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.
49.105 skill-uri din 2.358 de depozite · actualizat acum 14 ore
10.344 de skill-uri
- 1c-db-dump-xmlDesko77/claude-code-skills-1cВыгрузка конфигурации 1С в XML-файлы. Используй когда пользователь просит выгрузить конфигурацию в файлы, XML, исходники, DumpConfigToFilesAlteleFără avertismente★ 88↓ —
- 1c-db-load-cfDesko77/claude-code-skills-1cЗагрузка конфигурации 1С из CF-файла. Используй когда пользователь просит загрузить конфигурацию из CF, восстановить из бэкапа CFAlteleFără avertismente★ 88↓ —
- 1c-cfe-diffDesko77/claude-code-skills-1cАнализ расширения конфигурации 1С (CFE) - состав, заимствованные объекты, перехватчики, проверка переноса. Используй когда нужно понять что содержит расширение или проверить перенесены ли вставки в конфигурациюAlteleFără avertismente★ 88↓ —
- 1c-epf-dumpDesko77/claude-code-skills-1cРазобрать EPF-файл обработки 1С (EPF/ERF) в XML-исходники. Используй когда пользователь просит разобрать, декомпилировать обработку, получить исходники из EPF/ERF файлаAlteleFără avertismente★ 88↓ —
- lead-qualifyrunxhq/runxAssess known person or company facts against supplied ICP criteria, keeping commercial fit separate from contact eligibility.AlteleFără avertismente★ 106↓ —
- lead-enrichmentrunxhq/runxNormalize factual person and company evidence for one confidently matched lead, preserving provenance, freshness, missing fields and conflicts.AlteleFără avertismente★ 106↓ —
- knowledge-routerrunxhq/runxRoute one question or source event through a supplied knowledge catalog to validated source, owner, escalation, and follow-up skill references. Use for evidence discovery and ownership routing, not broad business-action fanout or answering the question itself.AlteleFără avertismente★ 106↓ —
- 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.AlteleFără avertismente★ 106↓ —
- shapKalarisLabs/research-agent-skillsExplain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.AlteleFără avertismente★ 88↓ —
- logto-webhooksNouhookdeck/webhook-skillsReceive and verify Logto webhooks. Use when setting up a Logto webhook endpoint, validating the logto-signature-sha-256 HMAC header, or handling events like PostSignIn, PostRegister, User.Created, User.Data.Updated and Grant.LimitExceeded.AlteleFără avertismente★ 97↓ —
- prompt-refineApeironics/prompt-refine-skillSilently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.AlteleFără avertismente★ 53↓ —
- process-compose-ops0xDarkMatter/claude-modsProcess Compose orchestration for non-containerized local services: process-compose.yaml schema, health checks, restart policies, dependencies, TUI/REST/MCP control, scheduling, and boot persistence. Use as a PM2/supervisord/Foreman replacement for local dev service management.AlteleFără avertismente★ 80↓ —
- registry.installAI45Lab/OpenARTInstall GitHub-hosted registry skill folders into the OpenART tool store as guide-only or wrapper-backed script tools.AlteleFără avertismente★ 268↓ —
- dyz-med-registrationNouduyunzhoudyz/dyz-med-paper-skills从官方注册平台核实临床试验或其他研究的注册记录，并与方案、分析计划和稿件交叉检查注册时间、研究设计、 结局、样本量及结果报告差异。当用户提供 NCT、ChiCTR、ISRCTN、UMIN 等注册号，询问是否前瞻注册、是否 存在结局切换或需要注册声明时使用；报告规范的全面检查交给 dyz-med-guideline，未查到原始记录时不得生成 确定性注册声明。 Use to check trial registration records against protocols and manuscripts.AlteleFără avertismente★ 72↓ —
- dyz-med-manuscript-diagnoseNouduyunzhoudyz/dyz-med-paper-skills对用户已有的医学稿件、部分草稿、摘要、表格、拒稿信或审稿意见做只读现状诊断，给出材料清单、当前阶段、 主要科学与写作风险、投稿准备度和优先级。当用户想先知道“这篇稿子现在有什么问题、下一步怎么走”时使用； 本 Skill 不直接改写稿件，具体修订交给 dyz-med-revision 或分节 Skill。 Use for read-only manuscript assessment and revision priorities.AlteleFără avertismente★ 72↓ —
- dyz-med-revisionNouduyunzhoudyz/dyz-med-paper-skills修订已有医学稿件或逐条回应编辑和审稿人意见，覆盖语言、结构、科学表述、改投适配和拒稿后恢复，并保留 可追溯的修改记录。当用户明确要求修改稿件、回复审稿意见或按新期刊重整时使用；先给修订计划，文字和 格式修改可在授权范围内执行，涉及新数据、重分析、伦理、作者或其他源事实时必须先获得确认。 Use for manuscript revision, response to reviewers and journal resubmission preparation.AlteleFără avertismente★ 72↓ —
- dyz-med-mechanismNouduyunzhoudyz/dyz-med-paper-skills检验和升级医学研究问题的机制与因果逻辑，支持机制链检查、临床与基础双向转化、AI 模型解释、研究再设计、 因果图和中介分析方案。当用户询问“机制是否说得通”“能否从相关性升级”“如何构建因果图或中介路径”时 使用；不负责从零选题，也不把关联、特征重要性或预测性能解释为因果机制。 Use to examine causal reasoning, mechanism hypotheses and study logic.AlteleFără avertismente★ 72↓ —
- dyz-med-sensitivityNouduyunzhoudyz/dyz-med-paper-skills围绕既有医学研究结果的具体不确定性，规划、执行或记录替代模型、缺失数据、偏倚假设、分析人群和研究纳入 变化，产出可追溯的稳健性比较与局限性说明。当用户问“结果稳不稳”“换假设会不会变”或明确要求敏感性分析 时使用；原始主分析交给 dyz-med-analyze，临床重要性解释交给 dyz-med-interpret。 Use for approved sensitivity analyses and robustness comparisons of existing findings.AlteleFără avertismente★ 72↓ —
- bmad-advanced-elicitationalvin-reyes/better-agentic-idePush the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red teamAlteleFără avertismente★ 85↓ —Apare și în 1 alt depozit
- bmad-alphaalvin-reyes/better-agentic-ideA tidy fixture skill. Use when a golden needs a clean skill.AlteleFără avertismente★ 85↓ —
- connection-auth-rulesmonte-carlo-data/mc-agent-toolkitBuild a Connection Auth Rules for a Monte Carlo connection type. Fetches live connector schemas and transform steps from the apollo-agent repo.AlteleFără avertismente★ 93↓ —
- motion-graphicsJimLiu/baocut给音频视频定制内容背景与标题，或要在视频上加一段动效图形时用：下横栏（姓名职务）、关键词字幕、大数字与图表、标注与引导、品牌贴片与片尾、倒计时与进度。不选模板，按规则写一个自包含的 HTML 画面（时间的纯函数），打包成代码包导入后放上时间线。只加静态文字、贴纸或已有的文字动画预设时不用；声波一律用内置的声波元素，不用本 skill 画；整条成片的规划看「从简报到成片」。AlteleFără avertismente★ 1,6 K↓ —
- essays-in-persuasion-keynessimbajigege/book2skillsApply Keynes policy reasoning. Trigger on: "will austerity work?", "inflation or deflation?", "analyze this economic crisis".AlteleFără avertismente★ 199↓ —
- dyz-med-flowchartNouduyunzhoudyz/dyz-med-paper-skills从可追溯的研究流程计数生成并核对随机试验、观察性研究、系统综述或范围综述流程图，交付结构化计数、 Mermaid/可渲染图稿、图注和流程叙述。当用户要求 CONSORT、STROBE、PRISMA 或 PRISMA-ScR 流程图时使用； 文献去重与筛选由 dyz-med-screening-pipeline 负责，其他统计图表由 dyz-med-figures-tables 负责。 Use for PRISMA, CONSORT and observational study flow diagrams from traceable counts.AlteleFără avertismente★ 72↓ —