全部 Agent Skills
41,263 个结果
- Render ScalingRender OSSScales Render services—configures autoscaling targets, chooses instance compute plans, sets manual instance counts, and optimizes cost. Use when the user needs to handle more traffic, set up autoscaling, pick the right compute plan, reduce costs, or troubleshoot scaling behavior like slow scale-down or stuck instances.
- Render Static SitesRender OSSDeploys and configures static sites on Render's global CDN—build commands, publish paths, SPA routing, redirects, custom headers, and PR previews. Use when the user needs to deploy a static site, set up a React/Vue/Hugo/Gatsby frontend, configure SPA fallback routing, add redirect rules, customize response headers, or choose between a static site and a web service for their frontend.
- Render Web ServicesRender OSSConfigures Render web services—port binding, TLS, health checks, custom domains, auto-deploy, PR previews, persistent disks, and deploy lifecycle. Use when the user needs to set up a web service, fix health check failures, add a custom domain, configure zero-downtime deploys, or troubleshoot port binding issues.
- Render WorkflowsRender OSSBuild, validate locally, deploy, and troubleshoot Render Workflows with the current Python or TypeScript SDK. Use for defining or chaining tasks, integrating the SDK into an existing project, running tasks with the local development server, optionally scaffolding a starter, authoring "type: workflow" in render.yaml, triggering runs from application code, and releasing workflows.
- Replay TriagePendoTriage issues captured in a Pendo session replay by fetching devlogs, mapping errors to the local codebase, proposing fixes, and prompting for a pull request. Accepts either a replay URL directly or a ticket reference (e.g. Jira key or URL, GitHub issue URL, etc.) and will pull the replay link from the ticket.
- Replicas Agentreplicas-groupGuide for background coding agents running inside Replicas cloud workspaces
- request-transitisraelvicarsA public transit map for your requests. Use when the user wants to visualize, animate or share how a request moved through services, from a distributed trace (OpenTelemetry/OTLP, Datadog, PostHog, AWS X-Ray, Grafana Tempo). Draws the trace as an animated subway map (services are lines, hops are stations, slow and failed calls are service alerts) and can render a frame-exact MP4/GIF.
- Research OrchestratorTristan578Coordinates academic research workflow - delegates analysis, correlation, writing, and review tasks to specialist agents
- Researching Internet Slang And Cultural Trendsapidojo-ioExtracts slang definitions, cultural terms, and crowd-sourced meanings from Urban Dictionary using apidojo's Urban Dictionary Scraper on Apify. Triggers when the user asks to: look up internet slang terms, find how Gen Z or millennials define a word, research cultural vocabulary or meme terminology, understand what a term means on social media, analyze slang used in brand monitoring, find…
- Researching MarketsjesseotremblayConducts comprehensive market research including industry analysis, competitor analysis, market trends, customer insights, and regulatory landscape. Use when the user requests market research, industry analysis, competitive intelligence, or wants to understand a market or industry.
- Resolving ConflictMilesChou協助解決 Git Rebase 或 Merge 過程中的衝突，提供系統化的衝突解決流程。
- RespondRootly AI Labs[experimental] Investigate and respond to a production incident. Pulls context, finds similar past incidents, suggests solutions, and enables coordination. Forked-subagent flow may not have MCP access in all Claude Code contexts -- prefer /rootly:status + /rootly:brief for now.
- Retargeting FunnelmbfinottiDesign a multi-stage retargeting sequence from a site's own funnel data - recency windows and behavioural-depth tiers per stage, a message and offer ladder for each stage, mutually exclusive audiences with exclusion logic, and per-stage frequency caps.
- RetroRootly AI Labs[experimental] Generate a structured post-incident retrospective from incident data. Forked-subagent flow may not have MCP access in all Claude Code contexts.
- Risk AssessmentuukuguyRisk identification and analysis frameworks for technology decisions
- Rootly-AI-Labs/rootly-claude-pluginRootly AI Labs技能合集Rootly for Claude Code
- Round Table AnalysispianzhuDeep pre-execution analysis framework using four philosophers (Socrates, Aristotle, Feynman, Drucker) for structured critical thinking before implementing plans. Use when users need to thoroughly understand a topic, question assumptions, clarify objectives, or explore multiple perspectives before taking action.
- Saas ClonerbigadamknightThis skill should be used when the user asks to "clone a SaaS", "build a typeform clone", "replicate calendly", "create an open source alternative to X", or wants to rapidly build functional clones of popular SaaS products focusing on core features.
- Safe Action Advancednext-safe-actionUse when working with bind arguments, metadata schemas, framework errors (redirect/notFound/forbidden/unauthorized), type inference utilities (InferSafeActionFnInput/Result), or server-level action callbacks
- Safe Action Better Authnext-safe-actionUse when adding authentication or authorization to safe actions with Better Auth -- covers betterAuth() middleware setup, typed session context (BetterAuthContext), custom authorize callbacks (AuthorizeFn), unauthorized() handling, nextCookies() configuration, and Next.js authInterrupts setup
- Safe Action Clientnext-safe-actionUse when creating or configuring a next-safe-action client, defining actions with input/output validation, handling server errors, or setting up createSafeActionClient with Standard Schema (Zod, Yup, Valibot)
- Safe Action Formsnext-safe-actionUse when integrating next-safe-action with forms -- react-hook-form adapter (useHookFormAction, useHookFormOptimisticAction, mapToHookFormErrors), native HTML forms, bind arguments, or file uploads
- Safe Action Hooksnext-safe-actionUse when executing next-safe-action actions from React client components or building optimistic UI -- useAction, useOptimisticAction, useStateAction, useOptimisticStateAction, status/callbacks (onSuccess/onError/onSettled), execute vs executeAsync, formAction, reset, and queued or serialized mutations such as drag-to-reorder, Kanban boards, overlapping saves, accumulating changes, and shared…
- Safe Action Middlewarenext-safe-actionUse when implementing middleware for next-safe-action -- authentication, authorization, logging, rate limiting, error interception, context extension, or creating standalone reusable middleware with createMiddleware() or createValidatedMiddleware(). Covers both use() (pre-validation) and useValidated() (post-validation) middleware.