Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
48.014 skill-uri din 2.309 depozite · actualizat acum 19 minute
10.137 de skill-uri
- trl-setupcxcscmu/SkillLearnBenchSetup and installation of TRL (Transformer Reinforcement Learning) library with compatible torch/transformers versions. Use when setting up preference optimization training environments.AlteleFără avertismente★ 91↓ —
- simpo-losscxcscmu/SkillLearnBenchSimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.AlteleFără avertismente★ 91↓ —
- scala-circe-jsoncxcscmu/SkillLearnBenchWorking with Circe JSON library in Scala for type-safe JSON processingAlteleFără avertismente★ 91↓ —
- deadlinesThomasMoreAI/legal-skills-openTrack case deadlines — add, cross-case rollup report, update, complete, close. Warns at configurable thresholds (default 14/7/3/1 days); overdue items stay flagged until resolved. The operational record for a clinic workload. Use when a student or supervisor needs to add a deadline, ask what's due this week, get a deadline report, or update a case deadline.AlteleFără avertismente★ 97↓ —
- takedown-zhou210712ThomasMoreAI/legal-skills-open起草"通知-删除"通知（依信息网络传播权保护条例）、对收到的通知进行分诊或起草反通知。 当通过著作权通知主张权利并经历合理使用和伪证双重关口，当收到的通知需要分诊为合规/ 反通知/协商/忽略选项，或当起草反通知并经历联邦管辖同意关口时使用。AlteleFără avertismente★ 97↓ —
- fuzzy-fund-searchcxcscmu/SkillLearnBenchFuzzy matching techniques for finding hedge funds by name when exact names are unknownAlteleFără avertismente★ 91↓ —
- eventsdeeleeramone/PyWryThe PyWry event system — namespaced events, request/response round-trips, widget IDs, component IDs, and how tool results flow back to the agent.AlteleFără avertismente★ 99↓ —
- duldung-60aThomasMoreAI/legal-skills-openFür Duldung Paragraf 60a: Fachmodul im Migrationsrecht: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.AlteleFără avertismente★ 97↓ —
- geospatial-analysiscxcscmu/SkillLearnBenchAnalyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.AlteleFără avertismente★ 91↓ —
- mccosmosayingQAQ/McCosmosCompare McDonald's food nutrition, find calorie-constrained alternatives, and explain nutrition similarities using real McDonald's MCP data or an explicitly dated McCosmos snapshot. Use for meal comparisons, food searches and nutrition maps.AlteleFără avertismente★ 114↓ —
- ask-mattadriannoes/awesome-agentic-aiAsk which skill or flow fits your situation. A router over the user-invoked skills in this repo.AlteleFără avertismente★ 91↓ —
- simpo-losscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —
- glm-lake-modelcxcscmu/SkillLearnBenchRunning the General Lake Model (GLM3) for lake temperature simulation, including configuration file structure and execution.AlteleFără avertismente★ 91↓ —
- file-organizationcxcscmu/SkillLearnBenchOrganize files into target directories based on classification resultsAlteleFără avertismente★ 91↓ —
- audit-agent-surfaceJoviDeCroock/prachtInventory what agents can reach in a pracht app — capability exposure (HTTP, WebMCP, remote MCP), `agents` trust config, the destructive-confirmation gate, `llms.txt`, Markdown negotiation, OpenAPI — and report where the surface is wider than intended, or confirm an opt-out app ships none. Use for "audit the agent surface", "what can agents do on my site", "is my MCP endpoint safe", "did this PR widen what agents can reach".AlteleFără avertismente★ 105↓ —
- parallel-grid-searchcxcscmu/SkillLearnBenchParallelize hyperparameter grid search using joblib for efficient multi-core execution.AlteleFără avertismente★ 91↓ —
- 1c-bsp-registrationDesko77/claude-code-skills-1cДобавить функцию регистрации БСП (СведенияОВнешнейОбработке) в модуль объекта обработкиAlteleFără avertismente★ 87↓ —
- opencv-grayscalecxcscmu/SkillLearnBenchConvert images from RGB/BGR to grayscale using OpenCV and save in-place.AlteleFără avertismente★ 91↓ —
- parallel-tool-orchestratorroedyrustam/vibes-plugParallel tool calling, MCP batching, and async subagent fan-out / Eksekusi tool paralel, batching MCP, dan subagent async fan-out.AlteleFără avertismente★ 116↓ —
- skill-verwalterThomasMoreAI/legal-skills-openFür Skill-Manager: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.AlteleFără avertismente★ 97↓ —
- operator-theoryparcadei/Continuous-Claude-v3Problem-solving strategies for operator theory in functional analysisAlteleFără avertismente★ 3,9 K↓ —
- glm-calibrationcxcscmu/SkillLearnBenchCalibrating General Lake Model (GLM) parameters to match field observations of water temperature. Use this skill whenever you need to adjust light extinction (Kw), mixing coefficients (coef_mix_hyp), or atmospheric bulk transfer factors (wind_factor, lw_factor, ch) to improve model fit. Essential for reducing temperature RMSE and achieving model validation thresholds for lakes.AlteleFără avertismente★ 91↓ —
- meshy-3d-printingmeshy-dev/meshy-3d-agentGenerate or prepare models for physical 3D printing, including white or multicolor prints, Creative Lab products, sizing, and slicer handoff.AlteleFără avertismente★ 106↓ —
- 13f-analysiscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —