ai-agents skills

52,407 tagged ai-agents, measured the same way as everything else here.

Browse within: LLM 360agentic-ai 302agent 225antigravity 218chatgpt 207agentic-skills 192ai-workflows 185coding-agents 164cli 146ai-assistant 133agents 105claude-code-skills 101agent-infrastructure 100claude-cli 100

loop-builder

2281

yangchao228/loop-builder

Skill Claude CodeCodex

A design workbench for turning a vague task into a controlled, repeatable Agent Loop. An Agent Loop is a task process with defined steps, checks, stopping points, and recovery actions.

not rated 6 2mo ago A 200 tokens original MIT

ElmatadorZ/alternative-coffee-claudeskill

Skill Claude CodeCodex

Alternative Slowbar coffee intelligence — scientific analysis from seed to cup using First Principle + System Thinking. Covers: varieties, terroir, cultivation, disease diagnosis, processing, roasting physics/chemistry, extraction science, brewing, business strategy, storytelling. ALWAYS trigger for coffee-related…

not rated 6 1mo ago A 92 tokens original CC0-1.0

philo-council

2283

umair-tareen/philosopher-council

Skill Claude CodeCodex

Convene an eleven-philosopher LLM council on a question, decision, plan, or claim - virtue-scored opinions from named philosophers (Socrates, Kant, Lao Tzu, ...), a synthesis, and a first-class minority report. Use when the user asks to "convene the council", "ask the philosophers", wants a decision deliberated from…

not rated 6 +1 1mo ago A 108 tokens original MIT

unity-ui

2284

batihandev/unity-mcp-skills

Skill Claude CodeCodex needs its repo

Use when users want to create Canvas, Button, Text, Image, or other UI elements.

not rated 6 1mo ago A 22 tokens original MIT

herd

2285

Kampe/Herdforge

Skill Claude CodeCodex

Operate the Herdforge self-forging software factory with Kaneo, Herdr, isolated worktrees, verification, review, and cleanup.

not rated 6 +1 2d ago A 30 tokens original MIT

ctxpm

2286

gBearBest/Bear.CTXPM

Skill Claude CodeCodex

Skill "ctxpm" from gBearBest/Bear.CTXPM, covering ctxpm, resource discovery and precedence, management boundary, canonical resource root and compatibility exposure.

not rated 6 changed 3d ago A 0 tokens

scip-plan

2287

PlunderStruck/scip-query

Skill Codex

Plan changes by mapping the existing system end to end, finding comparable features and conventions, and documenting how to reuse or extend current owners instead of creating parallel implementations.

not rated 6 changed 4d ago A 36 tokens original Apache-2.0

dejavu

2288

WhiteBite/opencode-dejavu

Skill Claude CodeCodex

Protocol for working with the dejavu error-gate plugin. Use when a tool call is answered with a "[dejavu] REMINDER" or "[dejavu] BLOCKED" message, when the same tool call fails repeatedly, or when you discover the root cause of a gated failure. Covers how to react to reminders, what BLOCKED means, the dejavu:proceed…

not rated 6 changed today A 99 tokens original MIT

raven-language-skill

2289

martian56/raven-language-skill

Skill Claude CodeCodex

Reference and patterns for writing Raven programming language source (.rv files). Use this whenever the user is writing, editing, debugging, or reviewing Raven code, working in an rvpm project (rv.toml), discussing Raven syntax, importing from Raven's stdlib (std/io, std/string, std/fmt, std/collections, std/math…

not rated 6 2mo ago A 262 tokens original MIT

docx2md

2290

gonzalopezgil/docx2md-cli

Skill Claude CodeCodex

Convert Word (.docx) files to high-fidelity Markdown. Preserves tables (including vMerge), footnotes, field-code references, bibliography SDT blocks, numbered/bullet lists, images, and YAML frontmatter. Use when asked to convert a Word document to Markdown, extract text from .docx, parse a Word file for further…

not rated 6 5mo ago A 87 tokens original MIT

phoenix

2291

All-The-Vibes/ATV-Phoenix

Skill Claude CodeCodex

The meta-skill that routes a task to the right Phoenix lifecycle skill and enforces the non-negotiable operating laws. Use at the start of any session or task to decide which Phoenix skill applies. Phoenix is a self-healing, token-efficient engineering harness — every stage verifies its work with an objective check…

not rated 6 +1 changed 11d ago A 92 tokens original MIT

pdf-documents

2292

alex-alecu/garden-desk

Skill Claude CodeCodex

PDF reading, page work, creation. Load for PDF input or deliverable.

not rated 6 2d ago A 20 tokens original Apache-2.0

design-md-creator

2293

iFurySt/DESIGN.md

Skill Codex

Create or refine a DESIGN.md from a public website URL, then use that design system to build and open a standalone HTML page based on either a reference URL or the user's requested page and content. Visually validate the HTML and feed reusable corrections back into DESIGN.md. Use when the user wants a DESIGN.md, an…

not rated 6 2mo ago A 99 tokens original MIT

clawhub

2295

FarkhodovIslom/Tarantul

Skill Claude CodeCodex

Search and install agent skills from ClawHub, the public skill registry.

not rated 6 12d ago A 19 tokens copy · 83% MIT

ui-motion-workflow

2296

powehi-eu/ui-motion-workflow

Skill Codex

Orchestrate UI direction, composition, motion provider selection, implementation, and browser-proven quality for polished frontend work. Use when Codex needs to improve a visual surface with animation or interactive polish; when a request mixes design intent, component choice, browser validation, accessibility, or…

not rated 6 1mo ago A 111 tokens original MIT

tmux-remote-linux

2297

lenovobenben/tmux-remote-linux

Skill Claude CodeCodex

Use this whenever the task requires operating, inspecting, testing, or diagnosing a remote Linux environment through a user-prepared tmux pane, especially when you would otherwise run ssh. Replace direct ssh attempts with this skill unless the user explicitly asks for direct SSH. Covers bastion hosts, Kubernetes…

not rated 6 2mo ago B 76 tokens original MIT

md-analysis

2298

SFETNI/Deep-Matter-Chem-Skills

Skill Claude CodeCodex

This skill covers quantitative post-processing of atomistic molecular dynamics trajectories: loading and preprocessing trajectories from LAMMPS, GROMACS, or ASE; computing structural observables (RDF, coordination numbers, angular distributions, bond orientational order, common-neighbor analysis, centrosymmetry…

not rated 6 1mo ago A 2 tokens original MIT

cost-aware-development

2299

BottleYo/model-economy

Skill Claude CodeCodex

Guidance for choosing the smallest suitable development process based on a task's risk and complexity.

not rated 6 +1 1mo ago A 40 tokens original MIT

lucius

2300

berkantay/lucius

Skill Claude CodeCodex

Drive the lucius pairing canvas — build rich, self-contained HTML/CSS/JS/SVG one-pagers on ANY topic (architecture diagrams, product one-pagers, sales/CS collateral, design docs, explainers, simulations) as versioned iterations while pairing with a user. Use when the user says "lucius", "put it on the canvas", "new…

not rated 6 1mo ago A 92 tokens

roblox-best-practices

2301

andrian-syh/roblox-best-practices-skill

Skill Claude Code

Framework-agnostic Roblox/Luau coding standards. Use when writing, reviewing, or refactoring any Luau code (Script, LocalScript, ModuleScript) in a Roblox project, or when the user asks to keep best practices in mind as standing guidance — enforces the VARIABLES/FUNCTIONS/INITIALIZATION layout, naming, performance…

not rated 6 +1 18d ago A 184 tokens original MIT

auto-re

2302

timwhitez/AutoRE-CLI

Skill Codex

A command-line tool for static reverse engineering, which means examining compiled files without running them, including ELF, PE, Mach-O, object files, and identified shellcode.

not rated 6 +1 changed 2d ago A 82 tokens original MIT

delegating-work

2303

rundesk-ai/rundesk-cli

Skill Claude CodeCodex

Use when named delegation is a genuine option for current work, when preparing or reviewing a handoff, or when continuing delegated work to a verified outcome. It supplies context recovery, deliberate skill selection, necessary-only delegation, evidence requirements, and continuation discipline. Do not use for…

not rated 6 3d ago A 76 tokens original MIT

Content Factory

2304

hassancs91/content-factory-starter

Skill Claude CodeCodex

End-to-end content pipeline — idea in, published evidence-backed page out. Orchestrates search recon, real lab experiments (cloud VMs / local Docker), screenshot and asset production, drafting in a defined voice, verification loops, ship, and a write-back to your knowledge base. Triggers on "/factory ...", "new piece…

not rated 6 28d ago A 112 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: