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
5,210 results · page 53 of 174
- View details
director-art-designSkillMedia
Costume, makeup & props — designs image-generation prompts for "character design sheets" and "scene environment art", including a top "style prefix block" (camera/film/color grading/aspect ratio etc., a unified style baked into the image) + image-gen avoid list (extra fingers/text watermarks/continu
Ready to connect★ 511
- View details
director-cinematographySkillMedia
Cinematic language and cinematography methodology—unified shot size system, composition rules, the emotional language of camera movement, lighting setups, depth of field control, color temperature and light sources, lens characteristics, and how to translate these into video prompts. Reference for N
Ready to connect★ 511
- View details
director-consistencySkillMedia
A methodology for tackling the three chronic problems of AI video: same character changing faces, same props changing form, and same scenes changing look across shots — covering five-dimension consistency checks, reference-image anchoring, in-scene state tables, and inter-segment continuity. Use as
Ready to connect★ 511
- View details
director-keyframe-reviewSkillMedia
A Go/No-Go review checklist for reference images (character/scene design sheets) — item-by-item checks, decision rules, and feedback templates to help users quickly determine whether a design sheet passes and, if not, how to give feedback for adjustments and re-generation; used for reviewing after N
Ready to connect★ 511
- View details
director-performanceSkillMedia
Performance direction for non-action dramatic scenes — micro-expressions, body language, gaze design, silence acting, and character behavioral patterns. AI cannot "act" on its own; emotions must be precisely physicalized in the prompt into filmable bodily signals (eyebrows/eyes/mouth/hands/shoulders
Ready to connect★ 511
- View details
director-shot-translationSkillMedia
A manual for translating 'shot intent' into video prompts — camera movement translation table (push/pull/pan/follow/orbit… → prompt wording), focus translation, composite shot (multi-clip) patterns, iron rules for replacing contaminated words, and converting abstract actions/emotions into physical a
Ready to connect★ 511
- View details
director-soundSkillMedia
Sound design knowledge—ambience/sound effects/score mood/silence design/auditory motifs (leitmotif)/audiovisual counterpoint—for narrative planning and post-editing reference only; ⚠️ video generation prompts contain no audio, so this content is not written into shot prompts—it's for Nomi's timeline
Ready to connect★ 511
- View details
director-stagingSkillMedia
Multi-character staging methodology — blocking design / sightline networks / attention guidance / foreground-background layering / multi-character consistency control in AI generation for scenes with 3+ characters. Refer to it when Nomi writes prompts for multi-character shots (who stands where / fa
Ready to connect★ 511
- View details
director-style-otomo-wrightSkillMedia
Director style fusion move · Kiyoshi Kurosawa × Edgar Wright (stylish action heist DNA) — assigns camera moves + editing rhythm + audio-visual beat sync separately by scene type (car chase / fight / parkour / theft stealth / warm dialogue scene / stylish costume-change entrance). Apply when Nomi is
Ready to connect★ 511
- View details
director-transitionsSkillMedia
Creative transition methodology. AI videos are generated shot by shot and frames naturally don't align, so hard cuts expose seams — use creative transitions like occlusion, whip pans, dips to black, match cuts, or objects passing across the lens to stitch adjacent shots into a seamless flow, while a
Ready to connect★ 511
- View details
effect-camera-27SkillMedia
Controls shot pacing with concrete camera position and movement descriptions. Use when the user requests audio transitions.
Ready to connect★ 511
- View details
effect-restore-drawingSkillMedia
Old image redraw: uses connected references to preserve subject consistency. Use when the user requests redrawing of an old image.
Ready to connect★ 511
- View details
nomi-add-modelSkillMedia
Connect a generative model (text / image / video / audio / 3D) to the local Nomi and run a real verification pass. Use when the user says things like "hook X up to Nomi", "add a model in Nomi", or "connect this relay provider to Nomi". Requires the host to be connected to Nomi's MCP server (tool nam
Ready to connect★ 511
- View details
release-media-packSkillMedia
Create story-first bilingual promo videos, update visuals, and release copy for Nomi desktop releases, chaining version facts, TikHub sample research, Nomi generation, and local post-production into a traceable asset pack.
