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
1,0571,104 · page 23 / 447
holoscan-install-sourceBuild Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.NVIDIAholoscan-install-wheelInstall Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.NVIDIAhrv-alexithymia-expertHeart rate variability biometrics and emotional awareness training. Expert in HRV analysis, interoception training, biofeedback…FreedomIntelligencewriteshuggingface-tokenizersFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE…Orchestra-Researchi4h-catheter-navigation-digital-twinBuild a patient vasculature digital twin from CT (preprocess + segment). Use when asked to preprocess CT, segment vessels…NVIDIAi4h-catheter-navigation-viewportLaunch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a…NVIDIAiterate-pivot-decisionDocuments a strategic pivot or persevere decision with the evidence, analysis, and rationale. Use when evaluating whether to…product-on-purposeiterate-refinement-notesDocuments backlog refinement session outcomes including stories refined, estimates, questions raised, and decisions made. Use…product-on-purposejetson-customize-fanUse when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin…NVIDIAjetson-customize-nvpmodelUse when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor)…NVIDIAjetson-derive-carrierBootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after…NVIDIAjetson-download-bspDownload NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target.…NVIDIAjetson-generate-kbBuild a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after…NVIDIAjetson-init-imageExtract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the…NVIDIAjetson-set-targetSwitch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target…NVIDIAkill-the-standupReads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing /…Varnan-Techli-gong-demo模拟李工(后端工程师)在架构评审、发布流程、跨团队对齐场景下的工作方式与沟通边界。用于团队内部对齐与培训。agenmodlocalization-setupGenerate internationalization (i18n) infrastructure for multi-language support in iOS/macOS apps. Use when localizing for…rshankraswritesmacos-capabilitiesExpert guidance on macOS platform capabilities. Covers sandboxing, app extensions, menu bar apps, and background execution. Use…rshankrasmatchmsSpectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores…foryourhealth111-pixelmatchmsSpectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores…LeonChaoXmatlab-create-custom-arduino-libraryUse when the user wants to use Arduino sensors or peripherals from MATLAB that are not directly supported by the MATLAB Support…matlabmatlab-write-performance-testsWrites MATLAB performance tests using the matlab.perftest.TestCase framework. Use when asked to write, create, or add performance…matlabmcore-create-issueInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.NVIDIAmcore-linting-and-formattingLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style…NVIDIAmcore-run-on-slurmHow to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable…NVIDIAmcore-split-prSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.NVIDIAmeasure-survey-analysisAnalyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, thematic…product-on-purposemolfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to…K-Dense-AIwritesmono-editorial-banner把一句判断、观点或标题编译成「黑白编辑横幅」生图提示词:纯白虚空 + 透视细线地面,一个自带纯黑锚点的写实主体,超大高反差衬线主标题压在上方,5:2 超宽横板。中英文标题都走衬线(Didone /…FANzR-archmutation-testingConfigures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs. Use when…trailofbitswritesnature-academic-searchUse when users ask to 找文献、做文献检索、查论文、查临床试验、核验引用、去重文献、设计 PubMed/MeSH 检索式、解析 DOI/PMID/PMCID/arXiv/OpenAlex/Semantic Scholar/NCT ID,…wp-anemo-automodel-distributed-trainingGuide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and…NVIDIAnemo-automodel-launcher-configConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.NVIDIAnemo-automodel-recipe-developmentCreate and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.NVIDIAnx-workspaceConfigure, explore, and optimize Nx monorepo workspaces. Use when setting up Nx, exploring workspace structure, configuring…tech-leads-clubopenrlhf-trainingHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+).…Orchestra-Researchopenrouter-sdk-patternsBuild reusable OpenRouter client wrappers with retries, typing, and middleware. Use when creating SDKs or client libraries.…jeremylongshorewrites案件讨论与提纲AI自动完成的深度案件分析工具,整合前序材料进行四维度自问自答分析、三方模拟法庭演练,最终生成案件提纲。当用户提及"案件讨论"、"案件提纲"、"案件分析"、"模拟法庭"、"案件研讨"等指令时触发使用。立案完成后主动提醒律师执行。pa1nrui1民事判决书一审普通程序民事判决书生成工具。从已有案件材料(起诉状、答辩状、庭审纪要、法律分析等)提取要素,生成符合法院文书样式标准的Word判决书初稿。按总控当前事项记录和复盘台账衔接。当用户发送客户编号并提及"判决书"、"民事判决书"、"起草判决书"、"模拟判决书"等…pa1nrui1调解与和解提供调解与和解全流程支持,包括可行性分析、调解方案起草、调解书/和解协议审查、撤诉管理等功能。当用户发送客户编号并提及"调解"、"和解"、"撤诉"、"调解方案"、"调解书"等指令时触发使用。pa1nrui1重整程序破产重整程序全流程管理。覆盖重整申请与受理、重整期间管理、重整计划草案编制、债权分组表决、法院强制批准、重整计划执行与监督等全部环节。适用于管理人(R1)、债权人代理(R2)、债务人代理(R3)三类角色。当用户发送客户编号并提及"重整"、"重整计划"、"重整程…pa1nrui1Persons个案概念化四步模型一个结构化的CBT个案概念化工作流程,用于系统梳理问题清单、维持机制、当前诱发及加重因素、早期起源,支撑后续干预设计。适用于CBT初阶评估阶段。ECNU-ICALKProlonged Exposure ProtocolA structured, evidence-based macro-level treatment framework for PTSD involving repeated imaginal and in vivo exposure to trauma…ECNU-ICALKREBT不合理信念自动化识别与反驳训练在治疗巩固阶段(第7~8次咨询),引导来访者主动筛查残留不合理信念,通过结构化ABC辩论促进自动化觉察习惯形成,最终内化为稳定的合理信念体系。ECNU-ICALKsentry-error-captureImplement advanced error capture and context enrichment with Sentry. Use when adding captureException/captureMessage calls…jeremylongshorewritessentry-performance-tracingSet up performance monitoring and distributed tracing with Sentry. Use when implementing performance tracking, tracing requests…jeremylongshorewritessentry-release-managementManage Sentry releases with versioning, commit association, and source map uploads. Use when creating releases, linking commits…jeremylongshorewrites
← Prev23 / 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