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: AI & models
8,898 results · page 286 of 297
- View details
Brainstorming Ideas Into DesignsSkillAI & models
Interactive idea refinement using Socratic method to develop fully-formed designs
Ready to connect
- View details
campaign-copywritingSkillAI & models
Transforms a campaign strategy with an evidence ledger into traceable, distinct, channel-appropriate copy routes. Does not redo research or invent claims. Triggers on: "copy baseada na pesquisa", "copy baseada na pesquisa e mantenha as evidencias", "copy deck da campanha", "variações de anúncio".
Ready to connect
- View details
campaign-research-strategySkillAI & models
Researches market, competitors, audience and consumer voice to build a verifiable strategic foundation for a campaign before copy or visual direction. Produces an evidence ledger, authorized claims, prioritized opportunities and guardrails. Trigger words: "pesquisa de campanha", "base estratégica do
Ready to connect
- View details
campaign-visual-directionSkillAI & models
Converts approved strategy and copy into a visual concept, a Continuity Bible, and structured shot intents. Separates identity and language references and reserves text/UI for deterministic overlays. Triggered by: "direção visual da campanha", "bíblia de continuidade do anúncio", "shot intents", "
Ready to connect
- View details
Code Review ReceptionSkillAI & models
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation
Ready to connect
- View details
Collision-Zone ThinkingSkillAI & models
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"
Ready to connect
- View details
competitive-landscapeSkillAI & models
Lets your agent analyze competitors and draft market positioning strategies using structured frameworks.
Ready to connect
- View details
component-architectureSkillAI & models
Use when designing or changing a component's public API, its composition, or its state model in libs/ui-react or libs/ui-rnative — layering (core vs internal vs primitives), BaseProps/Props splits, converting a component to compound / changing its composition with createSafeContext, controlled/uncon
Ready to connect
- View details
content-growth-engineSkillAI & models
Content strategy skill as an acquisition engine for SaaS and B2B: build a content plan from scratch, prioritize topics by commercial intent, define cadence, decide whether to create vs. update content, internal linking, extract topics from sales objections, measure AI citation share and revenue. Tri
Ready to connect
- View details
context-doctorSkillAI & models
Diagnose and fix context window issues. Use when Claude seems confused, forgetful, slow, or the user says "context is full", "you forgot", "you're repeating yourself", "start fresh", or "why are you ignoring my instructions".
Ready to connect
- View details
critical-net-routerSkillAI & models
RAG-backed. Plan and optionally commit one bounded critical-net or differential-pair route in DipTrace with explicit rules and post-checks. Use when the user says “Route this explicitly named critical PCB net.”
Ready to connect
- View details
css-protipsSkillAI & models
Use when writing, reviewing, refactoring, or modernizing CSS/Tailwind. Apply a policy-first approach: semantic tokens, explicit cascade order, static CSS, intrinsic component layouts, accessible state, measured performance, and progressive enhancement backed by current sources.
Ready to connect
- View details
de-slopifySkillAI & models
Remove AI-writing tells from README, docs, and user-facing text. Must be done line-by-line, no regex. Use after agents write any user-visible prose.
Ready to connect
- View details
decision-mappingSkillAI & models
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Ready to connect
- View details
detective-specSkillAI & models
Reverse engineering of specs for legacy systems. Use when you need to extract executable specs, business rules, module contracts, flows, and retroactive ADRs from existing code that has no prior spec. Trigger words: "legado", "engenharia reversa", "extrair spec", "documentar codigo existente",
Ready to connect
- View details
Developing Internal HooksSkillAI & models
Create, configure, and develop custom automation hooks, slash commands, event hooks, and dynamic skills under internal-hooks/
Ready to connect
- View details
diptrace-board-bringupSkillAI & models
RAG-backed. Plan or guide first power-on, programming, measurements, functional acceptance, and repeatable production tests for a specific DipTrace board revision. Use for assembled boards, bring-up, fixture plans, or production test procedures; «первое включение», «проверка собранной платы». Use wh
Ready to connect
- View details
diptrace-bom-sourcingSkillAI & models
RAG-backed. Build and check a purchasable DipTrace BOM for a specified assembly variant and quantity, verify live stock, and assess substitutions. Use for BOM completeness, component sourcing, JLCPCB/LCSC selection, shortages, or procurement preparation; «подбери компоненты», «проверь BOM». Use when
Ready to connect
- View details
dramakeSkillAI & models
For Codex, Claude Code, WorkBuddy and other Agent Skills clients, turns a one-line idea, story synopsis, novel, copy, script, storyboard, or existing material into coherent, chainable, publishable AI short dramas and AI short films. Suitable for horizontal or vertical content on Douyin, Hongguan sho
Ready to connect
- View details
Executing PlansSkillAI & models
Execute detailed plans in batches with review checkpoints
Ready to connect
- View details
feature-gap-bottleneck-analysisSkillAI & models
Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps, performance/process bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.
Ready to connect
- View details
ferrox-fastSkillAI & models
A trivial change you could describe in one line. Runs inline, no subagents, no planning
Ready to connect
- View details
ferrox-map-codebaseSkillAI & models
You want to understand an unfamiliar codebase. Parallel agents write .planning/codebase/
Ready to connect
- View details
ferrox-reviewSkillAI & models
You want other AI models to critique a plan before you build it. Cross-AI peer review
Ready to connect
- View details
ferrox-settingsSkillAI & models
You want to change workflow toggles and which models Ferrox uses
Ready to connect
- View details
fresh-eyesSkillAI & models
Reset review context when bead polishing or code review has flatlined. Requires starting a brand-new Claude / Codex session. Use when you're seeing the same small edits round after round.
Ready to connect
- View details
frontend-integrationSkillAI & models
Frontend Developer skill for implementation with React/Next.js, Zustand, React Query, and Skeleton loading. Use when you need to implement components, pages, API integration, state management, or any frontend code. Triggers: "React", "Next.js", "component", "page", "Zustand
Ready to connect
- View details
game-engine-developmentSkillAI & models
Skill for real game engine code implementation — Unity C# and Unreal C++. Covers MonoBehaviour and ScriptableObject patterns, object pooling, state machines, ECS, Unreal Actor components/UPROPERTY/UFUNCTION, and performance optimization (profiling, batching, LOD, culling, garbage collection)
Ready to connect
- View details
geo-deep-learningSkillAI & models
Invoke before recommending, training, or auditing a neural method for geospatial imagery, including vision transformers, U-Net/DeepLab/SegFormer, object detection, pixel classification, building/road extraction, and EO foundation-model fine-tuning. Also invoke for neural chip-split validity, IoU/acc
Ready to connect
- View details
github-deep-researchSkillAI & models
Conduct in-depth research on a GitHub repository (README/structure/key source code/activity) and produce a research report. A pure prompt-based skill that relies on the web_fetch tool.
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.
53,789 of the 54,221 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.