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
769816 · page 17 / 447
domain-expired-opportunity-finderEvaluates expired domain candidates against a target niche, scores them by topical relevance, historical activity level, and…Varnan-Techfeature-flaggingOperational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy…rampstackcofiscal-briefingPublic finances briefing. Supports UK, US, and Australia. Produces a single compact briefing on borrowing, debt, receipts…brycewang-stanfordwritesgolang-dependency-managementDependency management strategies for Golang projects — go.mod management, installing/upgrading packages, Minimal Version…samberwritesgrowth-engineeringEngineer growth loops. Use when: building referral programs, viral loops, or product-led growth strategy.indranilbanerjeehsb-ip-create-topCreate or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or…NVIDIAhsb-ip-packetizerChoose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB…NVIDIAjetson-customize-mgbeEnable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.NVIDIAjetson-customize-uphyConfigure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.NVIDIAjetson-flash-imageUse to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4t_initrd_flash.sh. Do NOT use for BSP…NVIDIAjetson-promote-imageUse to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp…NVIDIAjuristiSuomalaisen oikeuden ja lakikielen yleisapuri. Käytä tätä skilliä AINA kun käyttäjä työskentelee lakien, pykälien, säädösten…akunikkolalainvalmistelun-prosessiopasOpas lainsäädännön valmisteluprosessista Suomessa. Sisältää kaikki vaiheet aloitteesta lain saattamiseen voimaan, mukaan lukien…akunikkolanetwork-scanScan your LinkedIn contacts' companies for matching job openingsInfrasity-Labs案件材料生成专业文档根据案件材料或沟通记录生成各类法律服务文档(诉讼方案、咨询报告、非诉方案、建议书、沟通报告等)。本技能应在用户需要将案件材料、咨询记录或沟通内容整理为专业法律文档时使用。pa1nrui1初步法律分析基于"六来源体系"、请求权基础6步法与要件审判九步法融合框架,进行系统性法律分析,按总控当前事项记录和复盘台账衔接,生成法律服务建议书Word文档。当用户发送客户编号并提及"初步法律分析"、"法律分析"、"请求权分析"等指令时触发使用。pa1nrui1pennylaneHardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building…K-Dense-AIwritespennylaneHardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building…LeonChaoXportfolio-optimizationUse when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP…NVIDIAresearch-proposalUse when the user has a research proposal (problem + proposed methodology + planned experiments) and wants it iteratively…gaasherself-media-platform-copywriting将已确认的母题、证据和创作简报写成平台原生内容。用于 X 短帖、长帖或线程,小红书图文,微信公众号文章,视频号或抖音发布文案,以及同一母题的多平台适配。强调各平台独立设计标题、开头、证据顺序、结构和行动,不做机械缩写或共享正文式的一稿多发。yanhua1010sentry-policy-guardrailsEnforce organizational governance and policy guardrails for Sentry usage. Use when standardizing Sentry configuration across…jeremylongshorewritesSpatial Omics Skills IndexSkills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and…BioTender-maxtao-generate-image-groundingTwo-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space…NVIDIAwritestao-generate-referring-expressionsFour-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene…NVIDIAwritesusmlePrepare for US medical licensing exams with progress tracking, weak area analysis, question bank management, and residency match…BioTender-maxutility-mermaid-diagramsTeaches PMs to create syntactically valid mermaid diagrams by selecting the right diagram type for their communication need…product-on-purposeandroid-devProduction-grade Android app development guide covering native (Kotlin/Java), cross-platform (Flutter, RN, KMM), and hybrid…sickn33applyFill out a job application on Greenhouse, Lever, or WorkdayInfrasity-Labsbuilding-architecture-modelsCommon steps for building multi-layer system architecture models using System Composer. Use when implementing architecture models…matlabcitecheckUse when the user asks to "verify citations", "check references", "validate paper citations", or "evaluate reference relevance".…color4-altcontinuous-discoveryBuild a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and interview snapshots. Use…wondelaicpp-proWrite idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and…sickn33croOptimize conversion rates. Use when: auditing landing pages, testing forms, or improving checkout flow.indranilbanerjeecursor-rules-configConfigure Cursor project rules using .cursor/rules/*.mdc files and legacy .cursorrules. Triggers on "cursorrules"…jeremylongshorewritesdangnianmingyue-perspective当年明月历史通俗写作思维——幽默风趣、现代视角、心灵历史、权力与人性。 触发词:「当年明月视角」「像当年明月那样写」「明朝那些事儿」「历史通俗化」。 擅长:历史通俗写作、幽默叙事、人物心理分析、权力斗争描写、现代语言解构历史。momozi1996datadog-cliDatadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production…softaworksdatamolPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES…FreedomIntelligencedatamolPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including…LeonChaoXdeliver-release-notesCreates user-facing release notes that communicate new features, improvements, and fixes in clear, benefit-focused language. Use…product-on-purposedigital-health-clinical-asr-finetuneStage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline…NVIDIAdimensional-analysisAnnotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Use when someone asks…trailofbitswriteserror-monitoringGenerates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics). Use when user wants to add crash…rshankraswritesfilesystemAdvanced filesystem operations - listing, searching, batch processing, and directory analysis for ClawdbotopensquillafluidsimFramework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including…BioTender-maxfluidsimFramework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including…foryourhealth111-pixelfluidsimFramework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including…LeonChaoXflutter-expertUse when building cross-platform applications with Flutter 3+ and Dart. Invoke for widget development, Riverpod/Bloc state…Jeffallan
← Prev17 / 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