Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,399 skills from 2,375 repositories · updated 1 hour ago
10,398 skills
- numerical-stabilityHeshamFS/materials-simulation-skillsAnalyze numerical stability for time-dependent PDE simulations — check CFL and Fourier criteria, perform von Neumann stability analysis, detect stiffness, evaluate matrix conditioning, and recommend explicit vs implicit time-stepping schemes. Use when selecting time steps, diagnosing numerical blow-up or solver divergence, checking convergence criteria, or evaluating scheme stability for advection, diffusion, or reaction problems, even if the user doesn't explicitly mention "stability" or "CFL."OtherNo warnings★ 83↓ —
- 1c-support-stateDesko77/claude-code-skills-1cЧтение и переключение состояния поддержки конфигурации 1С в XML-выгрузке - разрешить правку типового объекта, снять с поддержки, вернуть на замок, включить возможность изменения. Используй когда пользователь спрашивает про состояние поддержки, объект на замке, снятие с поддержкиOtherNo warnings★ 88↓ —
- hpc-runtime-doctorHeshamFS/materials-simulation-skillsDiagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler portability, and resource mismatch. Use when an ALREADY-SUBMITTED job failed, ran slowly, got killed, or behaved differently on a cluster than on a workstation. To author or vet a NEW submission script before running, use slurm-job-script-generator instead.OtherNo warnings★ 83↓ —
- alterlab-pymcAlterLab-IEU/AlterLab-Academic-SkillsBayesian modeling and probabilistic programming with PyMC 6 and ArviZ 1.x — hierarchical models, MCMC (NUTS via PyMC, nutpie, NumPyro, or BlackJAX), variational inference, PSIS-LOO model comparison, and prior/posterior predictive checks. Use when fitting Bayesian or hierarchical models, estimating posteriors and credible intervals, diagnosing divergences, R-hat, or ESS, running probabilistic inference, or comparing models with LOO (WAIC was removed from ArviZ 1.x). Part of the AlterLab Academic Skills suite.OtherNo warnings★ 84↓ —
- processing-stix-taxii-feeds26zl/cybersec-toolkitProcesses STIX 2.1 threat intelligence bundles delivered via TAXII 2.1 servers, normalizing objects into platform-native schemas and routing them to appropriate consuming systems. Use when onboarding new TAXII collection endpoints, automating bi-directional intelligence sharing with ISACs, or building pipeline validation for malformed STIX bundles. Activates for requests involving OASIS STIX, TAXII server configuration, MISP TAXII, or Cortex XSOAR feed integrations.OtherNo warnings★ 87↓ —
- premium-visual-reference-libraryTheGoat395/Codex-SkillsFind references, Viktor Oddy and MotionSites.OtherNo warnings★ 136↓ —
- ai-storyboard-director62656456/ai-film-skills根据剧本与已定导演方案设计观看顺序、人物调度、电影摄影和剪辑，编写或修订分镜与视频提示词；支持创意镜头思路、打戏和运镜诊断。创意思路可单独交付或并列于主分镜，采用后才纳入；分镜、提示词与实际生成按当前阶段分别执行。OtherNo warnings★ 103↓ —
- anlagen-bauenThomasMoreAI/legal-skills-openFür Fluggastrechte — Anlagen bauen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- spring-cloud-gatewayrrezartprebreza/spring-boot-skillsUse when building Spring Cloud Gateway 5 on Spring Boot 4, including WebFlux or Web MVC routes, edge authentication, trusted headers, rate limits, timeouts, and resilience. Do not use for ordinary outbound HTTP clients or domain orchestration.OtherReview first★ 338↓ —
- detecting-kerberoasting-attacks26zl/cybersec-toolkitDetect Kerberoasting attacks by monitoring for anomalous Kerberos TGS requests targeting service accounts with SPNs for offline password cracking.OtherNo warnings★ 87↓ —
- detecting-pass-the-hash-attacks26zl/cybersec-toolkitDetect Pass-the-Hash attacks by analyzing NTLM authentication patterns, identifying Type 3 logons with NTLM where Kerberos is expected, and correlating with credential dumping.OtherNo warnings★ 87↓ —
- spring-ai-integrationrrezartprebreza/spring-boot-skillsUse when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.OtherReview first★ 338↓ —
- 1c-mxl-decompileDesko77/claude-code-skills-1cДекомпиляция табличного документа (MXL) в JSON-определение. Используй когда нужно получить редактируемое описание существующего макетаOtherNo warnings★ 88↓ —
- content-gatecgallic/kai-cmo-harnessRun the full quality gate on any content file. Score against 28 rules, apply policy, show detailed scorecard with fix suggestions. Works on any markdown file.OtherNo warnings★ 61↓ —
- alterlab-torch-geometricAlterLab-IEU/AlterLab-Academic-SkillsGraph Neural Networks with PyTorch Geometric (PyG) — node and graph classification, link prediction, GCN, GAT, and GraphSAGE layers, heterogeneous graphs, and molecular property prediction. Use when building or training GNNs for geometric deep learning on graph-structured data. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 84↓ —
- taste-profilerunxhq/runxBuild a scoped taste profile packet from examples, preferences, and explicit dislikes so downstream agents can make style decisions without inventing the user's taste.OtherNo warnings★ 105↓ —
- kai-retrocgallic/kai-cmo-harnessRun a learning retrospective on the Kai harness. Mines gate-failure logs and 30-day performance results into lessons, triages candidate lessons (promote/keep/retire), and graduates repeated lessons into enforced gate checks with golden corpus cases. Use when "retro", "what have we learned", "triage lessons", "promote lessons", "why does this keep failing", "harness retrospective", or monthly / after any heavy content sprint.OtherNo warnings★ 61↓ —Also in 1 other repo
- kai-retrocgallic/kai-cmo-harnessRun a learning retrospective on the Kai harness. Mines gate-failure logs and 30-day performance results into lessons, triages candidate lessons (promote/keep/retire), and graduates repeated lessons into enforced gate checks with golden corpus cases. Use when "retro", "what have we learned", "triage lessons", "promote lessons", "why does this keep failing", "harness retrospective", or monthly / after any heavy content sprint.OtherNo warnings★ 61↓ —Also in 1 other repo
- skill-adoptrunxhq/runxAdopt a pinned third-party SKILL.md as an exact native Runx binding bundle with deterministic source digests, a bounded execution profile, isolated harness proof, and no publication claim. Use skill-build for first-party Runx skills.OtherNo warnings★ 105↓ —
- ghostwriterunxhq/runxTurn validated evidence and operator intent into publication-ready drafts, deterministic channel packages, and provider-neutral handoffs.OtherNo warnings★ 105↓ —
- 1c-epf-buildDesko77/claude-code-skills-1cСобрать внешнюю обработку 1С (EPF/ERF) из XML-исходников. Используй когда пользователь просит собрать, скомпилировать обработку или получить EPF/ERF файл из исходниковOtherNo warnings★ 88↓ —
- postmortem-draftrunxhq/runxTurn resolved-incident fragments into a traceable postmortem that separates fragment-cited facts from hypotheses, blocks publication while unknowns remain, and keeps the comms send behind a human gate.OtherNo warnings★ 105↓ —
- githubrunxhq/runxRead or synchronize bounded GitHub issues, threads, and pull requests through the GitHub connector, with scoped authority and readback.OtherNo warnings★ 105↓ —
- implementing-saml-sso-with-okta26zl/cybersec-toolkitImplement SAML 2.0 Single Sign-On (SSO) using Okta as the Identity Provider (IdP). This skill covers end-to-end configuration of SAML authentication flows, attribute mapping, certificate management, aOtherNo warnings★ 87↓ —