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
913960 · page 20 / 49
requirement-convergenceSeparates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands…shinprresearch-and-compareResearch and compare the Stateless Agent Methodology (SAM) against other methodologies using only verifiable reference material.…majiayu000research-architect-designUse when a Research Architect candidate research spine and approved exemplar adaptation need to become a feasible…mmTheBestvibe-research-before-designDispatches SOTA research before proposing any new feature, architecture, or technology choice. Use when facing design decisions…majiayu000research-brief-skillLightweight source-backed research and synthesis for normal Reviva agents. Use when the user asks to summarize materials, compare…mingchen666researchSystematic technical and scientific research for algorithms, papers, libraries, and implementation strategies. Use when…majiayu000research-methodologyStructured research using sophisticated query design, source vetting, and synthesis techniques. Use when conducting competitive…majiayu000research-patternsResearch methodology and best practices for finding existing patternsmajiayu000research-proposal-generatorGenerates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and…majiayu000research"Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a…testdoubleQualitative Research-Through-DesignApply research-through-design (RtD) methodology to investigate wellbeing in design contexts. Use when conducting user research…majiayu000responsive-imageGenerate responsive image sets with srcset, WebP/AVIF conversion, and art directiona5c-aiwritesretro-16bit-styleRetro 16-bit art direction for Blender-assisted SNES/Genesis-era color richness, dither cues, and sprite-like clarity.arjun988retro-8bit-styleRetro 8-bit art direction for Blender-assisted pixel/low-res aesthetics inspired by NES-era constraints.arjun988retroThrowback design with vintage-inspired typography, high-contrast retro palettes, and nostalgic visual elements.bergsideRL Circuit Parameter TuningDesign and implement reinforcement learning environments to tune bounded circuit parameters, featuring a sophisticated reward…majiayu000Safety System SkillRobot safety system design and validation for industrial and collaborative robotsa5c-aiwritessatellitetoolbox-celestialbodiesSatelliteToolboxCelestialBodies.jl for computing Sun and Moon positions and velocities in the MOD frame. Use when computing…majiayu000biomniAutonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology…majiayu000stable-baselines3Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating…majiayu000scikit-learn-specialistMaster scikit-learn machine learning patterns including pipeline design, cross-validation, hyperparameter tuning, feature…majiayu000scope-permission-designerDesign and implement scoped permission modelsa5c-aiwritesscout-reposFetch .claude/ configs from curated repos in sources.yml, compare against dotforge template, report novel patterns.majiayu000self-improve-prompt-designWrite self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent…majiayu000writessenior-prompt-engineerThis skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build…majiayu000senior-prompt-engineerThis skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build…majiayu000sentence-transformersFramework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity…Orchestra-Researchsequential-thinkingUse when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative…majiayu000sequential-thinkingSystematic step-by-step reasoning with revision and branching. Use for complex problems, multi-stage analysis, design planning…majiayu000serializationExpert skill for binary and text serialization formats, schema design, and optimizationa5c-aiwritesshare-github-prUse this plugin when the user wants to package an accepted plugin or artifact as a GitHub pull request for Open Design or another…nexu-iosignal-processing-dsp-basicsFoundations of digital signal processing — sampling, aliasing, the Nyquist criterion, quantization, convolution, the discrete…majiayu000simulation-architectDesign and implementation of comprehensive simulation studiesbrycewang-stanfordsimulator-effectImplication beats simulation — imagination renders (Will Wright)majiayu000skill-model-checkerResearch and develop semantic theories using ModelChecker with Z3 SMT solver. Define operators, adjust frame constraints, create…majiayu000writessleekModern minimalist aesthetic with clean lines, intentional color palette, subtle interactions, and consistent spacing.bergsideslo-designerDesign Service Level Objectives (SLOs) with SLIs, targets, alerting thresholds, and error budget calculations following Google…majiayu000high-end-visual-designTeaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that…nexu-iosolublempnnSolubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2)…majiayu000sparringUse when the user has a proposal, position, or design and wants it adversarially pressure-tested before committing.majiayu000spatial-transcriptomics-tutorials-with-omicverseGuide users through omicverse's spatial transcriptomics tutorials covering preprocessing, deconvolution, and downstream modelling…FreedomIntelligenceSSA/IR DesignExpert skill for designing intermediate representations and implementing SSA constructiona5c-aiwritesstable-baselines3Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating…majiayu000talk-stage1-extractStage 1 — Extract and structure source material into a talk summary. Auto-detects REX vs Concept type.majiayu000writesstatistical-analysisHypothesis testing, power analysis, ablation design, and multiple comparison corrections for ML experiment evaluation.majiayu000stencil-convolutionExpert skill for optimized stencil and convolution pattern implementations on GPU. Design tiled stencil algorithms with halos…a5c-aiwritessurge-activationUse when asked to improve activation, map the growth funnel, identify growth levers, design a referral program, build a retention…jeremylongshorewritessurge-landingUse when asked to design growth-optimized landing pages, activation funnel layouts, or experiment-friendly page structures.…jeremylongshorewrites
← Prev20 / 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