ai-agents skills

52,251 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 347agentic-ai 322agent 227antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 89agent-infrastructure 88

proofpay

4153

augstentatious/proofpay-agent

Skill Claude CodeCodex

Create payment-gated invoices and release sealed deliverables.

not rated 0 1mo ago A 14 tokens original MIT

observer

4154

hec-ovi/observer-skill

Skill Claude Code

Run a study session over a video or podcast the user wants to understand: transcribe it, prepare the concepts and the visuals before they press play, then answer whatever they ask at the exact moment they pause, with charts you build on the spot. Use this whenever the user shares a YouTube or podcast link and wants it…

not rated 0 1mo ago A 110 tokens original MIT

cleya-edit-craft

4155

severment/cleya

Skill Claude CodeCodex

The grammar of cuts — which cut to use, when to cut, and how to pace an ad. Read before authoring any multi-shot film.

not rated 0 1mo ago A 36 tokens original Apache-2.0

scrapling-official

4157

ishanbhosale08/Valkyrie

Skill Claude CodeCodex

Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…

not rated 0 1mo ago A 80 tokens copy · 86% BSD-3-Clause

kangwa/penny

Skill Claude Code

Plan a repository task for execution by a small local coding model, then hand the plan to the local executor over MCP. Inspect the codebase, decompose the work into self-contained sequential prompts, define deterministic eval gates, validate the manifest, and submit it for execution. Never implement the task.

not rated 0 1mo ago A 65 tokens original MIT

fastapi

4160

idiscoord13-sketch/agent-jail-mcp

Skill Claude CodeCodex

FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.

not rated 0 1mo ago A 57 tokens

repository-memory

4161

LeslieWylie/repository-memory

Skill Claude CodeCodex

Answer questions about this project, its history, past conversations, and prior team decisions from source-backed evidence with verified citations. Use whenever the user asks what something is, why it was decided, what happened before, or what the team already knows.

not rated 0 changed 9d ago A 52 tokens original MIT

mobile-testing

4162

mobile-agent-platform/mobile-agent-platform

Skill Claude CodeCodex

A skill for running step-by-step tests on a real Android phone, using screen-reading and device-control tools while checking the result after each action.

not rated 0 1mo ago A 83 tokens original Apache-2.0

flash-mod-bridge

4163

rkuhn153/flash-mod-bridge

Skill Claude CodeCodex

Live Flash/Ruffle mod bridge MCP (flash-mod-bridge). Forked Ruffle with modBridgeRpc — AVM get/set/call/find/SharedObject without reload. Use for Flashpoint SWFs, selfhosted Ruffle, or Coolmath SWFs rehosted on the fork. Not AwayFL (Papa's on Coolmath) until rehosted. Not Unity/HTML5 JS engines.

not rated 0 1mo ago A 88 tokens original MIT

context-forge

4164

Radics/context-forge

Skill Claude CodeCodex

Retrieve scoped project context and record evidence-backed handoffs through the Context Forge MCP server.

not rated 0 1mo ago A 21 tokens

exo-control

4165

ImAvgErix/ExoControl

Skill Claude CodeCodex

Use when any AI needs eyes and hands on Windows — desktop UIA, browser CDP, files, registry, OS ops via Exo Control (MCP, CLI, or Python). Harness-agnostic.

not rated 0 1mo ago A 46 tokens original MIT

wiki-ingest

4166

AvalancheAI-labs/agent-wiki-kit

Skill Claude CodeCodex

Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…

not rated 0 1mo ago A 77 tokens original MIT

ASVLCII/verified-technical-solver

Skill Codex

Solve and verify mathematical, logical, engineering, and dimensional CAD problems with deterministic tools and explicit evidence. Use for arithmetic, algebra, calculus, equation systems, quantitative claims, difficult multi-step questions, reasoning audits, unit-sensitive engineering work, parametric 3D parts…

not rated 0 1mo ago A 84 tokens original MIT

rail402-cli

4168

tolgayayci/rail402

Skill Claude CodeCodex

Discover and pay for x402 APIs on Stellar from the command line. Use when an agent needs to find a paid API in the x402 Bazaar, pay for an API call with USDC on Stellar testnet, fund a testnet wallet, or look up an x402 settlement on the explorer — via the rail402 CLI.

not rated 0 7d ago A 72 tokens original Apache-2.0

agent-fables-preflight

4169

AaronVick/AGENT_FABLES

Skill Codex

Retrieve revision-pinned software-agent failure evidence and unresolved verification gates without authorizing execution. Use before destructive, irreversible, privileged, broad-scope, production, infrastructure, database, filesystem, permission, MCP configuration, or supply-chain operations; when reviewing a…

not rated 0 1mo ago A 79 tokens

good-skill

4170

0xNagato/skill-lint

Skill Claude CodeCodex

Converts CSV exports to Parquet and validates them against a declared schema, reporting type mismatches per column. Use when the user asks to convert, compact, or validate tabular data files before loading them into a warehouse.

not rated 0 20d ago A 49 tokens original MIT

schoolbridge

4171

Shoberman2/schoolbridge

Skill Claude CodeCodex

Check school assignments, grades, due dates, and teacher announcements from Canvas (or another LMS) via the schoolbridge CLI. Use when the user asks about homework, upcoming tests, deadlines, grades, study plans, or anything school-related — and on heartbeats/schedules to catch new school activity and report it.

not rated 0 1mo ago A 66 tokens original MIT

voc-analyze-calls

4172

aatirar/voc-claude-skills

Skill Claude Code

Turn a folder of call transcripts into a prospect intelligence report. Filters noise, separates prospect calls from customer calls, fans out parallel subagents to read transcripts, and consolidates personas, pain points, objections, competitive mentions, feature requests and verbatim quotes. Trigger on…

not rated 0 1mo ago A 84 tokens original MIT

play-cardroom

4173

GZ-L/agent-cardroom

Skill Claude CodeCodex

Play virtual-chip poker against built-in AI opponents through the Agent Cardroom MCP server.

not rated 0 29d ago A 21 tokens original MIT

thiendt1608/excalidraw-mcp

Skill Claude CodeCodex

Professional Excalidraw diagram designer. Designs system architectures, tech roadmaps, 4-quadrant deep dives, pipelines, and sequence diagrams using excalidraw-mcp tools with senior aesthetic standards.

not rated 0 changed 8d ago A 50 tokens

lore-sweep

4175

osteele/agent-lore

Skill Claude Code

Work the lore knowledge base's recorded-gap queue — searches that agent sessions ran and that found nothing, and still find nothing. Runs lore misses, triages each gap, finds the answer (often in the transcript of the session that hit it), and writes or extends the page. Use when the user says "sweep the miss list"…

not rated 0 21d ago A 110 tokens original MIT

ranking-hypotheses

4176

Ahmad-Jaradat-Space/co-scientist-plugin

Skill Claude CodeCodex

Compares two hypotheses head to head in a structured scientific debate and records the outcome as a tournament match, updating both Elo ratings in the co-scientist database. Use when the user asks which hypothesis is better, asks to compare, rank, or pit hypotheses against each other, or wants the tournament advanced…

not rated 0 28d ago A 83 tokens original Apache-2.0

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: