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.
47.268 de skill-uri din 2.272 de depozite · actualizat acum 23 de minute
10.071 de skill-uri
- genre-open-world-sandboxarjun988/blender-skillsArt direction for open world and sandbox games in Blender with biome landmarks, traversable scale, and discovery props.AlteleFără avertismente★ 1,2 K↓ —Apare și în 1 alt depozit
- indie-horror-aestheticsarjun988/blender-skillsIndie horror aesthetic pack for Blender covering Silent Hill, Fear to Fathom, Puppet Combo, corporate horror, cabin/forest/hospital horror, and related looks.AlteleFără avertismente★ 1,2 K↓ —Apare și în 1 alt depozit
- 13f-analysiscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —
- self-improveeai-org/agent-toolkitCapture durable user feedback into the governing skill, doc or check, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill, doc or check covers or should cover, and when manually invoked to improve or create guidance.AlteleFără avertismente★ 76↓ —
- glm-calibrationcxcscmu/SkillLearnBenchCalibration strategy for GLM lake temperature simulations, including parameter sensitivity and typical ranges.AlteleFără avertismente★ 91↓ —
- using-superpowersadriannoes/awesome-agentic-aiUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questionsAlteleFără avertismente★ 87↓ —
- spielervertragThomasMoreAI/legal-skills-openFür Spielervertrag: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Fachanwalt für Sportrecht. Route: spielervertrag.AlteleFără avertismente★ 95↓ —
- market-talent-mappingViy1204/recruiting-copilot基于 Boss 直聘 + 猎聘实时人才数据，对某在招岗位做市场人才盘点，转成可执行招聘打法， 产出本地 markdown 报告（可选飞书云文档 + HTML 版）。当用户要盘点/调研某岗市场人才、 做人才 mapping、看某岗目标公司有谁、某岗薪资/学历/年限市场对标、判断某岗好不好招时使用； 只要意图是摸清某岗市场人才结构并转成招聘决策就触发，不必出现"mapping"字样。 区别于 recruit-daily（每日增量寻源），本 skill 是一次针对一两个岗的深度市场调研。AlteleFără avertismente★ 104↓ —
- cm-product-managerkingxiaozhe/cm-workflow产品经理 Skill，负责需求分析、用户故事与验收标准编写、歧义清单生成、变更影响分析、业务验收走查；把关型角色，不做技术设计与技术测试AlteleFără avertismente★ 97↓ —
- d3-force-bubble-chartcxcscmu/SkillLearnBenchCreate force-simulation bubble charts with D3.js v6, including sector clustering, collision avoidance, tooltips, and legends.AlteleFără avertismente★ 91↓ —
- brd-draftChenxingJi-Innovate/Cheatcode_Skills and tools for your AI apps, added in one click. The open source parts of cheatcodehq.com: Mac installer, package format, skill packs.AlteleFără avertismente★ 81↓ —
- trend-to-microbetFAIRY123456789/human-edge-agent-skillsTurn a fast-moving AI, product, creator, career, or technology trend into a small evidence-producing bet instead of a vague FOMO reaction. Use when the user says something is suddenly hot, wonders whether to chase a new model, platform, agent, Skill, or plugin, or wants a 48-hour to 7-day experiment with a clear upside, effort cap, proof metric, and stop rule.AlteleFără avertismente★ 108↓ —
- agentsclaude-world/director-mode-liteList all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.AlteleFără avertismente★ 80↓ —
- prompt-enhancerDesko77/claude-code-skills-1cУлучшает и структурирует короткие неструктурированные промпты и постановки задач, превращая их в подробные императивные ТЗ с пронумерованными шагами анализа, явными граничными случаями и описанием формата ожидаемого вывода. Сохраняет все термины и условия исходника, не добавляет новых требований. Используй когда пользователь просит: улучшить промпт, проработать постановку, расширить описание задачи, структурировать ТЗ, оформить заметку в подробную инструкцию, сделать промпт точнее или подробнее, подготовить ТЗ из черновика, причесать задание, преобразовать короткую заметку в понятное ТЗ. Принимает текст в аргументе команды или путь к .md файлу.AlteleFără avertismente★ 86↓ —
- loogle-searchparcadei/Continuous-Claude-v3Search Mathlib for lemmas by type signature patternAlteleFără avertismente★ 3,9 K↓ —
- document-classifiercxcscmu/SkillLearnBenchLogic for categorizing documents into subjects based on keyword matching.AlteleFără avertismente★ 91↓ —
- hook-3s-scriptxianyu110/ecommerce-video-skills3 秒钩子脚本：为电商短视频写前 3 秒开场（台词 + 画面 + 花字），按痛点/反差/结果先行/提问/数字/场景代入等钩子类型一次给出多版，并做合规自检。Use when the user asks for a hook, 开头, 黄金 3 秒, 前三秒, opening line, scroll-stopper, 完播率, or wants to rewrite a weak opening for 抖音 / TikTok Shop / 视频号 / Reels.AlteleFără avertismente★ 107↓ —
- skillsclaude-world/director-mode-liteList all available skills grouped by category. Use when the user asks what skills are available or runs /skills.AlteleFără avertismente★ 80↓ —
- 1c-form-patternsDesko77/claude-code-skills-1cСправочник паттернов компоновки управляемых форм 1С. Используй как справочник при проектировании форм - архетипы, конвенции, продвинутые приемыAlteleFără avertismente★ 86↓ —
- proof-theoryparcadei/Continuous-Claude-v3Problem-solving strategies for proof theory in mathematical logicAlteleFără avertismente★ 3,9 K↓ —
- pareto-optimizationcxcscmu/SkillLearnBenchCompute Pareto-optimal frontiers from multi-objective optimization results, including dominance checking and frontier extraction.AlteleFără avertismente★ 91↓ —
- evolving-loopclaude-world/director-mode-liteSelf-Evolving Development Loop - Dynamic skill generation with learning and evolutionAlteleFără avertismente★ 80↓ —
- run2_fund_analysiscxcscmu/SkillLearnBenchAnalyze individual fund holdings, AUM, and portfolio composition from 13-F dataAlteleFără avertismente★ 91↓ —
- simpo-loss-functioncxcscmu/SkillLearnBenchImplement SimPO loss with length-normalized rewards and target margin.AlteleFără avertismente★ 91↓ —
glm-runner
cxcscmu/SkillLearnBench
AlteleActualizat 2 oct. 2026
De la autor
Manage GLM (General Lake Model) configuration and execution. Use this skill when modifying 'glm3.nml' or running the GLM binary to ensure simulation parameters are correctly set and the model runs successfully.
Instalare
npx skills add cxcscmu/SkillLearnBench --skill glm-runner -a claude-code
Se instalează în .claude/skills/glm-runner/ · 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