agent-skills skills

41,013 tagged agent-skills, measured the same way as everything else here.

Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 155ai-skills 152anthropic-claude 136claude-ai 136

skill-autoresearch

2065

souljorje/agent-skills

Skill Claude CodeCodex

Validates and improves agentic skills by running isolated executor agents against test briefs, scoring confusion, fixing unclear instructions, and rerunning until stop criteria pass. Use when asked to test or evaluate a skill, find skill failure modes, or harden a skill before reuse. Inspired by Karpathy's…

not rated 4 3mo ago A 67 tokens

emmanuelperu/microcks-skills

Skill Claude CodeCodex needs its repo

Write OpenAPI examples that work with Microcks dispatchers for API mocking. Covers example pairing rules, JSON body dispatching, Groovy script dispatching, and dispatcher configuration via the Microcks API.

not rated 4 6mo ago A 47 tokens original Apache-2.0

computerlovetech/skills

Skill Claude CodeCodex

Applies Computer Love's official brand colors and typography to any sort of artifact that may benefit from having Computer Love's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

not rated 4 2mo ago A 53 tokens

understand

2068

fcescob/understand

Skill Claude CodeCodex

Use when someone wants to genuinely understand something and have it stick — a topic, mechanism, paper, theorem, algorithm, domain, or real code — not just get an answer. Fires on comprehension intent even without the word "understand": "help me understand X", "derive X from first principles", "why does this behavior…

not rated 4 2mo ago A 134 tokens original MIT

wire-lang

2069

eduardozf/wire-lang

Skill Codex

Create, revise, and explain Wire Lang .wire schematic source. Use when writing electronic schematics, converting circuit descriptions into Wire Lang, fixing Wire Lang syntax, or giving good and bad examples of Wire Lang authoring.

not rated 4 changed 10d ago A 47 tokens original MIT

agent-forge

2070

sinclarespeaking143/openclaw-superagent

Skill Claude CodeCodex

A tool for creating, improving, and reviewing skills and agents for OpenClaw. It has separate workflows for creating a skill, creating an agent, or improving an existing one.

not rated 4 2d ago A 111 tokens

WorksOnMyVM/android-device-perception-skill

Skill Codex

Observe an authorized Android test device through read-only ADB commands. Capture the foreground app, focused window, UIAutomator semantic tree, and optional screenshot as a timestamped SituationSnapshot with stable fingerprints. Use this skill to understand the current device screen, investigate an app that appears…

not rated 4 1mo ago A 105 tokens original Apache-2.0

douyin-effect-pipeline

2072

24kobebryant/agent-skills

Skill Codex

A Chinese-language workflow for designing and preparing Douyin AR effects, which are interactive camera effects for ByteDance's Douyin video platform. It takes an idea through research, concept development, effect creation, testing, troubleshooting, and preparation for submission.

not rated 4 changed 10d ago A 145 tokens original MIT

design-system

2073

Cash4478/design-system-skill

Skill Claude CodeCodex

Generate a complete design system (design.md, design-guidelines.md, design-components.md) from any reference materials — images, PDFs, links, or descriptions.

not rated 4 yesterday A 35 tokens copy · 100% MIT

clawvr-smb-ai-strategy

2074

Steffd415/clawvr-agent-skill

Skill Claude CodeCodex

Generates a complete custom AI Operating System for any small business — master prompt + workflow superprompts + 30-day deployment roadmap — across 21+ verticals (dental, contractor, salon, real estate, restaurant, law, vet, photographer, fitness, insurance, CPA, and more). Use when a small business owner asks for…

not rated 4 3mo ago A 109 tokens original MIT

build-right-execution

2075

pax-k/build-right

Skill Codex

Execute one bounded task using baseline evidence, narrow implementation, verification, evidence capture, and tracker updates. Use when the user invokes /build-right-execution, wants to work the next issue, run an evidence-driven implementation loop, verify a task, update task state, or continue execution from a…

not rated 4 1mo ago A 67 tokens original MIT

obo

2076

agenthand/obo

Skill Claude Code

Control the user's real Chrome browser with their logged-in sessions, cookies, and extensions. Triggers include "open a website", "click a button", "fill a form", "take a screenshot", "check my email", "browse as me", or any task requiring the user's authenticated browser.

