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
5,264 results · page 142 of 176
- View details
design-system-adaptationSkillMedia
Translate an outside visual reference into an existing design system without breaking product consistency, token logic, or component contracts.
Ready to connect★ 54
- View details
design-system-distillationSkillMedia
Distill product context and references into a project-level DESIGN.md or design brief with explicit visual rules and anti-patterns.
Ready to connect★ 54
- View details
design-ui-critique-and-polishSkillMedia
Critique an existing UI with prioritized findings, system-level causes, and concrete polish moves that preserve implementation realism.
Ready to connect★ 54
- View details
douyin-publishSkillMedia
Fill in and publish image-text or video posts in the Douyin Creator Center, including local asset upload, video cover settings, music selection, pre-publish validation, and explicit confirmation clicks. Use when the user asks to publish a Douyin image-text post/video or review pending content; not f
Ready to connect★ 54
- View details
figma-drift-auditSkillMedia
Audit drift between code-side and Figma-side design systems across tokens, components, library version, and screens, then output a remediation plan keyed by severity and direction.
Ready to connect★ 54
- View details
figma-implementation-handoffSkillMedia
Generate implementation suggestions or scoped code-change drafts from a Figma node, frame, or page with explicit assumptions, missing-token callouts, and a reviewable handoff record.
Ready to connect★ 54
- View details
imagencnSkillMedia
Multi-platform AI image generation via DashScope/Ark/Hunyuan/Zhipu/StepFun plus Grok/OpenAI/Gemini/FLUX (international), specializing in Chinese text rendering and photorealistic images
Ready to connect★ 51
- View details
math-figureSkillMedia
Use when a 高教社杯/CUMCM mathematical modeling paper needs to plan, select, review, or fix figures, charts, table-to-figure conversion, captions, image evidence lines, body-text placement, appendix demotion, or post-figure conclusions.
Ready to connect★ 53
- View details
math-modelSkillMedia
Use when a 高教社杯/CUMCM mathematical modeling task requires variables, assumptions, formulas, constraints, algorithms, validation design, robustness planning, sensitivity analysis, result schema, or code handoff based on the problem statement and local evidence.
Ready to connect★ 53
- View details
motion-render-opsSkillMedia
Render a validated storyboard into reproducible video output with pre-render checks, render configs, and render manifests.
Ready to connect★ 54
- View details
motion-storyboardSkillMedia
Turn a motion brief into a validated storyboard with scenes, targets, audio, captions, and a cover frame before render.
Ready to connect★ 54
- View details
smith-planSkillMedia
Execute the implementation planning workflow using the plan template to generate design artifacts.
Ready to connect★ 54
- View details
smith-tasksSkillMedia
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
Ready to connect★ 54
- View details
smith-taskstoissuesSkillMedia
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
Ready to connect★ 54
- View details
thai-translateSkillMedia
Use this skill for any task involving English-Thai or Thai-English translation, localization, or rewording. Trigger whenever the user asks to: translate text between Thai and English, localize content for a Thai audience, render English idioms in Thai (or vice versa), pick the right pronouns and reg
Ready to connect★ 54
- View details
ux-spec-authorSkillMedia
Converts UX/design intent into testable design specifications that feed requirements. Use when defining user flows, accessibility, or design constraints.
Ready to connect★ 54
- View details
videogencnSkillMedia
Use when generating video clips with Chinese video models — text-to-video (文生视频), image-to-video (图生视频), first/last-frame and reference-to-video across 4 platforms: Bailian (Wan/PixVerse/Kling/Vidu/HappyHorse), Jimeng (doubao-seedance), MiniMax (Hailuo), Hunyuan (hy-video)
Ready to connect★ 51
- View details
x-recruiterSkillMedia
For posting recruitment posts on X (x.com). Includes copywriting guidelines, image generation prompts, and automated publishing scripts. Prefer this when posting AI-related or design-related job openings.
Ready to connect★ 54
- View details
xiaohongshu-recruiterSkillMedia
Used to publish high-quality AI job recruitment posts on Xiaohongshu. Includes auto-generation of geek-style recruitment cover and detail images, and provides an automated publishing script. Use when the user needs to post recruitment information or find Agent designers or other AI-domain talent.
Ready to connect★ 54
- View details
xsaiSkillMedia
Use this skill when the user is building with `xsai` or any `@xsai/*` package, or is evaluating xsAI for a small OpenAI-compatible workflow with text generation, streaming, tool calling, structured output, embeddings, image generation, speech synthesis, or transcription.
Ready to connect★ 54
- View details
yt2bbSkillMedia
Use when the user wants to repurpose a YouTube video for Bilibili, add bilingual (English-Chinese) subtitles to a video, or create hardcoded subtitle versions for Chinese platforms.
Ready to connect★ 51
- View details
assemblyai-streamingSkillMedia
This skill should be used when working with AssemblyAI’s Speech-to-Text and LLM Gateway APIs, especially for streaming/live transcription, meeting notetakers, and voice agents that need low-latency transcripts and audio analysis.
Ready to connect★ 53
- View details
change-managementSkillMedia
Diagnose adoption barriers and design organizational change, stakeholder engagement, communications, training, and reinforcement. Use for system rollouts, new operating models, integration, culture change, and adoption measurement.
Ready to connect★ 53
- View details
client-deliverablesSkillMedia
Create and refine consulting reports, decision memos, and executive presentations, including storylines, exhibits, visual design, and artifact review. Use for board readouts, investment committee memos, steering updates, and final reports. For sales proposals and pitch decks, use proposal-developmen
Ready to connect★ 53
- View details
cm-brainstorm-ideaSkillMedia
Strategic analysis gate for existing products — multi-dimensional evaluation (tech, product, design, business) using Design Thinking + 9 Windows (TRIZ) + Double Diamond. Outputs 2-3 qualified options with recommendations. Use BEFORE cm-planning for complex initiatives and enhancements on existing co
Ready to connect★ 53
- View details
cm-design-studioSkillMedia
[Deprecated] design pipeline merged. Use `cm-design-system` instead.
Ready to connect★ 53
- View details
cm-design-systemSkillMedia
Ultimate Design System Intelligence. Manage, extract, replicate, and improve UI design systems. Extracts design tokens visually from existing sites (Harvester v5), manages multi-page tokens, and utilizes MCP servers like Google Stitch and Pencil.dev to generate complete, consistent design systems (S
Ready to connect★ 53
- View details
cm-ui-previewSkillMedia
[Deprecated] UI preview is part of design system. Use `cm-design-system` instead.
Ready to connect★ 53
- View details
cm-ux-masterSkillMedia
Ultimate UI/UX design intelligence: an Anti-Slop layer that kills AI tells (em-dash, AI purple glow, generic names, template layouts), tunable Design Dials (variance/motion/density) and Style Modes (functional, minimalist, brutalist, soft-premium, marketing), 161 industry color palettes in a shadcn-
Ready to connect★ 53
- View details
cm-video-factorySkillMedia
Private Code-to-Video Engine using Remotion React, TTS (ElevenLabs/OpenAI), and Content Mastery. Creates pure VibeCoding-style animations for TikTok/Shorts/Reels automatically.
Ready to connect★ 53
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.
54,249 of the 54,680 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.