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 149 of 176
- View details
oma-architectureSkillMedia
Architecture specialist for software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis. Uses context-aware methods such as diagnostic routing, design-twice comparison, ATAM-style risk analysis, CBAM-style prioritization, and ADR-style decision records.
Ready to connect
- View details
oma-brainstormSkillMedia
Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for brainstorming, ideation, exploring concepts, and evaluating approaches.
Ready to connect
- View details
oma-frontendSkillMedia
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.
Ready to connect
- View details
ost-renderSkillMedia
Render `.claude/canvas/opportunities.yml` as a diagram or structured list. Read-only. Default format Mermaid mindmap. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` consent + privacy gate. Second specialist in the render fleet.
Ready to connect
- View details
p0-needs-orchestratorSkillMedia
Requirements discovery orchestrator. Coordinates six tool cards — micro-need detection, real-need validation, requirement breakdown, requirement archaeology, good question generation, and Agent boundary design — executing them in sequence and producing a complete requirements discovery report.
Ready to connect
- View details
p0h-ai-product-triple-balanceSkillMedia
AI Product Triple Balance Sheet. AI product design needs to strike a balance across three dimensions: business, humanity, and technology. This Skill provides a systematic triple-balance evaluation framework. Based on "AI
Ready to connect
- View details
p12a-contemplation-right-speechSkillMedia
Make your words true instead of making problems sound smooth — language de-greenwashing, minutes health check, honest expression practice
Ready to connect
- View details
p13c-product-psychologySkillMedia
Product psychology — user mental models, behavior design, motivation analysis
Ready to connect
- View details
p2c-process-redesignSkillMedia
A hands-on Skill for the AI-native product methodology — process restructuring and task design.
Ready to connect
- View details
p6a-certainty-premium-calculatorSkillMedia
Certainty premium calculator. Based on the core formula from 'The AI Certainty Business Model', it helps product teams calculate the certainty premium of AI products to design higher-value pricing models.
Ready to connect
- View details
p7d-marketing-productizerSkillMedia
Marketing productization designer. Based on the marketing productization concept card from 'AI Native Marketing and Growth', it helps products design marketing campaigns as product features, so users naturally complete 'being marketed to' during use.
Ready to connect
- View details
p8c-progressive-disclosureSkillMedia
Progressive disclosure checklist. Based on the progressive disclosure theory from 'User Experience in the AI Era', provides a design checklist for AI products to gradually reveal features and capabilities, avoiding delivering too much information to users at once.
Ready to connect
- View details
privacy-checkSkillMedia
Use to assess Privacy by Design compliance and GDPR/data protection alignment for a feature or system.
Ready to connect
- View details
receipt-renderSkillMedia
Render a completed diamond's work as a shareable, factual one-page "work receipt" (problem framed, assumptions tested, what was killed vs kept) carrying an origin line + a volitional onward-handoff data flow. Read-only. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conve
Ready to connect
- View details
renderSkillMedia
Central dispatcher for the canvas/state render fleet. Routes intent to a specialist (`/mycelium:diamond-render`, `/mycelium:ost-render`, `/mycelium:cycle-render`) OR lists what's renderable. Cross-cutting views spanning multiple canvases (opp→sol→cycle traceability, confidence-over-time, cluster-gra
Ready to connect
- View details
roblox-audioSkillMedia
Use when implementing Roblox audio playback, spatial sound, music, sound effects, SoundGroups, or dynamic audio effects.
Ready to connect
- View details
roblox-growth-designSkillMedia
Use for growth diagnosis, discovery, retention, onboarding, experiments, LiveOps, and packaging.
Ready to connect
- View details
roblox-ui-designSkillMedia
Use for Roblox UI composition, hierarchy, visual systems, style inheritance, accessibility, and design review.
Ready to connect
- View details
spec-brainstormSkillMedia
Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codebase research and arc
Ready to connect
- View details
spec-implementSkillMedia
Continue an approved Spec-backed workflow when the user says "implement", "go", "start", or "do it". After Codex Plan Mode, persist the next missing design.md or plan.json artifact and stop. When both artifacts exist, execute plan.json with TDD and report between batches.
Ready to connect
- View details
spec-planSkillMedia
Write approved implementation plans in one of two modes. Explicit Inline mode creates a conversational plan for bounded work. Spec-backed Plan converts an approved design.md into plan.json. Both modes stop after producing their plan output. Trigger after atelier-orchestrator selects a mode, when the
Ready to connect
- View details
adhdSkillMedia
Parallel divergent ideation, framed generators, then a critic scores, clusters, and deepens the top 3. Triggers "brainstorm", "ideate", "widen the option space", or a fuzzy design or debugging question. Not for lookups or bugs with a known cause.
Ready to connect
- View details
audit-frontend-designSkillMedia
Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility, hierarchy, tokens, states, and responsive design before editing code.
Ready to connect
- View details
build-swiftui-interfaceSkillMedia
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
Ready to connect
- View details
design-system-referenceSkillMedia
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
Ready to connect
- View details
handdrawn-diagramSkillMedia
Generate a hand-drawn (sketch-style) architecture or flow diagram as a committable image (SVG + PNG). Use when the user wants a sketch-aesthetic diagram for a README, docs, or hackathon/Devpost submission that still has correct, legible text and per-group color. Authors a Mermaid look:handDrawn sour
Ready to connect
- View details
ios-ettrace-profilerSkillMedia
iOS ETTrace Simulator profiles: capture and interpret symbolicated startup, scrolling, navigation, rendering, CPU hotspots, and before/after evidence.
Ready to connect
- View details
ios-intents-architectSkillMedia
Design and implement iOS App Intents, AppEntity, EntityQuery, and App Shortcuts for Siri, Spotlight, widgets, controls, Shortcuts, and app handoff routes.
Ready to connect
- View details
remember-design-systemSkillMedia
Use when an agent is about to build or refactor interface code and needs a compact, repository-specific brief covering existing tokens, components, routes, conventions, and verification commands.
Ready to connect
- View details
to-specSkillMedia
Turn the current conversation into a design spec for a task and write it to .agents/tasks/<slug>/DESIGN.md — no interview, just synthesis of what's already been discussed. Invoke only when the user explicitly runs /to-spec.
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.
54,249 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.