agent-skills skills

41,017 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

fable-skill

2785

almutaz9000/fable-skill

Skill Claude CodeCodex

High-stakes work: debug, migrate, refactor, verify.

not rated 2 changed 2d ago A 19 tokens original MIT

spec-driven-planning

2786

johnnykor82/spec-driven-planning

Skill Codex

Use when planning or continuing non-trivial project work: project plans, roadmaps, decomposition, large changes, feature builds, migrations, rewrites, multi-step work, 10+ tool calls, multiple phases or sessions, scope changes, or verifiable spec compliance. Also use as reference when .planning/ or an existing…

not rated 2 2mo ago A 96 tokens original MIT

django-schema-design

2787

llodev/skills

Skill Claude CodeCodex

Design robust Django database schemas with model best practices, migration patterns, and primary key strategy (incremental, UUID, UUIDv7). Use when designing Django models, choosing PK types, writing migrations, or reviewing app schema. Covers Django ORM, PostgreSQL, indexes, constraints, and security considerations…

not rated 2 yesterday A 66 tokens original MIT

placeholder

2788

MauricioPerera/llms-txt-skills

Skill Claude CodeCodex

Generate SVG placeholder images for UI mockups via the placeholder-img HTTP API. Use when the user asks for placeholder images, mockup assets, or dummy images with specific dimensions and colors.

not rated 2 18d ago A 39 tokens original MIT

pex-ai-song-detector

2789

Pexeso/ai-agents

Skill Claude CodeCodex

Detect whether an audio file contains AI-generated music using the Pex AI Song Detector API. Use this skill whenever the user wants to check if a song or audio file was created by AI, identify which AI music platform generated a track (Suno, Udio, Mureka, Sonauto, ElevenLabs, Boomy, etc.), or integrate AI music…

not rated 2 1mo ago A 154 tokens original Apache-2.0

agentype

2790

cyzlmh/agentype

Skill Claude CodeCodex

Run the Agentype workflow for local AI-agent usage analysis: collect and cache deterministic JSON, infer a persona/archetype from aggregate usage signals, then render a terminal summary or PNG poster. Supports Claude Code, Codex, OpenCode, pi-agent, Gemini CLI, OpenClaw, Nanobot, and configured Nanobot-compatible…

not rated 2 4mo ago A 98 tokens original MIT

deploy-service

2791

alanqoudif/SkillRewind

Skill Claude CodeCodex

Deploys the service quickly over HTTP with a certificate-check fallback.

not rated 2 1mo ago A 16 tokens original Apache-2.0

arkgum/arkgum-agent-skills

Skill Codex

Autonomously orchestrate a source-grounded topic-to-page workflow through Google NotebookLM: create or reuse a notebook, run Deep Research, import and verify sources, produce a cited research report, rank audience/content opportunities, create a page brief, and return a final prompt for Google AI Studio or another…

not rated 2 1mo ago A 139 tokens original MIT

Coverage-Cat/skills

Skill Codex

Use whether you're a consumer's own AI agent or a partner operator. This skill covers two homeowners paths: a consumer-prefill handoff that assembles one review-and-consent page from the user's own context, and an operator-partner delegated loop that fills the application from approved CRM, loan, prior-session, email…

not rated 2 changed 6d ago A 90 tokens

ShinKev/kmp-skill-library

Skill Claude CodeCodex

Convert Android XML layouts to Jetpack Compose. Use when asked to migrate Views to Compose, convert XML to Composables, or modernize UI from View system to Compose.

not rated 2 3mo ago A 41 tokens

devops-generate

2795

sirius-zuo/devops-skills

Skill Claude CodeCodex

Use when called by the devops dispatcher after security review to generate all DevOps config files based on analysis.json and security-findings.json.

not rated 2 4mo ago A 32 tokens

Cosmostima/macos-calendar-reminders-skill

Skill Claude Code

Manage Apple Calendar events and Apple Reminders on macOS via calctl.py and remindctl.py — self-contained EventKit CLI scripts. Use when the user wants to create, query, update, or delete calendar events or reminders on macOS.

not rated 2 6mo ago A 57 tokens original MIT

br3eze-code

2797

br3eze-code/br3eze-code

Skill Claude CodeCodex

AgentOS uses a modular 3-tier ReAct reasoning engine. The AI (Gemini 2.0 Flash / Claude Sonnet 4.6 / GPT-4o / Ollama) automatically discovers, chains, and executes these skills via the Tool Registry and Skill Loader.

not rated 2 yesterday A 0 tokens original Apache-2.0

yescan-office-qoder

2798

alibaba-quark-scanking/alibaba-quark-transoffice-qoder

Skill Claude CodeCodex

A document-conversion skill for turning user-provided images, screenshots, or scans into editable Word, Excel, or PDF files. It is intended for documents with tables, contracts, or mixed text and images.

not rated 2 2mo ago A 146 tokens original MIT

gemmamatch

2799

walex8925/Gemma4local

Skill Claude CodeCodex

Auto-detect hardware and recommend the best Gemma 4 model for local deployment on PC, Mac, or mobile.

not rated 2 5mo ago A 28 tokens

pg-skill-forge

2800

gaoguo/pg-skill-forge

Skill Claude Code

A toolkit for creating, testing, and improving skills for the opencode coding agent. A skill is a reusable set of instructions for a particular workflow.

not rated 2 2mo ago A 111 tokens original MIT

unslop

2801

jlwin/unslop_ai

Skill Claude CodeCodex

Writing and editing guardrail against AI slop in German and English prose. Use whenever text is being written or revised that should not read as machine-written – LinkedIn posts, emails, newsletters, blog articles, website copy, reports, slide decks (Präsentationen, Folien, Folientitel), bios, press releases, cover…

not rated 2 changed 11d ago A 181 tokens original MIT

ouyangevan/evidence-first-ai-video-skill

Skill Codex

Use when researching, scripting, sourcing, producing, revising, or quality-checking Chinese or English AI and technology talking-head, presenter-led, voiceover, product-demo, explainer, or social videos whose claims need traceable evidence, real interfaces, synchronized narration, B-roll, or final media QA.

not rated 2 2mo ago A 68 tokens original MIT

scratch-blocks

2803

Z-Bra0/Scratch-Skills

Skill Claude CodeCodex

Use this skill when the user uploads a .sb3 or .sprite3 file, or when the conversation is about Scratch and clearer block-style visualization would help.

not rated 2 5mo ago A 38 tokens original MIT

ideate

2804

nelsonwerd/ideate-skill

Skill Claude CodeCodex

Take a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one living CONCEPTBRIEF.md: a locked concept + phased roadmap. Acts as a blunt, honest co-founder (permission to overrule you), forces a success metric and a kill criterion…

not rated 2 3mo ago B 210 tokens copy · 100% MIT

eat-to-live

2805

ineomu/eat-to-live

Skill Claude CodeCodex

A Chinese-language guide for using food choices to assess and improve health. It covers meal balance, possible links between food and symptoms, diet misconceptions, and dietary reviews for several chronic conditions.

not rated 2 22d ago A 629 tokens

delegate-to-grok

2806

Sunwood-ai-labs/delegate-to-grok-skill

Skill Codex

Delegate coding, repository inspection, comparisons, web research, and public X search from Codex to the locally installed Grok Build CLI on Windows. Use when a user asks to run or consult Grok, resume Grok Build authentication, compare Codex and Grok, inspect or modify a project with Grok, or perform public X…

not rated 2 1mo ago A 74 tokens original MIT

introspect

2807

lukehalley/introspect

Skill Claude Code

Review the user's recent AI coding threads across Claude Code, OpenAI Codex, and Cursor to learn how THEY prefer to work — the preferences and corrections they keep repeating — and to spot places where a missing rule or script made the agent repeat work, then propose and (on approval) write those updates back into…

not rated 2 2mo ago B 243 tokens original MIT

prompt-engineering

2808

ZHOUCOOKIE/prompt-engineering-skill

Skill Claude CodeCodex

Writes, rewrites, reviews, and audits prompts and system prompts using Anthropic's current official guidance, and selects the right model and effort level for the task before drafting. Use when the user asks to write a prompt, improve or fix a prompt, design a system prompt, or check a prompt before running a task …

not rated 2 1mo ago A 212 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: