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.
48.019 skill-uri din 2.309 depozite · actualizat acum 29 de minute
10.140 de skill-uri
- zhuangxiu-yanshou-zhinanzx029w/zhuangxiu-skills装修验收指南专用 Skill。覆盖水电隐蔽工程、瓦工木工验收、竣工验收与收房、验收工具与清单等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的装修验收。AlteleFără avertismente★ 86↓ —
- disk-cleanupmoonlight-lupin/agent-skillsUse when df says disk is above 80% full or the user wants to reclaim storage space on a VM.AlteleFără avertismente★ 113↓ —
- thinking-dhhaAAaqwq/AGI-Super-TeamDHH's thinking framework — convention over configuration, ship fast, perfect is the enemyAlteleFără avertismente★ 112↓ —
- d3-fundamentalscxcscmu/SkillLearnBenchEssential D3.js v6 concepts including selections, scales, SVG basics, and data binding for building interactive visualizationsAlteleFără avertismente★ 91↓ —
- netcdf-processingcxcscmu/SkillLearnBenchReading, processing, and analyzing NetCDF output from lake simulation modelsAlteleFără avertismente★ 91↓ —
- pm-business-modelkonglong87/superPMUse when: 需要设计商业模式画布、规划盈利模式、制定定价策略、设计收入模型 Do NOT use when: 商业模式已确定且已验证、仅需简单定价调整而非全面设计AlteleFără avertismente★ 84↓ —
- kv-cache-prefix-optimizerroedyrustam/vibes-plugExpert guide for deterministic prompt prefix engineering, KV-cache locking for Gemini 4 Pro / Claude 5.5 / GPT Astra 6, canonical tool sorting, and achieving 90%+ prompt cache hit rates / Panduan ahli rekayasa prefix prompt deterministik, penguncian KV-cache untuk Gemini 4 Pro / Claude 5.5 / GPT Astra 6, pengurutan kanonikal tool, dan pencapaian 90%+ cache hit rate.AlteleFără avertismente★ 116↓ —
- alterlab-molfeatAlterLab-IEU/AlterLab-Academic-SkillsFeaturizes molecules for machine learning with molfeat — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, pharmacophore and shape descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, CheMeleon) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.AlteleFără avertismente★ 81↓ —
- california-sc100-formcxcscmu/SkillLearnBenchUnderstand the structure and fields of the California Small Claims Court Form SC-100AlteleFără avertismente★ 91↓ —
- simpo-losscxcscmu/SkillLearnBenchGuide on understanding and implementing the SimPO (Simple Preference Optimization) loss function for language models.AlteleFără avertismente★ 91↓ —
- module-scaffold26zl/cybersec-toolkitUse when creating a brand new module file in modules/ for a new tool category. Generates the boilerplate with correct array prefix, install_module_<name>() function, and ensures it integrates with install.sh, profiles, and MCP server. Triggers on "new module", "add a module for X", "scaffold module".AlteleFără avertismente★ 87↓ —
- creativityTheGoat395/Codex-SkillsGenerate original ideas or escape fixation.AlteleFără avertismente★ 135↓ —
- press-mediarshankras/claude-code-apple-skillsGet press coverage and media attention for your indie app. Covers press kit preparation, finding journalists/bloggers/YouTubers, pitch timing, embargo strategy, and story angles that get coverage. Use when user wants press coverage, is preparing for a launch, or wants to build a media kit.AlteleFără avertismente★ 842↓ —
- wiki-arsenalEncod3d-Sec/TORCHFast PARALLEL wiki lookup engine over wiki/techniques + wiki/payloads + wiki/tools + wiki/cheatsheets for a surface/service/vuln-class. Two modes - quick (one qmd search, cheap, fire constantly) and deep (4 parallel subagents, one per area, merged ready-to-use arsenal card, cached). This is the fast path arsenal that `arsenal` delegates to; the hunt-* skills each inline their own qmd_query and can hand off here for a parallel lookup. Use for "what do I use against <surface>", "arsenal for <X>", "deep/full arsenal", "tool + payload + technique + cheatsheet for <X>", "fast wiki lookup", "parallel wiki search", any "how do I attack/exploit <service|vuln-class>" where you want the documented tooling + payloads before hand-rolling.AlteleFără avertismente★ 337↓ —
- glm-runnercxcscmu/SkillLearnBenchA skill to execute the GLM binary and manage its simulation output.AlteleFără avertismente★ 91↓ —
- pm-decisionkonglong87/superPMUse when: 需要做重大战略决策（自研vs外包vs收购）、投资评估、多方案比较选择 Do NOT use when: 决策已由高层确定、决策影响极小无需系统分析AlteleFără avertismente★ 84↓ —
- hunt-sqliEncod3d-Sec/TORCHSQLi and NoSQLi hunting - error-based, boolean-blind, time-based, UNION, NoSQL operator injection. sqlmap automation after manual confirmation. Wiki-first, FIND schema output.AlteleFără avertismente★ 337↓ —
- app-cliprshankras/claude-code-apple-skillsGenerates App Clip targets with invocation URL handling, lightweight experiences, and full app upgrade prompts. Use when user wants NFC/QR/Safari banner invocation, instant app experiences, or App Clip Card setup.AlteleFără avertismente★ 842↓ —
- anlagen-bauenKlotzkette/claude-fuer-deutsches-rechtFür Fluggastrechte — Anlagen bauen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.AlteleFără avertismente★ 1,8 K↓ —
- wikiEncod3d-Sec/TORCHSearch, query, and maintain the qmd-indexed wiki - semantic search, keyword search, re-index after adding pages, check index status.AlteleFără avertismente★ 337↓ —
- nextjs-server-client-boundariesTheGoat395/Codex-SkillsSet use client and Server Function boundaries.AlteleFără avertismente★ 135↓ —
- glm-calibrationcxcscmu/SkillLearnBenchCalibrating GLM parameters (Kw, coef_mix_hyp, wind_factor, lw_factor, ch) to minimize RMSE against field observations.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↓ —
- vlop-quellenkarteThomasMoreAI/legal-skills-openFür Vlop Quellenkarte: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.AlteleFără avertismente★ 97↓ —
content-classification
cxcscmu/SkillLearnBench
AlteleActualizat 2 oct. 2026
De la autor
Classify documents by subject using keyword matching and text analysis
Instalare
npx skills add cxcscmu/SkillLearnBench --skill content-classification -a claude-code
Se instalează în .claude/skills/content-classification/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 83
Securitate100
Proveniență64
Întreținere100
Licență100
Adopție34
Fișiere (1)
- SKILL.md