Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
paid-ads
by alecs5amWhen the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' or 'should I run ads.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see page-cro.
lottie
by alecs5amLottie and dotLottie adapter patterns for HyperFrames. Use when embedding lottie-web JSON animations, .lottie files, @lottiefiles/dotlottie-web players, registering instances on window.__hfLottie, or making After Effects exports deterministic in HyperFrames.
ugc-ad-production
by alecs5amFull end-to-end workflow for generating a realistic AI UGC ad for a product. 15-second format. Looks real. Doesn't feel AI.
ugc-model-swap
by alecs5amUGC Model Swap Recreate any short UGC-style video with a different person while keeping everything else (setting, action, props, audio, camera feel) identical to the original.
ugc-ad
by alecs5amHow to make a realistic AI UGC ad for a product — generalized niche know-how that looks real and doesn't feel AI. A domain overlay on the standard pipeline: supplies the shooting-script shape (timestamp | VO | shot | mannerism), the creator-persona build, the problem-mirror hook, the trust-through-mannerisms rule, and the 9:16 ~15s UGC format defaults. Works for ANY product the user names — their skincare line, a no-name app, a gadget. The skill supplies the know-how; the user supplies the product. USE WHEN the user asks for a UGC ad / creator-style product ad / "make an ad that looks like a real person reviewing my product" / testimonial-style or problem-solution short for TikTok / Reels / Shorts, with no specific existing video to reproduce. This is a niche SKILL (generalized), not a remix TEMPLATE. For "remix this exact ad but swap the product/person", use the remix path (docs/skills-vs-templates.md). For swapping the creator in an existing clip, see /ugc-model-swap.
ugc-model-swap
by alecs5amHow to recreate a short UGC-style video with a DIFFERENT person/character while keeping everything else identical — setting, action, props, audio, camera feel. The craft layer behind the remix-with-swap pattern ("same video, but replace the creator with X"). Supplies the source-video analysis step, the single-continuous-scene prompt shape, the face-lock rule, prop-negative discipline, and explicit body-mechanics that keep the swap faithful. Works for any source clip + any replacement character. USE WHEN the user shares a UGC clip (challenge / reaction / review / try-on / unboxing) and wants the same clip with a different person or character, or wants several character variants of one clip. Pairs with the remix path in docs/skills-vs-templates.md: remix swaps any element of a template; this skill is the specialist for swapping the on-camera person. For building a UGC ad from scratch, see /ugc-ad.
ugc-rockstar
by alecs5amHow to make a GTA-V-style video in the Rockstar-crime-cinema aesthetic — generalized niche-style know-how, concept to camera-ready. A style overlay on the standard pipeline: supplies the visual DNA (teal-and-orange grade, golden-hour Los-Santos light, low-angle power shots, slow-push establishing, helicopter pull-backs), the satirical double-register tone, the location→character→conflict→theme scene logic, and the shot-list shape. Works for any premise — a fake-brand ad, a heist beat, a street skit, a short film. USE WHEN the user wants a GTA-V / Rockstar / Los-Santos / open-world-crime-cinema look, "make it feel like GTA", a satirical fake-brand ad in that register, or a Vinewood/heist-style short, with no specific existing video to reproduce. This is a niche-style SKILL (generalized), not a remix TEMPLATE. It is an original aesthetic homage — it does not impersonate real living people or reproduce a specific copyrighted scene.
ugc-toon-action
by alecs5amHow to make a stylized cartoon / painterly action animation of ANY subject — generalized niche know-how, not one specific video. A domain overlay on the standard pipeline that supplies the two pillars of good toon-action: (1) a seedance-2.0 t2v action-generation guide (the literal painterly STYLE block, the AUDIO-POLICY block, the named-style-reference silhouette-lock trick, multi-clip continuity anchoring, and WHY kling is wrong for non-default physics) and (2) GPT character-generation prompts (the SUBJECTS-block design discipline + named-pop-culture-reference lock). Works for ANY premise the user names — a skate duel, a cooking battle, a pet chase, a product mascot — the skill supplies the know-how, the user supplies the subject. USE WHEN the user wants a cartoon / animated / painterly / comic-book / Spider-Verse-or-Arcane-style action scene, "make a cool toon animation", a stylized action short, with no specific existing video to reproduce. This is a niche-style SKILL (generalized), not a remix TEMPLATE (o
ugc-unboxing
by alecs5amHow to make a generic UGC unboxing video for socials — generalized niche know-how, not a single video. A domain overlay on the standard pipeline (intake → scenarist → art-director → editor): supplies the beat structure (cold-open hook → reveal → detail macro → reaction → CTA), hands-only framing and lens vocabulary, the ASMR-leaning SFX register, the default model stack, and the niche's common failure modes. Works for ANY product the user names — their coffee grinder, a no-name skincare set, a gadget — the skill supplies the know-how, the user supplies the subject. USE WHEN the user asks for an unboxing / "open the box" / "first look" / haul / "what's inside" video for TikTok / Reels / Shorts, with no specific existing video to reproduce. This is a niche SKILL (generalized), not a remix TEMPLATE (one specific video). For "remix this exact unboxing but swap X", that is the remix path in docs/skills-vs-templates.md, not this skill.
normalize-skills
by alecs5amAudit the health of every `.agents/skills/*/SKILL.md` and fill icon gaps on the landing skills marketplace. Two jobs: (1) AUDIT — for each skill folder, check that frontmatter parses, `name` is kebab-case (`/^[a-z][a-z0-9-]*$/`) and matches the folder, `description` is ≤1536 chars, `namespace` is `user` or `maintainer`, and a `.claude/skills/<slug>` symlink exists and resolves; report drift. Complements `lint:skills`, does not replace it. (2) ICONS — detect skills with no `landing/public/assets/skills/<slug>.webp`, give each a fitting pixel-art subject in `landing/scripts/gen-skill-icons.sh`, run generation for the missing slug(s) only, chroma-key + composite via `build-skill-icons.py`, verify the webp landed, then commit + push. USE WHEN the user types `/normalize-skills`, says "audit the skills", "check skill frontmatter", "which skills are missing an icon", "generate the missing skill icons", "fill the icon gaps", "fix skill drift", or after renaming/adding a skill that needs a marketplace tile. See body f
analog-horror-psa
by alecs5amHow to make an analog-horror PSA short — the stenciled-pictogram / robo-broadcast / VHS-overlay format (faceless, 10 scenes × ~3s, 9:16, ~30s total). A domain overlay on the standard pipeline that supplies the IF / DO-NOT / BUT / AND scenario structure, the locked yellow-on-black 1970s-civil-defense pictogram visual STYLE, the chroma-key-to-alpha rule (icons must be transparent PNGs before composition), the robo-PSA voice profile (ElevenLabs "Alerter" community voice + ALL CAPS input + stability ~0.5 + style 0), the layered VHS-noise overlay stack (SnowCanvas + VcrTrackingCanvas + MobiusScanlines + MobiusWobble), the 5-layer RGB chromatic-split for icons + captions, the SMPTE colour-bars climax (3 wide vertical bars + filter blur(2.5px) mandatory), and the `-tune grain` CRF 30 final-encode rule for noise-heavy renders. Works for ANY PSA topic — "your fridge is not your fridge", "your phone is not your phone". USE WHEN the user asks for an analog horror PSA / "creepy PSA-style short" / fake-emergency-broadcast
storyboard-generation
by alecs5amRules and prompts for generating structured presentation slides and multi-panel storyboards.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.