AgentHubAgentHub
传输类型是什么?
  • stdio(本地进程)MCP 以子进程运行在本地,通过标准输入/输出与 Cursor、Claude 等通信。最常见,适合 npx/uvx 启动的工具。
  • streamable-http(远程 HTTP)MCP 托管在远程服务器,客户端通过 HTTP 连接。适合团队共享或无法本地安装的服务。
  • sse(远程 SSE)通过 Server-Sent Events 长连接访问远程 MCP。部分托管平台使用此方式。

共 2,719 个资源

backend-architecture

vmain

SkillSkillsMP

io.github.exceptionless/Exceptionless/backend-architecture

Use this skill when working on the ASP.NET Core backend — adding controllers, services, repositories, validators, authorization, WebSocket endpoints, jobs, Foundatio infrastructure, configuration, or Aspire orchestration. Prefer this as the backend entrypoint for project layering, C# conventions, logging, ProblemDetails, security-sensitive config, and OpenAPI baseline updates.

source

frontend-architecture

vmain

SkillSkillsMP

io.github.exceptionless/Exceptionless/frontend-architecture

Use this skill as the frontend entrypoint for the Svelte 5 app in ClientApp — adding routes, creating feature slices, writing Svelte components, applying TypeScript conventions, using shared UI/formatter components, handling accessibility, or adding frontend tests. The legacy Angular app still powers most of the current site in ClientApp.angular, but all new frontend development should be Svelte UI only unless the user explicitly asks for Angular or legacy UI changes.

source

deployment

vmain

SkillSkillsMP

io.github.NVIDIA/Model-Optimizer/deployment

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).

source

automation-monitoring-billing-narratives

vmain

SkillSkillsMP

io.github.Klotzkette/claude-fuer-deutsches-recht/automation-monitoring-billing-narratives

Automationen und Monitoring: Entwirft Monitore für Datenraum-Neuzugaenge, Q&A-Status, CP-Deadlines, Registerupdates, MAR-Signale und PMI-Aufgaben im Corporate/M&A-Kontext. Normen: MAR Art. 17, § 41 GWB (Vollzugsverbot), § 56 AWV im Corporate Kanzlei: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung. Liefert priorisierten Output mit Norm-Pinpoints, Risikoampel und nächstem Arbeitsschritt.

source

automation-monitoring

vmain

SkillSkillsMP

io.github.Klotzkette/claude-fuer-deutsches-recht/automation-monitoring

Mandant oder Kanzlei will Deal-Aktivitaeten automatisch tracken: Datenraum-Neuzugaenge Fristen Q&A MAR-Signale PMI-Aufgaben. Normen MAR VO 596/2014 §§ 35-44 GWB Insiderlisten. Prüfraster Datenraum-Monitor CP-Deadline-Kalender Register-Update-Check News-Screening PMI-Task-Tracking. Output Monitoring-Protokoll Alert-Regeln Ampel-Dashboard. Abgrenzung zu mittelstand-ma-fristen-cp-kalender (Fristen-only) und mittelstand-corporate-ma-deal-intake (Eingang) im Mittelstand Corporate Ma: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung. Liefert priorisierten Output mit Norm-Pinpoints, Risikoampel und nächstem Arbeitsschritt.

source

automation

vmain

SkillSkillsMP

io.github.Klotzkette/claude-fuer-deutsches-recht/automation

Monitoring und Automatisierungen für laufende M&A-Mandate einrichten: Anwendungsfall Deal-Team benoetigt automatisierte Überwachung von Datenraum-Neuzugaengen Q&A-Deadlines CP-Fristen Registerupdates und MAR-Signalen. §§ 35 ff. GWB Kartellrechtsfristen, §§ 55 ff. AWV FDI-Fristen, Art. 17 MAR Ad-hoc-Monitoring. Prüfraster Eskalationsregeln Owner-Matrix Stop-Schwellen PMI-Aufgaben News-Monitoring. Output Monitoring-Plan mit Trigger-Logik Eskalationspfad und Verantwortlichkeitsmatrix. Abgrenzung zu Steps-Plan-PMO für manuelle Aufgabenlisten und zu Fristen-CP-Kalender.

source

codex-cli

vmain

SkillSkillsMP

io.github.kortix-ai/suna/codex-cli

Drive OpenAI's Codex CLI (`codex exec`) as a non-interactive coding sub-agent from inside Claude Code. Load WHENEVER you want to delegate a coding/analysis/refactor task to Codex, get a second opinion / adversarial review from another model, fan out parallel agents across files or worktrees, or run a long mechanical job while you stay the planner. Covers the exact `codex exec` flags, sandbox tiers, output capture, JSON/schema modes, session resume, parallel fan-out, and the mandatory "delegate → capture → independently verify, never trust the self-report" supervision loop.

source

github-pr-review-session

vmaster

SkillSkillsMP

io.github.zeroclaw-labs/zeroclaw/github-pr-review-session

Human-reviewer co-pilot for ZeroClaw PR reviews. Use this skill when the user wants to review a specific PR as themselves, re-review a PR after author changes, work through a queue of PRs, check what's still open on a PR, or post a formal review verdict. Trigger on: 'review 1234', 'can you look at PR #1234', 're-review 1234', 'check 1234', 'what's still open on 1234', 'go through the queue', 'next PR', 'review the open PRs'. This skill posts reviews in the voice of the active `gh` account holder using gh CLI.

source

react-start-server-components

vmain

SkillSkillsMP

io.github.TanStack/router/server-components

Implement, review, debug, and refactor TanStack Start React Server Components in React 19 apps. Use when tasks mention @tanstack/react-start/rsc, renderServerComponent, createCompositeComponent, CompositeComponent, renderToReadableStream, createFromReadableStream, createFromFetch, Composite Components, React Flight streams, loader or query owned RSC caching, router.invalidate, structuralSharing: false, selective SSR, stale names like renderRsc or .validator, or migration from Next App Router RSC patterns. Do not use for generic SSR or non-TanStack RSC frameworks except brief comparison.

source
Agent Skill · SkillsMP · 搜索 · AgentHub