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
5,307 results · page 172 of 177
- View details
context7SkillMedia
Use when researching external libraries/frameworks (React, Radix, Tailwind, etc.) — reach for the Context7 MCP to get up-to-date docs. Not for internal codebase or design-system-token questions.
Ready to connect
- View details
copy-directionSkillMedia
Use when someone asks what the copy on one marketing or acquisition surface should feel like before the lines are written. Produces ranked, grounded copy goals and a `copy-direction.md` record for that surface. `tone-of-voice` owns the cross-surface brand register, `content-design` runs first to dec
Ready to connect
- View details
css-architectureSkillMedia
Organize CSS at scale using cascade layers, scoping strategies, and specificity budgets — preventing specificity wars, enabling safe deletion, and making CSS that other engineers can reason about. Triggers on "design the CSS architecture for this new codebase", "fix the specificity wars in our style
Ready to connect
- View details
design-intelligenceSkillMedia
Skill for Competitive Design Intelligence and UI Generation. Use when you need to research competitors, analyze visual trends of a niche, generate moodboards, or improve an existing interface based on visual benchmarking. Triggers on: "melhorar interface", "pesquisar concorrentes", "benchmark
Ready to connect
- View details
diptrace-revision-reviewSkillMedia
RAG-backed. Compare DipTrace hardware revisions, trace electrical/BOM/layout changes, and prepare an ECO with affected verification and release artifacts. Use for netlist diffs, substitutions, rework reconciliation, design regressions, or a new board revision; «сравни ревизии», «ECO платы». Use when
Ready to connect
- View details
fallaciesSkillMedia
Apply when a session is about to propose, widen, add or "fix" something nobody asked for, when a finding argues a design is not the simplest, when a CI, cache or trigger change is being weighed, and when a review's quality lane asks whether a concern is real before asking whether the fix is. Esposte
Ready to connect
- View details
ferrox-ai-integration-phaseSkillMedia
A step involves building an AI system and you want its design and evals pinned down first
Ready to connect
- View details
ferrox-design-initSkillMedia
You want a durable design contract before any UI is built. Creates DESIGN.md by interview
Ready to connect
- View details
ferrox-ui-phaseSkillMedia
A step involves frontend work and you want the design pinned down before it is built
Ready to connect
- View details
ffmpeg-mediaSkillMedia
Skill for mechanical video/audio editing and manipulation via ffmpeg — cutting, joining, subtitles, loudness normalization, silence detection, redaction, aspect ratio correction, speed changes, metadata extraction. Runs 100% locally via Python scripts (stdlib + subprocess), no paid API and no upl
Ready to connect
- View details
gaia-react-perfSkillMedia
Diagnose React render performance by driving a micro-interaction, capturing real renders, and surfacing memo-defeating reference instability with a recommended structural fix. Measure-only: it emits a diagnosis, it does not auto-fix. Trigger on `/gaia-react-perf` or natural-language asks like "profi
Ready to connect
- View details
game-architecture-designSkillMedia
Skill for game architecture, design review, and numerical balancing — the decision-making layer before engine code. Covers paradigm selection (rich entity vs data-driven vs prototype), design of specific systems (combat, skills, AI, narrative, UI, PCG), and critical review of GDD/mechanics/levels
Ready to connect
- View details
google-ai-studio-ttsSkillMedia
Generate speech, podcasts, voiceovers, and multi-speaker dialogue with Google AI Studio's Gemini Flash TTS by driving the live web app in Chrome via the claude-in-chrome MCP server. Use whenever the user asks to (1) create a podcast, audiobook chapter, narration, audio drama, or voiceover with Gemin
Ready to connect
- View details
image-generatorSkillMedia
Lets your agent generate and edit images, like photos, logos, and product mockups.
Ready to connect
- View details
image-style-librarySkillMedia
A library of style templates for image generation with a guide to prompt writing (a pure prompt skill, used together with the image_generate tool).
Ready to connect
- View details
light-sceneSkillMedia
Use when a PlayCanvas scene must read as a deliberate image rather than a flat asset preview — photoreal and cinematic, or stylized, low-poly, and palette-driven — to set key and ambient lighting, sky and image-based lighting, shadows, tone mapping and exposure, water, and a restrained post-process
Ready to connect
- View details
link-downloadSkillMedia
Download videos as MP4 or extract audio as MP3 from Instagram, YouTube, TikTok, Twitter/X, Facebook, and 1000+ other platforms using yt-dlp. Use this skill when the user wants to download, save, or grab a video or audio/song/music from any URL. Supports MP4 (default) and MP3 (with --mp3 flag). Handl
Ready to connect
- View details
lofnSkillMedia
Run the full award-winning Lofn creative pipeline — art/image, music/song, video/animation, or story — backed entirely by Codex. Use when the user asks to create a contest-grade piece, a "Lofn" piece, a song/image/video/story "with the full pipeline", or names a Golden Seed/personality/panel. This i
Ready to connect
- View details
lofn-animatorSkillMedia
Animate Lofn visual concepts and produce motion/animation plans across the current generator field (Veo 3.1, Kling v3, Seedance 2.x, MiniMax H3, LTX-2.x, Gemini Omni Flash). Use for animation, motion design, video-transition planning, animated image prompts. Do NOT use for static image generation, m
Ready to connect
- View details
lofn-coreSkillMedia
Create Lofn golden seeds, core briefs, seed packets, and high-level creative DNA for image/music/video/story runs. Use at pipeline start. Do NOT use for final QA, scoring 24 outputs, or direct rendering.
Ready to connect
- View details
lofn-dailySkillMedia
Run the Lofn daily pipeline backed by Codex — fetch real-world facts, then generate the day's music (24 songs) and images (24→top 6) through the full Lofn pipeline with the daily rules (tri-source method, dual 3+3 constraint, emotional duality, library-only selection). Use for "daily run", "today's
Ready to connect
- View details
lofn-distributeSkillMedia
Take a finished Lofn release (album, single, image set, video) out to the world across Suno, Instagram, TikTok, YouTube, NightCafe and the Spotify/Apple destination — route audit first, per-surface copy contracts, panel, The Scientist's approval, publish, verify, ledger. Use for "announce the album"
Ready to connect
- View details
lofn-evaluationSkillMedia
Evaluate, score, rank, and select Lofn outputs using panels, facets, eligibility scoring, and platform fit. Use after 24 outputs exist or when choosing finalists. Do NOT use to generate songs/images or perform QA formatting cleanup.
Ready to connect
- View details
lofn-imageSkillMedia
Run Lofn image/vision pipeline steps, visual prompt generation, render prompt packaging, and image competition prompt work. Do NOT use for music lyrics, QA audit, or evaluator ranking.
Ready to connect
- View details
lofn-musicSkillMedia
Run the Lofn music/audio pipeline (steps 00–11) backed by Codex — Suno-ready song packages with two-field style/exclude prompts, EMO-tagged lyrics, song guides. Use for songs, tracks, beats, lyrics, music production briefs, or "write a song with the full pipeline". Expects a Phase-0/1 orchestrator p
Ready to connect
- View details
lofn-qaSkillMedia
Audit, validate, and classify completed Lofn pipeline outputs against the strict quality gates, backed by Codex. Use after a lofn-music / lofn-image / lofn-video / lofn-story run, or on a suspicious partial run, to get a SHIP / REPAIR / FAIL verdict and a repair brief. Do NOT use for creative genera
Ready to connect
- View details
lofn-render-auditSkillMedia
Audit a FINISHED audio render against the prompt that asked for it — numeric measurement plus a listening-model pass — to find out which intents survived the generator, which were smoothed away, and which deviations are better than what was specified. Use after rendering Suno output, when asked "did
Ready to connect
- View details
lofn-storySkillMedia
Run Lofn narrative/story pipeline, prose, scene, beat, and storytelling outputs. Do NOT use for music, image prompts, QA, or evaluation.
Ready to connect
- View details
lofn-videoSkillMedia
Run the Lofn video/animation pipeline (steps 00–10) backed by Codex — cinematic shot lists and motion/animation prompts, written for a NAMED renderer (Veo / Kling / Seedance / MiniMax H3 / LTX / Gemini Omni Flash) with synchronized audio. Use for video, film, cinematic clips, animation, animated loo
Ready to connect
- View details
mega-brain-com-copy-thiefSkillMedia
I want you to now use the full power of mega brain with... the copy thief, which is activated in the system. It needs to investigate more... smart terms and what is happening now, in the current market, so that this video gets as many hits and views as possible.
Ready to connect
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.
54,624 of the 55,055 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.