Ready to connect★ 511
- View details
workbench-generationSkillMedia
Generation-area AI assistant. Plans image/video canvas nodes with prompts; never auto-executes generation.
Ready to connect★ 511
- View details
writer-behavior-psychologySkillMedia
Behavioral psychology screenwriting tool — turns psychological tools like cognitive dissonance, attachment theory, defense mechanisms, and microexpressions into character behavior design and audience psychological manipulation. Reference when designing character behaviors / psychological turning poi
Ready to connect★ 511
- View details
writer-dialogueSkillMedia
Dialogue expert (David Mamet methodology) — line writing / subtext design / character voice personalization / dialogue beat analysis / silence design. Reference for Nomi when writing scripts or dialogue in the creation zone.
Ready to connect★ 511
- View details
writer-structureSkillMedia
Structurist (John Truby methodology) — organic story structure design / opponent network building / scene weaving / pacing control / hook arrangement. Reference when building a story skeleton in Nomi's writing area.
Ready to connect★ 511
- View details
video-assembleSkillMedia
Assembles the final narration video: lays narration audio over the source video, ducks the original audio according to narration windows, generates SRT / ASS subtitles with optional burn-in, and finally performs loudness normalization. Used as the final assembly stage. Inputs: source video, tts_meta
Ready to connect★ 509
- View details
editorial-card-screenshotSkillMedia
Generate high-density editorial HTML info cards in a modern magazine and Swiss-international style, then capture them as ratio-specific screenshots. Use when the user provides text or core information and wants: (1) a complete responsive HTML info card, (2) the design to follow the stored editorial
Ready to connect★ 508
- View details
maintainer-declineSkillMedia
Guide for drafting issue closure and decline responses as an open-source package maintainer. Use when helping compose a reply that says \"no\" to a feature request, closes an issue as won't-fix, redirects a user to a different package, explains why a design choice is intentional, or otherwise declin
Ready to connect★ 498
- View details
review-testingSkillMedia
Review test code for quality, design, and completeness after implementing a feature or fixing a bug. Use when the user asks to "review my tests", "check my test quality", "are these tests good enough", "review testing", or after completing a feature implementation that includes tests. Also use when
Ready to connect★ 498
- View details
cds-codeSkillMedia
Provides a workflow for building and reviewing high-quality React and React Native UI with the Coinbase Design System (CDS). Use this skill to create UI or make visual changes to existing UI with CDS components, tokens, style props, icons, and illustrations. Use it for explicit CDS-adherence audits
Ready to connect★ 505
- View details
cds-design-to-codeSkillMedia
Turn Figma designs into CDS React (cds-web) or React Native (cds-mobile) code. Use when the user shares a Figma design URL (e.g. `figma.com/design/...?node-id=...`) or asks to "implement this design" or "build this from Figma" in a frontend project that is using Coinbase Design System (CDS). Do not
Ready to connect★ 505
- View details
research.component-libsSkillMedia
Orchestrates a comprehensive research effort across multiple design systems/component libraries
Ready to connect★ 505
- View details
feature-devSkillMedia
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementa
Ready to connect★ 504
- View details
huggingface-lora-space-builderSkillMedia
Lets your agent build and publish a Gradio demo page on Hugging Face for your LoRA model.
Ready to connect★ 504
- View details
bench-fixture-genSkillMedia
Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.
Ready to connect★ 503
- View details
claude-designSkillMedia
A skill that analyzes the current codebase (or folder), synthesizes a "design context brief" (stack/design tokens/components/routes/actual UI copy/curated assets/repo links), automatically passes it to Claude Design (claude.ai/design) to generate a design, and returns the result link in a clickable
Ready to connect★ 503
- View details
omdSkillMedia
Compatibility router for older `omd` invocations. Route existing UI work to omd:apply, autonomous greenfield work to omd:autopilot, and DESIGN.md-only setup or migration to omd:init. Use it only when the legacy skill name is invoked; it reads Core v2 or legacy context without writing DESIGN.md itsel
Ready to connect★ 503
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.
53,585 of the 54,017 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.