Agent skills

Skills for codex

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
9,699 found
2,1132,160 · page 45 / 203
nnsight-remote-interpretabilityProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.…Orchestra-Researchobsidian-markdownCreate and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use…kepanoobsidian-markdownCreate and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use…sickn33okx-dapp-discoveryPlugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound…internet-courtoma-refactorBehavior-preserving refactoring specialist - plans and executes safe incremental restructuring with code smell / SATD / hotspot…first-flukeoma-scmSCM (software configuration management) and Git: branching, merges, conflicts, worktrees, baselines, audit readiness, plus…first-flukeorchestrate-batch-refactorPlan and execute large refactors with dependency-aware work packets and parallel analysis.sickn33outlinesGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models…Orchestra-Researchpaper-reading-zh中文论文精读、工程拆解、多论文比较、按图表讲解与证据审计。Use when the user provides a paper anchor(PDF、链接、标题、摘要/全文、图表或论文列表)并要求深读、复现分析、比较或证据核对。不用于纯翻译、单术语定义、仅…MrGeDiaoperforming-causal-analysisEstimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression…foryourhealth111-pixelprdGenerate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when…smallnestpricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,'…sickn33production-schedulingCodified expertise for production scheduling, job sequencing, line balancing, changeover optimisation, and bottleneck resolution…sickn33push-notificationsImplement, review, or debug push notifications in iOS/macOS apps — local notifications, remote (APNs) notifications, rich…dpearson2699pytorch-lightningHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and…Orchestra-Researchpyvene-interventionsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use…Orchestra-Researchquality-nonconformanceCodified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier…sickn33redpolitikaРедполитика проекта на русском языке: короткое интервью, извлечение голоса из примеров и файл `.agents/redpolitika.md` для…N1arkorelease-plannotatorPrepare and execute a Plannotator release — draft release notes with full contributor credit, bump versions across all package…backnotpropresearch-decision-roomTurn messy user research notes, interviews, support tickets, surveys, and product context into an evidence-backed decision room…nexu-ioara-research-managerRecords research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to…Orchestra-Researchreturns-reverse-logisticsCodified expertise for returns authorisation, receipt and inspection, disposition decisions, refund processing, fraud detection…sickn33roadrunner-build-scenario-from-oscBuild a RoadRunner Scenario programmatically from an OpenSCENARIO 1.x (.xosc) file using the `roadrunner-scenario-authoring`…matlabroadrunner-coreFoundation skill for all RoadRunner workflows: MATLAB path setup, connection, project/scene/scenario lifecycle, world settings…matlabroadrunner-scenario-simulatingExpert guidance for simulating RoadRunner scenarios via the MATLAB programmatic API and Simulink co-simulation. Use when the user…matlabrwkv-architectureRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN…Orchestra-Researchsparse-autoencoder-trainingProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations…Orchestra-ResearchseabornStatistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for…foryourhealth111-pixelsetup-bclSet up, build, debug, review, and explain BCL payment gateway, BCL Pay, BCL Payment Link, BCL QR Terminal, BCL Forms…afu-itsetup-billplzSet up, build, debug, review, and explain Billplz payment integrations using Billplz API docs, help center, GitHub plugins…afu-itsetup-chipSet up, build, debug, and explain CHIP Collect payment integrations using the official CHIP Collect API documentation. Use when…afu-itsetup-curlecSet up, build, debug, review, and explain Razorpay Curlec payment gateway integrations using Curlec and shared Razorpay…afu-itsetup-toyyibpaySet up, build, debug, review, and explain toyyibPay payment integrations using official toyyibPay API references, onboarding…afu-itsglangFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained…Orchestra-Researchsimpo-trainingSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on…Orchestra-Researchsimulink-single-precision-conversionConverts a double-precision Simulink system or subsystem to single precision using DataTypeWorkflow.Single (Fixed-Point…matlabskill-reviewUse when reviewing Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive…QoderAIsocial-contentWhen the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok…alirezarezvanisocial-media-matrix-tracker-template社媒矩阵数据追踪面板模板(Social Media Matrix Tracker)。 Use when users ask for a cinematic, data-dense social media analytics dashboard with…nexu-iostitch-ui-designExpert guidance for crafting effective prompts in Google Stitch, the AI-powered UI design tool by Google Labs. This skill helps…sickn33storekitImplement, review, or improve in-app purchases and subscriptions using StoreKit 2. Use when building paywalls with…dpearson2699subagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionforyourhealth111-pixelsubagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionGanyuanRansubagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionsickn33suede-content-strategySuede-owned content-strategy discipline for audience questions, content pillars, topic clusters, editorial priorities, cadence…JasonColapietrosuede-customer-researchSuede-owned customer-research discipline for interview design, transcript and ticket synthesis, review and forum mining, quote…JasonColapietrosuede-free-toolsSuede-affiliated engineering-as-marketing strategy for selecting, scoring, and scoping calculators, graders, generators, and…JasonColapietrosuede-imageSuede-affiliated marketing image production for generation prompts, hero and social graphics, product mockups, export sizing…JasonColapietro
← Prev45 / 203Next →
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