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
817864 · page 18 / 49
monitoring-and-alertingDesign and run a monitoring system for a website or web app. Use this skill when setting up uptime checks, defining SLOs…rampstackcomonoMonospace-driven, matrix-inspired design with high-contrast elements, compact density, and a hacker-chic aesthetic.bergsidemulti-agent-patternsThis skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm…majiayu000multi-tenant-llm-hostingDesign secure, multi-tenant LLM hosting platforms with tenant isolation, quotas, billing attribution, noisy-neighbor protection…majiayu000nano-banana-promptsGenerate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art…majiayu000bio-workflows-neoantigen-pipelineEnd-to-end neoantigen discovery from somatic variants to ranked vaccine candidates. Integrates HLA typing, MHC binding…majiayu000network-designWhen the user wants to design or optimize a supply chain network, determine facility locations, or configure distribution…majiayu000neuheit-pruefenPrueft Neuheit nach § 3 PatG und Art. 54 EPUe. Methodisches Schema: ein Anspruch wird in seine Merkmale zerlegt und…majiayu000nexus-mapperGenerate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture…majiayu000noir-styleNoir art direction for Blender with high-contrast lighting, wet streets, silhouettes, and monochrome or limited-color grading.arjun988nw-ai-workflow-tutorialsAI workflow tutorial patterns — non-deterministic output handling, outcome-based verification, and agent workflow step designmajiayu000nw-design-patterns7 agentic design patterns with decision tree for choosing the right pattern for each agent typemajiayu000nw-forgeCreates new specialized agents using the 5-phase workflow (ANALYZE > DESIGN > CREATE > VALIDATE > REFINE). Use when building a…majiayu000nw-investigation-techniquesEvidence collection methods, problem categorization, analysis techniques, and solution design patternsmajiayu000observability-monitoring-slo-implementYou are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget-based…sickn33obsidian-experiment-logUse this skill when the user discusses experiment design, ablations, training runs, evaluation, baselines, metrics, failures, or…majiayu000obsidian-reference-architectureImplement Obsidian reference architecture with best-practice project layout. Use when designing new plugins, reviewing project…jeremylongshoreOBT Design OptimizerDesigns and optimizes One Big Table (OBT) patternsa5c-aiwritesod-plugin-authoringGuided scenario for creating an Open Design plugin folder that can be installed into My plugins.nexu-iood-plugin-contribute-open-designOpen a pull request adding a local Open Design plugin to the Open Design community catalog using gh CLI.nexu-iood-plugin-publish-githubPublish a local Open Design plugin to a new public GitHub repository using gh CLI.nexu-iood-share-to-communityPackage the user's just-finished work as an Open Design plugin without asking for fields the project files already answer, then…nexu-iood-web-effect-extractorExtract visual effects, animation systems, Canvas/WebGL/Shader behavior, and interaction details from a reference website, then…nexu-iooma-brainstormDesign-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for…first-flukeonboardGenerates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state…majiayu000writescog-onboardingPersonalize COG Second Brain workflow through role pack selection and vault initializationa5c-aionboardingWhen the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when…growthack88ontology-whyOntology Integrity Design Rationale Helper. Explains "why" decisions with 5 Integrity perspectives (Immutability, Determinism…majiayu000optimization-modelingWhen the user wants to build optimization models, solve mathematical programming problems, or find optimal solutions. Also use…majiayu000orcaflex-extreme-analysisExtract extreme response values with linked statistics from OrcaFlex simulations. Use for design load identification, max/min…majiayu000orcaflex-results-comparisonCompare results across multiple OrcaFlex simulations for design verification, sensitivity studies, and configuration comparison.…majiayu000ordered-localeOrdered Locales (Heunen-van der Schaaf 2024): Point-free topology with direction. Frame + compatible preorder with open cone…majiayu000decision-graphUse when building a deciduous decision graph to capture design evolution, architecture history, or how a codebase's design…majiayu000decision-graphUse when building a deciduous decision graph to capture design evolution, architecture history, or how a codebase's design…majiayu000package-agentGenerate a complete OAF-compliant agent package from an Agent Case (requirements) and Agent Design (architecture). Use when asked…majiayu000pacmanRetro arcade-inspired design with pixel fonts, dotted borders, playful high-contrast colors, and 8-bit game aesthetics.bergsidepaperPaper-textured, print-inspired design with minimal colors, clean serif/sans typography, and tactile surface qualities.bergsideparallel-patternsGPU parallel algorithm design patterns and implementations. Implement parallel reduction, scan/prefix sum, histogram, parallel…a5c-aiwritesparameter-optimizationExplore and optimize simulation parameters via design of experiments (DOE), sensitivity analysis, and optimizer selection. Use…majiayu000writespatent-novelty-checkAssess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\"…majiayu000writespatent-novelty-checkAssess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\"…majiayu000writesPattern ExtractionDetect and extract patterns from codebases for template generationmajiayu000patternsDesign patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.majiayu000pdcaCreate Chinese monospaced compass-style PDCA or CAPD problem-solving cards using East-West-South-North-Center layout, full-width…twhsiperformance-optimizationFind and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget…gamedev-skillsperplexity-reference-architectureImplement Perplexity reference architecture with model routing, citation pipeline, and research automation. Use when designing…jeremylongshorepersona-templateGenerate user persona documents and empathy maps from templatesa5c-aiwritesperspectiveSpatial depth design with isometric views, vanishing points, and layered elements that guide attention through 3D-like realism.bergside
← Prev18 / 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