Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: Media

5,215 results · page 83 of 174

  • muyang-dark-fashionSkillMedia

    Styles include: dark black-red illustration, dark Korean-style illustration, and dark cold-light illustration. Collects the user-specified subject and specific style, fills the subject as-is into the corresponding fixed recipe, and generates the image directly; must not display, expand, rewrite, or

    Ready to connect★ 200

    github.com/yokel1121/muyang-illustration-skills200 stars

    View details
  • muyang-editorial-minimalSkillMedia

    Styles include: refined minimal illustration, minimal modern illustration, minimal ice-blue illustration. Collects the user-specified subject and specific style, inserts the subject as-is into the corresponding fixed recipe, and generates the image directly; must not display, expand, rewrite, or mix

    Ready to connect★ 200

    github.com/yokel1121/muyang-illustration-skills200 stars

    View details
  • muyang-oriental-poetrySkillMedia

    Styles include: courtyard hand-drawn illustration, oriental blue-green illustration, and minimalist ink-gray illustration. Used to collect the subject and specific style specified by the user, fill the subject as-is into the corresponding fixed recipe, and generate the image directly; must not displ

    Ready to connect★ 200

    github.com/yokel1121/muyang-illustration-skills200 stars

    View details
  • muyang-print-posterSkillMedia

    Styles include: retro silhouette illustration, retro movie illustration, and Japanese woodblock print illustration. Used to collect the subject and specific style specified by the user, fill the subject as-is into the corresponding fixed recipe, and generate the image directly; must not display prom

    Ready to connect★ 200

    github.com/yokel1121/muyang-illustration-skills200 stars

    View details
  • muyang-white-coutureSkillMedia

    Styles include: soft gauze pure-white illustration, ornate silver-gray illustration. Collects the user-specified subject and specific style, fills the subject as-is into the corresponding fixed recipe, and generates the image directly; must not display, expand, or rewrite the prompt.

    Ready to connect★ 200

    github.com/yokel1121/muyang-illustration-skills200 stars

    View details
  • penpotSkillMedia

    How to set up and manipulate Penpot design tool state via HTTP APIs for CUA-Gym UI design tasks. For setup-gen and reward-gen agents.

    Ready to connect★ 200

    github.com/xlang-ai/cua-gym194 stars

    View details
  • async-learning-teacherSkillMedia

    Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor th

    Ready to connect★ 198

    github.com/tamdogood/builder-essential-skills198 stars

    View details
  • mcp_elevenlabsSkillMedia

    Generate audio through the ElevenLabs MCP. Use when the user asks to create a voiceover / text-to-speech, multi-speaker dialogue, a sound effect or ambience, or music.

    Ready to connect★ 164

    github.com/manor-os/manor-ai198 stars

    View details
  • mcp_facebookSkillMedia

    Operate Facebook Pages (and linked Instagram Business accounts) through the Facebook MCP. Use when the user asks to publish a Page post / photo / video, manage Page comments, send Messenger DMs, run a live video, read Page or post insights, or publish / moderate on a linked Instagram account.

    Ready to connect★ 164

    github.com/manor-os/manor-ai198 stars

    View details
  • mcp_jimengSkillMedia

    Generate and edit images and generate short videos through the Jimeng (即梦) MCP. Use when the user asks to create or edit an image, or generate a short video, especially from a Chinese-language prompt.

    Ready to connect★ 164

    github.com/manor-os/manor-ai198 stars

    View details
  • mcp_replicateSkillMedia

    Generate images and short videos from text prompts through the Replicate MCP. Use when the user asks to create/generate an image or video with AI, or to run a specific Replicate model.

    Ready to connect★ 164

    github.com/manor-os/manor-ai198 stars

    View details
  • mcp_tiktokSkillMedia

    Operate the user's TikTok creator account through the TikTok MCP. Use when the user asks to read their TikTok profile or videos, or publish a video/photo post to TikTok. For TikTok Shop (orders/products) use mcp_tiktok_shop instead.

    Ready to connect★ 164

    github.com/manor-os/manor-ai198 stars

    View details
  • codeck-speechSkillMedia

    Internal speech module for /codeck. Reads deck content, asks about style and duration only when missing, generates a verbatim speech transcript with stage directions. Outputs $DECK_DIR/speech.md.

    Ready to connect★ 197

    github.com/hiyeshu/codeck197 stars

    View details
  • swiftui-design-skillSkillMedia

    SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns. Covers design direction, layout systems, typography, color, spacing, brand integration, and design review. Use when designing new SwiftUI views, reviewing UI quality, creati

    Ready to connect★ 197

    github.com/wholiver/swiftui-design-skill197 stars

    View details
  • universal-video-prompt-skillSkillMedia

    Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.

    Ready to connect★ 194

    github.com/atlascloudai/awesome-seedance-2.5-prompts-skills197 stars

    View details
  • blender-directorSkillMedia

    Use when starting any Blender asset task, planning a production pipeline, coordinating multiple disciplines, or matching a reference photo/concept art. Invoke for game-ready assets, hard surface, environment, character, creature, export, or any multi-skill Blender workflow.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • camera-cinematographySkillMedia

    Cinematic camera work in Blender including framing, lenses, composition, camera animation, and shot language beyond basic rendering setup via MCP.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • compositingSkillMedia

    Blender compositor workflows for beauty stacks, render passes, color grade, glare, and delivery outputs via MCP.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • creature-artistSkillMedia

    AAA creature modeling for fantasy, aliens, monsters, and organic creature design with believable anatomy and movement. Use for creature blockouts, muscle flow, bone structure, and animation-ready creature assets in Blender via MCP.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • manga-styleSkillMedia

    Manga-inspired art direction for Blender emphasizing monochrome value design, speed lines, screentone feel, and manga panel staging.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • pixel-art-styleSkillMedia

    Pixel-art and texel-constrained art direction for Blender assets destined for pixel rendering, low-res textures, or HD-2D-adjacent pixel reads.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • renderingSkillMedia

    Blender rendering with Cycles and Eevee including sampling, denoising, camera setup, render passes, color management, and render optimization. Use for final output and look validation via MCP.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • stylized-styleSkillMedia

    Stylized art direction for Blender with shape language, exaggeration, color harmony, NPR rendering, and hand-painted asset workflows. Use for non-photorealistic game and animation projects.

    Ready to connect★ 193

    github.com/arjun988/blender-skills196 stars

    View details
  • codex-systemSkillMedia

    Codex CLI handles planning, design, and complex code implementation. Use for: architecture design, implementation planning, complex algorithms, debugging (root cause analysis), trade-off evaluation, code review. External research is NOT Codex's job — use general-purpose-opus instead. Explicit trigge

    Ready to connect★ 195

    github.com/del-taiseiozaki/claude-code-orchestra193 stars

    View details
  • context-loaderSkillMedia

    ALWAYS activate this skill at the start of every task. Load shared rules from .claude/rules/ and project design context before executing any task.

    Ready to connect★ 195

    github.com/del-taiseiozaki/claude-code-orchestra193 stars

    View details
  • initSkillMedia

    Analyze project structure, populate .claude/docs/DESIGN.md, and write the thin Repository Identity section in .claude/STATE.md.

    Ready to connect★ 195

    github.com/del-taiseiozaki/claude-code-orchestra193 stars

    View details
  • 2dimg2motionSkillMedia

    Use when a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.

    Ready to connect★ 194

    github.com/wu-haotian34/2dimg2motion194 stars

    View details
  • img2mo-learnSkillMedia

    Learn reusable 2D motion-generation knowledge from user-specified action resources with `/img2mo-learn <resource>`. Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animati

    Ready to connect★ 194

    github.com/wu-haotian34/2dimg2motion194 stars

    View details
  • img2mo-stdSkillMedia

    Standardize a 2D animation baseline image with `/img2mo-std xxx.png/pos`. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/

    Ready to connect★ 194

    github.com/wu-haotian34/2dimg2motion194 stars

    View details
  • hz-android-2d-portingSkillMedia

    Guides porting existing Android 2D apps to Meta Quest and Horizon OS — input adaptation, panel layout, and design requirements. Use when adapting a mobile Android app for Quest.

    Ready to connect★ 193

    github.com/meta-quest/agentic-tools193 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

53,789 of the 54,221 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI