Agent skills

Design & Presentation skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,329 found
865912 · page 19 / 49
pixel-art-stylePixel-art and texel-constrained art direction for Blender assets destined for pixel rendering, low-res textures, or…arjun988plan-mode-advancedCreate and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques…majiayu000planning-designDesign technical architecture, select technology stack, and define implementation strategy from specifications and constitution…a5c-aiwritesplantuml-rendererRender PlantUML diagrams to various image formats with theme and styling supporta5c-aiwritespower-analysisFPGA power estimation and optimization skill for low-power designa5c-aiwritesbio-experimental-design-power-analysisCalculates statistical power and minimum sample sizes for RNA-seq, ATAC-seq, and other sequencing experiments. Use when planning…majiayu000ppt-creationCreate polished presentations from notes, documents, research, or rough requirements. Plans slide structure, reduces text…mingchen666pptx-deck-contextUse when preparing the narrative, sources, and design context for a new editable PPTX deck.wshobsonpptx-slide-specificationUse when authoring or repairing a coordinate-explicit JSON specification for an editable PPTX deck.wshobsonpptx-visual-assetsUse when selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics in an editable PPTX deck.wshobsonpractice-cognition触发:当你提出了方案、假设或判断,需要通过实践验证、试错迭代或复盘升级认知时调用;常见信号包括 experiment、prototype、validate、iterate、feedback loop。HughYaupresenting-conference-talksGenerates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk…Orchestra-Researchprior-artDiscover how a codebase already handles a specific concern — search broadly, find every instance, and assess consistency. The…majiayu000prior-art-searchSearch patent databases and academic literature for prior art relevant to an invention. Use when user says \"现有技术检索\", \"prior…majiayu000writesproblem-framing-canvasGuide teams through MITRE's Problem Framing Canvas. Use when you need a clearer problem statement before jumping to solutions.majiayu000professionalPolished, business-ready design with modern typography, structured layouts, and a trustworthy visual identity.bergsideproject-analysisA specialist skill that analyses a codebase to understand its structure, dependencies, and architecture. This skill should be…majiayu000writesproject-analyzeMulti-phase iterative project analysis with Mermaid diagrams. Generates architecture reports, design reports, method analysis…majiayu000writesproject-analyzeMulti-phase iterative project analysis with Mermaid diagrams. Generates architecture reports, design reports, method analysis…majiayu000writesproject-developmentDesign and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between…majiayu000prompt-engineerExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output…majiayu000prompt-engineerExpert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or…majiayu000writesprompt-engineerExpert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters…majiayu000prompt-engineeringUse this skill when crafting LLM prompts, implementing chain-of-thought reasoning, designing few-shot examples, building RAG…majiayu000Prompt EngineeringComprehensive guide for LLM prompt engineering techniques and best practices. Prompt engineering is the art and science of…majiayu000prompt-engineering-expertAdvanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agentsmajiayu000prompt-optimizer> Prompt verimliliğini artırma ve token maliyeti düşürme metodolojisi.majiayu000prompt-section-designDesign composable prompt sections for building agentic prompts. Use when creating reusable prompt components, designing…majiayu000prompt-template-designStructured prompt template creation with variables, formatting, and version controla5c-aiwritesprompt-template-designerDesign reusable prompt templates that encode domain-specific patterns for recurring AI tasks. Use when you've executed similar…majiayu000prompt-template-designerDesign reusable prompt templates that encode domain-specific patterns for recurring AI tasks. Use when you've executed similar…majiayu000PromptingMeta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template…majiayu000PromptingMeta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template…majiayu000PromptingMeta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template…majiayu000PromptingMeta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template…majiayu000proteinmpnnDesign protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion…FreedomIntelligenceprotocol-parserSpecialized skill for binary and text protocol parsing and serialization. Design and validate protocol message formats, generate…a5c-aiwritesprototype-interactionDefine and document prototype interactions, transitions, and hotspotsa5c-aiwritespymooMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ)…majiayu000pymooMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ)…majiayu000pymooMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ)…majiayu000writesquick-win-sessionGenerates guided first-action flows that help users achieve a meaningful result within 60 seconds to boost retention. Use when…rshankraswritesrag-architectUse when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search…majiayu000rag-designProduction-grade RAG (Retrieval-Augmented Generation) system design patterns from OpenClaw. Use when implementing semantic…majiayu000rate-limiter-designerDesign and implement rate limiting strategiesa5c-aiwritesreactor-sub-agent專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構,生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。majiayu000community-registry-starterA small community registry starter plugin used to verify Open Design marketplace install flows.nexu-iorekisteroidyn-pyynnotRekisteröidyn oikeuksien toteuttaminen ja tietopyyntöihin vastaaminen EU:n tietosuoja-asetuksen (15–22 art) mukaan…akunikkola
← Prev19 / 49Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going