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 54 of 174
- View details
omd-aphroditeSkillMedia
Maximum-craft one-page landing — the wow bar. Built on top of the omd:landing structure, adding finishing touches (font sourcing, grain, depth, color grading, scroll timeline) and premium assets, with passing all items in the landing inspection as the minimum bar. Trigger: '와우', '압도적인', '최고급', '쇼케이스
Ready to connect★ 503
- View details
omd-applySkillMedia
Applies the project's DESIGN.md as brand context for UI/visual work. Triggers on specific requests like editing components, colors, fonts, or layout, as well as tone/mood expressions — KR '좀 더 따뜻하게', EN 'make it warmer/cooler', 日本語「もう少し暖かく」, 繁體中文「更溫暖一點」. If DESIGN.md is missing, run omd:init first.
Ready to connect★ 503
- View details
omd-autopilotSkillMedia
One-prompt autonomous product design and implementation. Use automatically for broad greenfield UI requests such as 'from scratch', '새 제품/화면을 알아서 만들어줘', or requests that delegate DESIGN.md creation. It decides whether to reuse, establish, refresh, or skip a project design system; asks at most one co
Ready to connect★ 503
- View details
omd-component-harvestSkillMedia
Legacy catalog component writer safety gate. Use when component harvesting is requested, but stop before editing until the Core v2 graph-backed catalog writer and readers are available.
Ready to connect★ 503
- View details
omd-harnessSkillMedia
A guided design harness that reviews step-by-step with the user. omd-master runs Discovery→Wireframe→Components→Microcopy→Validation and pauses at mandatory checkpoints in journey/system/validation. Use for '/omd-harness', 'review at each checkpoint', 'design step-by-step with me', 'guided design' r
Ready to connect★ 503
- View details
omd-humanizeSkillMedia
Polishes product docs, UX copy, and landing copy into natural sentences in KO/EN/JA/ZH-CN/ZH-TW while preserving facts, figures, commands, links, and brand voice. Use for requests like 'remove the AI feel', 'fix translationese', 'the sentences sound robotic', 'polish it like a local user', or 'human
Ready to connect★ 503
- View details
omd-lab-02-design-harnessSkillMedia
OmD Lab #02 — Design harness refinement experiment. Run the same task across v1, v2, v3... harness configurations and compare output quality, token cost, iteration count, and persona ABANDON rate. Triggers — '/omd-lab-02', 'start the harness lab', 'run design harness v2 and compare', 'lab #02 auto c
Ready to connect★ 503
- View details
omd-landingSkillMedia
Scroll-native one-page landing that overwhelms — concept, composition, asset placement, and scroll choreography derived from DESIGN.md and the measured landing-craft codex. Trigger: '랜딩 페이지', '원페이지', 'landing page', 'one-pager', 'hero to footer', '스크롤 랜딩', 'affinity.studio 같은'.
Ready to connect★ 503
- View details
omd-mediaSkillMedia
Brand-consistent asset sets from DESIGN.md — hero, section illustrations, icon sets, OG image — generated through whichever channel the user actually has (grok build image_gen, Codex $imagegen, Gemini, xAI/Recraft/OpenAI keys) as recorded by omd:setup, with a provenance and cost ledger. No channel →
Ready to connect★ 503
- View details
omd-showcaseSkillMedia
Turn a rendered page (or several, side by side) into a scroll demo video — deterministic frame capture, ffmpeg H.264/GIF, labels per arm. Trigger: '시연 영상', '스크롤 영상 만들어', 'showcase', 'demo video', '비교 영상', 'record the page'.
Ready to connect★ 503
- View details
omd-slop-auditSkillMedia
Audits UI/UX copy on real product routes to diagnose generic repeated AI patterns without product context, decoration with no brand rationale, overuse of cards/gradients/icon tiles, and translation-style or abstract copy, reporting rule IDs and line refs. Use for requests like 'catch AI slop', 'feel
Ready to connect★ 503
- View details
omd-token-backfillSkillMedia
Legacy reference token writer compatibility gate during the DESIGN.md Core v2 catalog cutover.
Ready to connect★ 503
- View details
omd-updateSkillMedia
Safely update an existing oh-my-design installation in place and verify it afterward. Use when the user asks to update, upgrade, refresh, reinstall, or check whether their OmD skills, agents, hooks, or reference catalog are current.
Ready to connect★ 503
- View details
omd:add-referenceSkillMedia
Reference catalog authoring compatibility gate. Blocks new legacy DESIGN.md writes until the Core v2 cutover is complete and explains safe resumption conditions.
Ready to connect★ 503
- View details
omd:asset-fetchSkillMedia
Fills placeholder slots in user product UI with **real free-license CDN assets** instead of generic SVGs. Maintains a catalog of logos, illustrations, icons, photos, fonts, and patterns using verified URLs only. Triggers on requests like 'fetch me an asset', 'replace placeholders with real images',
Ready to connect★ 503
- View details
omd:batch-launchSkillMedia
Reference batch writer compatibility gate during the DESIGN.md Core v2 catalog cutover.
Ready to connect★ 503
- View details
omd:codex-imageSkillMedia
Dynamically materialize image placeholders. Calls the built-in image-generation primitive on the Codex channel, falls back to omd-asset-curator on the Claude Code channel, and dumps the spec on OpenCode. Uses `<!-- omd:gen-image -->` blocks in HTML/MD as the single source of truth. Triggered by phra
Ready to connect★ 503
- View details
omd:designSkillMedia
Legacy survey-based DESIGN.md writer redirect. Use for old omd:design requests only to route them to the Core v2 Autopilot or init workflow; this compatibility skill never writes DESIGN.md itself.
Ready to connect★ 503
- View details
omd:designer-reviewSkillMedia
Visual + brand consistency review. Takes HTML/MD/JSX artifacts and audits typography hierarchy, color budget, radius scale, component states, and mobile responsiveness against brand DESIGN.md. Outputs severity BLOCK/WARN/FYI + line refs. Triggered by phrases like 'UI review', 'design review', 'audit
Ready to connect★ 503
- View details
omd:experiment-gallerySkillMedia
Generates a gallery index.html for comparing N brand experiments on one screen. Each card includes brand name, wow rating, multi-turn refinement deltas, an iframe scaled preview, and a standalone link. Triggered by requests like 'show me all results at once', 'make a gallery', 'a 5-item comparison v
Ready to connect★ 503
- View details
omd:feelSkillMedia
Applies (APPLY) or audits (AUDIT) interface details that design/front-end practitioners relied on 'feel' for, as quantified rules. Inheriting Jakub Krehel's make-interfaces-feel-better philosophy + extended with HIG/Material/WCAG/DS tokens/practitioner research: 17 axes, 113 rules (by provenance gra
Ready to connect★ 503
- View details
omd:final-qaSkillMedia
Read-only critic for the final pre-publication stage. Enforces an 8-item rubric. Rubber-stamping with 'looks good' is forbidden. Line references required. Hard cap of 2 revision rounds. Triggers: 'final QA', 'publication review', 'evaluate with the rubric' and similar phrases.
Ready to connect★ 503
- View details
omd:initSkillMedia
Bootstrap DESIGN.md at the project root — recommends references from real company examples via context matching and generates variations preserving the selected reference's tone & manner. Triggers on UI work when DESIGN.md is absent, or requests like '디자인 시스템 세팅', 'set up our design system', 「デザインシス
Ready to connect★ 503
- View details
omd:kr-writerSkillMedia
Korean writing multi-preset skill. Supports 12 presets — toss-tech-design (default) / karrot-neighborly / brunch-maker-popular / naver-d2-engineering / biz-formal-report / academic-paper / journalism-broadsheet / kakao-warm-product / line-global-saas / academic-lecture-essay / emotional-brand / lega
Ready to connect★ 503
- View details
omd:learnSkillMedia
Merges status:pending entries from .omd/preferences.md into the Core v2 System Graph, regenerates DESIGN.md, and flips the status to applied. Triggered by requests like '프리퍼런스 정리해줘', 'fold preferences', 'apply all corrections', 「好みをDESIGN.mdに反映」, or 「套用偏好」. For one-off correction records, use omd:re
Ready to connect★ 503
- View details
omd:locale-adapterSkillMedia
Adapts Korean canonical docs and UX copy for EN/JA/ZH-CN/ZH-TW — not translation, but locale adaptation. Preserves thesis, facts, and commands while rewriting sentence order, subjects, register, product terminology, and tone for each language. Use for requests like 'multi-language support', 'EN/JA/s
Ready to connect★ 503
- View details
omd:migrateSkillMedia
Legacy deep-reference writer safety gate. Use for old brand migration requests only to prevent retired section/frontmatter writes until the Core v2 catalog migration pipeline is authoritative.
Ready to connect★ 503
- View details
omd:tasteSkillMedia
Renders the design taste the system has learned about the user in a single view. Reads .omd/preferences.md + foldin-proposal.json + DESIGN.md and shows four groups: reflected / pending / on hold / unknown. Triggered by utterances like '/omd-taste', 'show my taste', 'what are my preferences'. History
Ready to connect★ 503
- View details
approve-architectureSkillMedia
Record per-PR architecture-review approval for design-artifact PRs (required by the architecture gate). ONLY on an explicit per-PR architect "approved".
Ready to connect★ 501
- View details
approve-designSkillMedia
Record per-PR design-review approval (UI merge gate). ONLY on an explicit per-PR designer "approved".
Ready to connect★ 501
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.