not rated 4 4mo ago A 61 tokens original MIT

discover-shims

2077

entr0pia/scoop-skills

Skill Claude CodeCodex

Discover available Scoop shims and identify valuable command-line tools. Use when the user asks about available tools, what commands they can use, or wants to explore their Scoop environment.

not rated 4 3mo ago A 39 tokens GPL-3.0

regrouping-git-history

2078

magarcia/skills

Skill Codex

Rebuild a tangled feature branch into a small set of reviewer-friendly logical commits while preserving its final tree byte-for-byte. Use when asked to regroup, squash, tidy, or rewrite a branch with many interleaved feature, fixup, review, merge, or formatting commits. Resolve the actual PR base, plan groups with the…

not rated 4 23d ago A 108 tokens original MIT

ai-agent-design

2079

05-deepak-patidar/claude-skills

Skill Claude CodeCodex

Designing and building AI agents — tool design, agent loops, context management, permissions/guardrails, memory, multi-agent orchestration, MCP, and agent evaluation. Use when building an agent that takes actions (calls tools/APIs, writes files, automates workflows), designing tool schemas, debugging agent…

not rated 4 2mo ago A 103 tokens original MIT

flutter-design-system

2080

musabekisakov-imj/flutter-design-engineer

Skill Codex

Create, extend, or repair semantic Flutter design systems covering tokens, themes, typography, color, spacing, geometry, motion, and component contracts. Use for ThemeData work, design-token extraction, dark mode, component standardization, UI consistency, or migration away from scattered visual constants.

not rated 4 1mo ago A 61 tokens original MIT

generate-system-map

2081

nataliacorrea03/claude-code-skills

Skill Claude CodeCodex

Generates a standalone, interactive HTML map of your Claude Code automation setup: a radial SVG mind-map of your skills grouped into departments, a schedule view of every scheduled task, and a feedback panel that turns flagged issues into copy-ready fix prompts. Best if you run several skills and/or scheduled agents.…

not rated 4 1mo ago A 98 tokens original MIT

HongMing-Huang/pretext-frontend-motion

Skill Codex

Build bold text-driven frontend demos across Accordion, Bubbles, Dynamic Layout, Variable Typographic ASCII, Editorial Engine, Justification Comparison, Rich Text, and Masonry. Use when the request needs strong frontend style, intentional typography, routed text layout, width-tight multiline UI, or kinetic typography…

not rated 4 2d ago A 76 tokens original MIT

skill-reverse-engineer

2083

BruceL017/skill-reverse-engineer

Skill Codex

Use when the user provides a Skill, SKILL.md, prompt workflow, agent instructions, marketplace page, or skill directory and asks to analyze, reverse-engineer, compare, improve, rewrite, trigger-test, port, or package it as a reusable agent skill.

not rated 4 4mo ago A 59 tokens original MIT

grill-with-docs-lite

2084

tmusser/ai-engineering-skills

Skill Claude CodeCodex

Groom a fuzzy request and the smallest relevant source set into a bounded PRE-SPEC ASSEMBLY packet for mini-spec, using optional read-only research fan-out while separating evidence, tensions, decisions, assumptions, and blockers before contract language is written.

not rated 4 changed today A 57 tokens original MIT

git-authoring

2085

n-shadloo/git-authoring

Skill Claude Code

Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery…

not rated 4 changed 11d ago A 220 tokens original MIT

frontend-code-review

2086

DNM03/frontend-code-review

Skill Codex

Review React, Next.js App Router, TypeScript, Tailwind CSS, shadcn/ui, TanStack Query, and frontend UI code. Use when reviewing a PR, branch, diff, page, component, hook, Server Action, route handler, or API client; debugging frontend behavior; assessing production readiness; or checking runtime bugs, client/server…

not rated 4 3mo ago A 102 tokens original MIT

short-drama-pipeline

2087

ouyangevan/codex-short-drama-pipeline-skill

Skill Codex

Use when the user explicitly asks to generate, produce, plan, revise, QC, or deliver an AI short-drama pipeline, project package, episode, assets-to-video workflow, prompt pack, clips, edit, or release pack.

not rated 4 2mo ago A 53 tokens original MIT

personal-board

2088

soyoungzsy/soya

Skill Claude CodeCodex

A personal reference skill for keeping profiles of people, including their key ideas, notable works, quotations, and suitable questions to ask them about.

not rated 4 27d ago A 0 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: