ai skills

25,839 tagged ai, measured the same way as everything else here.

Browse within: LLM 577agent 531cli 399chatgpt 292agents 205ml 152LangChain 134bun 127agentic 121cybersecurity 120generative-ai 120chatbot 119hacking 114mcp-server 84

changelog-bump-ver

1729

mir-am/skills-agents-ai-coding

Skill Claude CodeCodex

Promote CHANGELOG.md unreleased entries into the next release version and update Maven POMs to the next snapshot version.

not rated 2 4mo ago A 30 tokens original MIT

brand-operation

1730

sutchan/Agent-Skills-Hub

Skill Claude CodeCodex

Brand operation is the strategic management of an official brand account on Xiaohongshu to build brand awareness, engage with target audience, drive conversions, and create a cohesive brand presence that supports business objectives through consistent, value-driven content and community management.

not rated 2 today A 0 tokens original MIT

peak-scripts

1732

Peak-Studios/peak-agent-toolkit

Skill Codex

Install, configure, integrate, troubleshoot, or improve public Peak Studios FiveM resources using versioned documentation and source provenance. Use when working with peak-bridge, peak-chess, peak-clothingitems, peak-sprays, or peak-trucking; when selecting a compatible Peak script; or when adapting one to ESX…

not rated 2 today A 89 tokens original MIT

roic-api-v3

1733

roicai/agents-plugin

Skill Claude CodeCodex

Guides correct, budget-efficient use of the roic.ai v3 REST API (https://api.roic.ai/v3.0.0) — bearer/apikey auth, the strict EXCHANGE:SYMBOL identifier model, cursor pagination, reference catalogs, ticker search by ISIN/CUSIP/CIK/FIGI, stock and forex prices, bulk whole-universe latest-price feeds, the 11…

not rated 2 1mo ago A 224 tokens original MIT

add-a-source

1734

mayai-it/bandiradar

Skill Claude CodeCodex

Add a new funding-opportunity source adapter to BandiRadar (e.g. a regional bandi portal, a national incentives feed, an OCDS endpoint). Use when the user wants to integrate a new data source, write a Source adapter, map a raw payload into the canonical Opportunity model, or contribute a regional/sector source.…

not rated 2 2mo ago A 87 tokens original MIT

pine-develop

1735

ulianbass/tradingview-mcp

Skill Claude CodeCodex

Full Pine Script development loop — write code, compile, fix errors, iterate. Use when building a new indicator or strategy in TradingView.

not rated 2 4mo ago A 32 tokens fork

unityxclaude

1736

matthewagi/unityxclaude

Skill Claude CodeCodex

You have full control over Unity Editor via 24 MCP tools. This skill teaches you how to use them effectively.

not rated 2 5mo ago A 0 tokens copy · 100% MIT

session-continuity

1737

raya-ac/engram

Skill Claude CodeCodex

Use when an agent should pick work up from Engram quickly and leave behind a clean structured handoff for the next session. Best for multi-step coding, investigations, releases, debugging, and any task where recent decisions and open loops matter.

not rated 2 today A 53 tokens original MIT

doctor

1738

amanasmuei/amem

Skill Claude CodeCodex

Run health diagnostics on the amem memory database. Use when the user wants to check memory health, embedding coverage, stale memories, or diagnose issues.

not rated 2 4mo ago A 32 tokens original MIT

Knuckles-Team/tunnel-manager

Skill Claude CodeCodex

Manage the shared SSH host inventory via the tunnel-manager MCP server — list, add, and remove host aliases (hostname, user, port, identityfile) and push the inventory into the knowledge graph as typed :Host / :HostGroup / :SshKey nodes. Use when the agent must register a new SSH target, look up how a host is reached…

not rated 2 2d ago A 129 tokens original MIT

visual-design

1740

95gabor/agentic-workflow

Skill Claude CodeCodex

Visual design system, brand tokens, and SVG illustration. Defines colors, illustration style, and produces optimized SVG assets for marketing surfaces. Use with visual-designer subagent when illustrations, brand refresh, or OG visuals are needed.

not rated 2 1mo ago A 48 tokens

debug-driven

1741

rgnicoara/debug-driven

Skill Claude CodeCodex

Activates a structured, hypothesis-driven debugging loop. Use this skill whenever the user reports a bug, unexpected behavior, or runtime error and wants help diagnosing the root cause - especially for bugs that are hard to reproduce or where the fix isn't obvious. Trigger on phrases like: "debug this", "figure out…

not rated 2 5mo ago B 123 tokens original MIT

agentlint

1742

agentlint/agentlint

Skill Claude CodeCodex

Audit a repository's AI-agent readiness with the agentlint CLI and fix the findings. Use when the user asks to score, audit, or improve how well a repo works with AI coding agents (AGENTS.md, build/test docs, conventions, guardrails), or mentions agentlint.

not rated 2 today A 60 tokens original MIT

learn-as-you-build

1743

Fred-In-tech/learn-as-you-build

Skill Claude CodeCodex

Turns every coding or creative session into a teaching session. Explains the WHY behind decisions, surfaces the tradeoff that was made, names the pattern being applied, and flags what transfers to other problems — without slowing the work down. Use continuously in any build, debug, design, or content session.

not rated 2 29d ago A 65 tokens original MIT

t-rhex/obsidian-mcp-server

Skill Claude CodeCodex

Use when managing tasks, projects, multi-agent workflows, or knowledge persistence in an Obsidian vault via MCP. This skill should be used when creating tasks, claiming work, updating progress, completing deliverables, decomposing projects into sub-tasks, monitoring project status, logging decisions or discoveries, or…

not rated 2 6mo ago A 115 tokens original MIT

accreta-setup

1745

francescofioredev/accreta

Skill Claude CodeCodex needs its repo

Set up an accreta knowledge base over a corpus — pick a preset, write the config and a source declaration, generate the constitution, wire up MCP, and verify the first ingest. Use when someone wants an agent-maintained knowledge base with provenance and drift detection over a codebase, a document collection, or a…

not rated 2 +1 changed 6d ago A 100 tokens original MIT

sqlmind

1746

VeloceAI/sqlmind

Skill Claude CodeCodex

SQLMind solves five root causes of LLM SQL failure.

not rated 2 2mo ago A 0 tokens original MIT

ppt-master-branding

1747

chadixearth/graphyloop

Skill Claude CodeCodex

Use when generating Lifewood-branded PDF documentation, manuals, reports, one-pagers, or presentation-style deliverables — enforces PDF-only output (no PPTX/PPT), 16:9 landscape canvas, one-topic-per-page pagination with content compression before continuation pages, hierarchical X.0/X.1 numbering, bottom-anchored…

not rated 2 29d ago A 97 tokens original MIT

premium-web-design

1748

mrDesign-ww/vault-os

Skill Claude CodeCodex

Create premium, Awwwards-quality website designs as React (.jsx) components that look like they were built by a top-tier agency charging $50k+ per project. Use this skill whenever the user asks for a website, landing page, portfolio, or web component that should look expensive, premium, luxury, editorial, high-end, or…

not rated 2 7d ago A 196 tokens original MIT

project-memory

1749

jukrap/ai-agent-playbook

Skill Claude CodeCodex

Use when maintaining project state, decisions, evidence, or a handoff that must survive a new session.

not rated 2 changed 6d ago A 24 tokens original MIT

Cratis/AI

Skill Claude CodeCodex

Talk to a Chronicle server from a standalone .NET application with the Cratis.Chronicle client - connection strings, ChronicleClient construction outside any host, AddCratisChronicle for a worker or ASP.NET host, [EventType] records, IEventSequence.Append, reactors and reducers found by assembly scanning, the…

not rated 2 today A 123 tokens original MIT

ugrc-python-packaging

1751

agrc/agent-skills

Skill Claude CodeCodex

Python packaging migration guidance. Use when reviewing or migrating projects from setup.py to pyproject.toml, including Hatchling, dependencies, versioning, and console scripts.

not rated 2 4d ago A 39 tokens original MIT

waygate-mcp

1752

jeremylongshore/waygate-mcp

Skill Claude Code

Operate the Waygate MCP server's implemented filesystem, search, command, and HTTP tools with explicit safety boundaries. Use when inspecting files under a configured Waygate root, making a deliberate file change, running a bounded local command, or calling an explicitly authorized HTTP endpoint. Trigger with "use…

not rated 2 6d ago A 87 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: