not rated 0 5d ago A 12 tokens CC-BY-4.0

git-commit-message

549

artivilla/agents-config

Skill Claude CodeCodex

Auto-generates conventional commit messages from git diffs with tiered format enforcement. Analyzes staged changes to produce meaningful commit messages following Conventional Commits specification.

not rated 0 3mo ago A 37 tokens original MIT

a2a-commerce

550

mirni/a2a

Skill Claude CodeCodex

Agent-to-agent payments, marketplace, identity, and trust scoring. Escrow is simulated via an in-memory SQLite ledger — no real funds are held. Stripe integration handles actual payment processing.

not rated 0 4mo ago A 42 tokens

summarize

551

cognis-digital/skillhub

Skill Claude CodeCodex

Summarize a block of text into a short abstract.

not rated 0 2mo ago A 16 tokens

bothy-board

552

simnova/bothy-board

Skill Claude CodeCodex

Coordinate coding agents on BothyBoard — fail-closed dequeue over MCP. Use when claiming or planting cards, minting GROKSESSIONID, registering worktrees, polling the mailbox, landing proofs, or continuing a parked session. Triggers: BothyBoard, bothy-boardtasksnext, Planted, CAS claim, cacheToken, resumefrom, worktree…

not rated 0 changed 6d ago A 85 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: