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.
6.758 de skill-uri din 166 de depozite · actualizat acum 24 de minute
1.083 de skill-uri
- molykitsickn33/agentic-awesome-skillsCRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLMAlteleFără avertismente★ 48,2 K↓ —
- jev-usesickn33/agentic-awesome-skillsRoute enumerable judgment steps - did it work, which option, how risky, is this safe to run - to the Jev judgment model through the jev_judge and jev_gate MCP tools, batched into one call per state.AlteleFără avertismente★ 48,2 K↓ —
- viboscopesickn33/agentic-awesome-skillsPsychological compatibility matching — find cofounders, collaborators, and friends through validated psychometricsAlteleFără avertismente★ 48,2 K↓ —
- shuffle-json-datagithub/awesome-copilotShuffle repetitive JSON objects safely by validating schema consistency before randomising entries.AlteleFără avertismente★ 40,3 K↓ —
- java-docsgithub/awesome-copilotEnsure that Java types are documented with Javadoc comments and follow best practices for documentation.AlteleFără avertismente★ 40,3 K↓ —
- bench-readgithub/awesome-copilotRead artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.AlteleFără avertismente★ 40,3 K↓ —
- maxiasickn33/agentic-awesome-skillsConnect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.AlteleFără avertismente★ 48,2 K↓ —
- axiomsickn33/agentic-awesome-skillsFirst-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English.AlteleFără avertismente★ 48,2 K↓ —
- projection-patternswshobson/agentsBuild read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.AlteleFără avertismente★ 41,4 K↓ —
- mtls-configurationwshobson/agentsConfigure mutual TLS (mTLS) for zero-trust service-to-service communication. Use when implementing zero-trust networking, certificate management, or securing internal service communication.AlteleFără avertismente★ 41,4 K↓ —
- understand-dashboardEgonex-AI/Understand-AnythingLaunch the interactive web dashboard to visualize a codebase's knowledge graphAlteleFără avertismente★ 87,4 K↓ —
- jqsickn33/agentic-awesome-skillsExpert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.AlteleFără avertismente★ 48,2 K↓ —
- taaskysickn33/agentic-awesome-skillsNegotiate terms with another person or their agent through the hosted Taasky MCP server: meeting times, prices, dates. The human confirms every accept, reject or withdraw.AlteleFără avertismente★ 48,2 K↓ —
- inngestsickn33/agentic-awesome-skillsInngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.AlteleFără avertismente★ 48,2 K↓ —
- understand-onboardEgonex-AI/Understand-AnythingUse when you need to generate an onboarding guide for new team members joining a projectAlteleFără avertismente★ 87,4 K↓ —
- llm-opssickn33/agentic-awesome-skillsLLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.AlteleFără avertismente★ 48,2 K↓ —
- nature-literature-pipelineYuan1z0825/nature-skillsComplete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival. Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegram, or any messaging platform.AlteleFără avertismente★ 49,8 K↓ —
- pricingsickn33/agentic-awesome-skillsWhen the user wants help with pricing decisions, packaging, or monetization strategy.AlteleFără avertismente★ 48,2 K↓ —
- nature-ref-verifierYuan1z0825/nature-skills对学术文献逐条执行多源交叉验证，逐字段对比作者、标题、年份、卷期、页码， 标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题，输出结构化验证报告。 可批量处理整篇论文/开题报告的参考文献列表，也可单条校验，支持与 Zotero 同步修正。AlteleFără avertismente★ 49,8 K↓ —
- day-booksickn33/agentic-awesome-skillsDaily cash, bank and digital day book: opening and closing balances per book, in/out movements, debit/credit presentation and reconciliation status. Use for daily bookkeeping.AlteleFără avertismente★ 48,2 K↓ —
- hunt-atosickn33/agentic-awesome-skillsHunt account takeover taxonomyAlteleFără avertismente★ 48,2 K↓ —
- hunt-ldapsickn33/agentic-awesome-skillsHunt LDAP Injection and XPath InjectionAlteleFără avertismente★ 48,2 K↓ —
- rag-implementationwshobson/agentsBuild Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.AlteleFără avertismente★ 41,4 K↓ —
- ef-coregithub/awesome-copilotGet best practices for Entity Framework CoreAlteleFără avertismente★ 40,3 K↓ —