Agent skills

Other 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
21,420 found
673720 · page 15 / 447
spring-boot-testingExpert Spring Boot 4 testing specialist that selects the best Spring Boot testing techniques for your situation with Junit 6 and…githubbio-binning-qcPerform metagenomic binning with QuickBin, refinement, and QC with completeness/contamination checks.BioTender-maxcrossframe-dialogueUse when CrossFrame Suite routes explicit Chinese reader replies, editor responses, consultation-style short answers, or…sickn33jungian-psychologistExpert in Jungian analytical psychology, depth psychology, shadow work, archetypal analysis, dream interpretation, active…FreedomIntelligencewritesmatlab-modernize-codeModernize deprecated MATLAB functions and patterns. Use when check_matlab_code or checkcode reports "not recommended" or "to be…matlab调查取证与证据管理基于请求权要件分析进行证据缺口评估,系统化指引证据收集、调查取证、证人管理和财产保全全流程,生成取证方案、各类申请文书和调查笔录。当用户发送客户编号并提及"调查取证"、"证据收集"、"财产保全"、"调查令"、"证人出庭"、"补充材料"、"取证方案"等指令时触发…pa1nrui1running-causalpy-experimentsFit, summarize, plot, and interpret a chosen CausalPy experiment. Use after the causal method has been selected, including when…brycewang-stanfordSC Best Practices Skills IndexSkills derived from the Single-cell Best Practices book (sc-best-practices.org). Comprehensive workflows and guidelines for…BioTender-maxtemplatesProject scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for…sickn33bio-gene-callingCall genes and annotate basic features for prokaryotes, viruses, and eukaryotes.BioTender-maxCTF•杂项用于编码题、pyjail、bash jail、RF/SDR、DNS 异常、Unicode、奇特语言、QR、音频、约束求解、博弈论与沙箱逃逸等跨类或边缘 CTF 题;触发名:ctf-miscasdfgh1445writesmodalModal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML…K-Dense-AImodalRun Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch…LeonChaoXmodular-decompositionRuns a sequenced monolith-to-modular pipeline that sizes and inventories components, finds shared domain duplication, addresses…tech-leads-clubdaaf-orchestratorOperational framework for the DAAF orchestrator. Defines engagement modes, confirmation protocol, subagent dispatch, context…brycewang-stanforddeveloping-genkit-dartUse when building AI agents in Dart, implementing Genkit flows or tools, integrating LLMs into Dart or Flutter applications, or…evancadotnet-maui-doctorDiagnoses and fixes .NET MAUI development environment issues. Validates .NET SDK, workloads, Java JDK, Android SDK, Xcode, and…dotnetbio-protein-clustering-pangenomeCluster proteins into orthogroups and derive pangenome matrices.BioTender-maxbio-structure-annotationStructure prediction and structure-based annotation.BioTender-maxcomposition-patternsUse when working with composition-patterns tasks or workflowssickn33crossframe-teachUse when CrossFrame Suite routes explicit Chinese teaching of CrossFrame concepts, misreading boundaries, plain-language…sickn33eccc-jeanne-sulzerVerification-first methodology for the ECCC (Khmer Rouge Tribunal). Every citation is verified against eccc.gov.kh, the ECCC…lawve-aijetson-customize-cameraEnable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor…NVIDIAjetson-customize-usbEnable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.NVIDIAlamina-product-behaviorDefine authoritative runtime product truth across actors and views. Use when modeling domain behavior, setting product density…aryaniyapslatex-to-quartoConverts LaTeX article-class .tex documents to Quarto .qmd format for multi-format publishing (HTML, PDF, Word). Use when asked…brycewang-stanfordlitigacion-latam-joselyne-garcia-montesdeocaAsesor experto en litigación bajo sistemas de derecho civil (civil law) en América Latina. Asiste a abogados litigantes, equipos…lawve-ainemotron-retrieval-recipesUse when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.NVIDIAnuremberg-tokyo-jeanne-sulzerVerification-first methodology for the post-WWII tribunals: the IMT at Nuremberg, the twelve Nuremberg Military Tribunals, and…lawve-aiopenrouter-performance-tuningOptimize OpenRouter request latency and throughput. Use when building real-time applications, reducing TTFT, or scaling request…jeremylongshorewritestilegym-improve-cutile-kernel-perfIteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted…NVIDIAtooluniverse-drug-researchGenerates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness…BioTender-maxapple-intelligenceApple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and…rshankraswritesbinding-approvals-to-actionsUse when an irreversible, high-risk, scope-changing, or trust-changing operation requires a human decision that cannot be…casioreview20-glitchbio-annotationFunctional annotation and taxonomy inference from sequence homology.BioTender-maxbio-stats-ml-reportingAggregate results, train ML models, and produce reports with validated references.BioTender-maxcps-rca-central-african-republic-jeanne-sulzerMéthodologie « verification-first » pour la Cour Pénale Spéciale de Centrafrique (cour hybride, siège à Bangui). Toute citation…lawve-aicliLobeHub CLI (@lobehub/cli) development guide — commands, subcommands, architecture.lobehubcontroleur-fiscalInspecteur des finances publiques IA. Simule un contrôle fiscal DGFIP complet sur les comptes d'une entreprise française (SASU…romainsimonspecial-panels-timor-leste-jeanne-sulzer-2Verification-first methodology for Section I (War Crimes) of the Court of Bosnia and Herzegovina. Citations are verified against…lawve-aideepspeedExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit…Orchestra-Researchquick-calculatorQuickly produces accurate calculation results when a user needs arithmetic, unit conversion, or mathematical formula solving.…alibabaeac-habre-jeanne-sulzerMéthodologie « verification-first » pour les Chambres Africaines Extraordinaires (procès Hissène Habré, Dakar). Toute citation…lawve-aihig-components-systemApple HIG guidance for system experience components: widgets, live activities, notifications, complications, home screen quick…sickn33icty-ictr-irmct-jeanne-sulzerVerification-first methodology for the ICTY, the ICTR and the Residual Mechanism (IRMCT). Citations are verified against…lawve-aiinteractive-product-tourDesigning in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger…rampstackcoinvalidating-dependent-proofUse when a semantic change, artifact supersession, provider substitution, policy change, or source revision makes previously…casioreview20-glitchjetson-build-sourceUse when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp…NVIDIA
← Prev15 / 447Next →
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