Top Agent Skills

Add official Railway database services (Postgres, Redis, MySQL, MongoDB) to a project, check for existing databases, and connect them to other services.

Escreva código C eficiente com gerenciamento adequado de memória, ponteiros

Template do pack (ai-ml/03-rag-pipeline.md). Orienta o agente em integracao de IA/ML, LLM e pipelines de dados alinhado a esse contexto.

Modelagem metabólica baseada em restrições (COBRA). FBA, FVA, knockouts de genes, amostragem de fluxo, modelos SBML, para análise de biologia de sistemas e engenharia metabólica.

Rastreie sites inteiros usando a API /crawl do Cloudflare Browser Rendering. Inicia jobs de rastreamento assíncronos, monitora a conclusão e salva os resultados como arquivos markdown. Útil para ingerir sites de documentação, bases de conhecimento ou qualquer conteúdo web no contexto do seu projeto. Requer variáveis de ambiente CLOUDFLARE_ACCOUNT_ID e CLOUDFLARE_API_TOKEN.

Show the quick-reference guide for the whiteboard planning system (whiteboard, hot-seat, napkin, connotation-cop) — the flow, what to say, and the rules. Use when the user asks "whiteboard help", "how do I use the whiteboard", "what's the flow", "remind me how whiteboard works", "which skill do I use", or seems unsure how to start or continue a whiteboard effort. This skill only DISPLAYS the guide — it never starts a board, resolves tickets, or does any work.

Run a pre-mortem — imagine the project has already failed one year from now and work backward to find the root causes before they happen. Load when the user asks for a pre-mortem, wants to imagine failure before committing, asks "what could go wrong before we start", "assume this fails — why", "risk analysis before launch", "what kills this project", "what could go wrong", or when deep-thinking diagnoses a pre-mortem frame. Based on Gary Klein's prospective hindsight method, which surfaces failure causes more effectively than forward risk analysis. Most useful right before a major commitment.

Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure. Load when the user asks for a safe edit, verified change, one change at a time with rollback, or codespine-style edit loop. Also triggers on "safe change", "edit with verification", "don't break the build", "revert if tests fail", or any non-trivial code edit where blast radius matters. Always runs dependency-mapping first. Pairs with incremental-implementation for multi-slice work; this skill is one atomic verify cycle per invocation.

Create handcrafted static SVG graphics and performant SVG animations — icons, illustrations, loaders, path-draw effects, morphing shapes, and motion paths. Load when the user asks to create SVG, draw an SVG icon, animate an SVG, make an SVG loader, path animation, shape morph, animated logo, line drawing effect, or improve trashy AI-generated SVG. Also triggers on "SVG animation", "SMIL", "stroke-dashoffset", "vector illustration", or "self-contained animated SVG".

Review a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns, UX heuristics, and polish, and check contrast with APCA (not the legacy WCAG ratio). Produces specific, prioritized fixes — never vibes-based feedback. Works with pasted screenshots or Playwright MCP automated capture. Load when the user asks to review a UI, audit a design, check if a frontend looks generic or vibecoded, evaluate visual quality or polish, says "review this UI", "is this design good", "audit my frontend", "does this feel like [product]", "design QA", or when frontend-design routes here. Sub-skill of frontend-design.

Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.

Research a skill domain before building or improving a skill. Searches academic papers, practitioner blogs, and GitHub skill repos in parallel to find current best practices, domain gotchas, and existing skill patterns. Called by universal-skill-creator and improve-skills before writing any skill. Also load directly when the user asks to research a domain for a skill, find existing skills on a topic, discover best practices for a skill, check what research exists before building an agent skill, or says "what does current research say about", "find best practices for".

Gracefully retire a skill that is redundant, superseded, or no longer earning its place in the context window. Load when improve-skills finds a skill scoring 0-5/14 AND research confirms the domain is now handled natively by current models, when two skills have overlapping triggers and one subsumes the other, when the user asks to remove a skill, retire a skill, delete a skill, or clean up redundant skills, or when validate-skills flags a skill as a duplicate trigger risk. Handles removal cleanly: updates all callers, removes from AGENTS.md, updates README, and archives rather than deletes so the skill can be recovered if needed.

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.

Record durable project decisions with rationale, alternatives, assumptions, status, and revisit triggers. Load when the user says record this decision, we decided, decision log, why did we choose, revisit this later, or capture architectural/process rationale.

Review code changes for correctness, completeness, bugs, edge cases, and quality. Load when the user explicitly asks to review code, check a PR, review a diff, audit recent changes, or verify an implementation matches requirements. Also triggers on "review this code", "check this PR", "review my changes", "code review", "did this implement correctly", "audit this diff", or any explicit request for a formal code review. Do NOT load for "review changes for context" or "review what happened" — those are requests to read code, not to perform a formal review.

Validate process decomposition and architecture design quality before execution begins. Load when the setup-evaluator agent fires (automatic for agent-chain tasks), or when user says "evaluate this setup", "check the decomposition", "validate the architecture", "is this plan sound", "review the agent design". Catches structural errors, missing knowledge, unrealistic step ordering, and topology mismatches. Does NOT modify — only evaluates.

Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is, and identify which ones to test first. Load when the user asks to map assumptions, surface hidden beliefs, find what must be true for this to work, run an assumption audit, or when deep-thinking diagnoses an assumption frame. Also triggers on "what are we assuming", "what must be true for this to work", or "find the untested beliefs". Based on David Bland and Alex Osterwalder's assumption mapping method from Testing Business Ideas.

Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.

Decompose tasks into structured, outcome-defined process entries with complexity triage. Load when user says "decompose this", "break this down", "what steps do I need", "plan this out", "what's the process for", "how do I approach this", or when any complex task needs structured execution planning. Includes a problem-understanding pass before complexity triage. Routes to `problem-to-plan` when the user needs planning deliverables (spec + plan + TODO). Does NOT replace brainstorming — brainstorming is design approval (upstream), this is execution planning (downstream).

Orchestrator for agent harness work — the setup that makes AI agents follow project rules and improve when they fail. FIRES PROACTIVELY when agents misbehave, repeat mistakes, ignore instructions, skip skills, or when AGENTS.md exists but docs/harness/manifest.json is missing. Also triggers on: harness engineering, agent scaffold, agent keeps failing, agent not following instructions, make agents reliable, agents going off rails, agent forgot context, improve agent setup, self-improving agents, agents keep making mistakes, why is my agent bad, agent quality, agent setup broken, agents ignore skills, same mistake again, fix agent behavior, tune agent instructions, set up agent infrastructure, after project setup agents still bad. Routes bootstrap vs evolution. Not multi-agent topology — agent-builder.

Design and implement CI/CD pipelines and automation — fast checks on every PR, safe releases, and repeatable workflows. Load when setting up GitHub Actions (or similar), adding pre-merge gates, automating releases, or the user asks "add CI", "set up workflows", "automate checks", "CD pipeline". Not for one-off local scripts (use task-specific tooling).

Imported skill app from langchain

Imported skill parser from vercel

Imported skill diff from langchain

Imported skill package from vercel

Imported skill graph from langchain

Imported skill store from langchain

Imported skill validate from vercel

Imported skill memory from langchain

Imported skill _sections from vercel

Imported skill backend from langchain

Imported skill sandbox from langchain

Imported skill models from agentskills

Imported skill lora_ofl from anthropic

Imported skill protocol from langchain

Imported skill utilities from anthropic

Imported skill contributing from openai

Imported skill ui_component from openai

Imported skill gloock_ofl from anthropic

Imported skill filesystem from langchain

Expert knowledge for Azure Arc development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Arc-enabled Kubernetes, servers/VMs, data services, resource bridge, or Edge RAG workloads, and other Azure Arc related development tasks. Not for Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Virtual Machines (use azure-virtual-machines), Azure Stack Edge (use azure-stack-edge), Azure VMware Solution (use azure-vmware-solution).

Expert knowledge for Azure Role-based access control development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when designing Azure RBAC/ABAC scopes, custom roles, PIM, CLI/PowerShell/REST role ops, or ARM/Bicep templates, and other Azure Role-based access control related development tasks. Not for Azure Active Directory B2C (use azure-active-directory-b2c), Azure Information Protection (use azure-information-protection), Azure Policy (use azure-policy), Azure Security (use azure-security).

Expert knowledge for Azure Relay development including troubleshooting, security, configuration, and integrations & coding patterns. Use when configuring Hybrid Connections, WCF relays, Entra ID/SAS auth, Private Link, or .NET/Node.js Relay clients, and other Azure Relay related development tasks. Not for Azure Service Bus (use azure-service-bus), Azure Event Hubs (use azure-event-hubs), Azure Web PubSub (use azure-web-pubsub), Azure Application Gateway (use azure-application-gateway).

Expert knowledge for Azure Boards development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing work items, queries/charts, GitHub links, Scrum boards/sprints, or WIQL-based integrations, and other Azure Boards related development tasks. Not for Azure DevOps (use azure-devops), Azure Test Plans (use azure-test-plans), Azure Pipelines (use azure-pipelines), Azure Repos (use azure-repos).

Expert knowledge for Azure Quotas development including limits & quotas. Use when requesting per-region Storage account quota increases, checking limits, or filing Azure support requests, and other Azure Quotas related development tasks. Not for Azure Cost Management (use azure-cost-management), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy), Azure Resource Manager (use azure-resource-manager).

Generate conventional commit message suggestions for staged git changes, aligned with the repository's commit style. Use when the user wants a commit message suggestion, asks what to commit, or says "suggest commit".

Write, review, or refactor C# unit tests using XUnit v3, NSubstitute, FluentAssertions, and Atc.Test. Use this skill whenever the user asks to create tests, add test coverage, fix failing tests, mock dependencies with NSubstitute, or follow the ClassName_MethodUnderTest_ExpectedBehavior naming convention in a .NET/C# project.

Expert knowledge for Azure Sentinel development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Sentinel data connectors, analytics rules, playbooks/Logic Apps, ASIM schemas, or SAP/AWS/GCP sources, and other Azure Sentinel related development tasks. Not for Azure Defender For Cloud (use azure-defender-for-cloud), Azure Security (use azure-security), Azure Monitor (use azure-monitor), Azure Network Watcher (use azure-network-watcher).

Expert knowledge for Azure AI Vision development including decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. Use when using Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, or video frame analysis, and other Azure AI Vision related development tasks. Not for Azure AI Custom Vision (use azure-custom-vision), Azure AI Video Indexer (use azure-video-indexer), Azure AI Document Intelligence (use azure-document-intelligence), Azure AI Immersive Reader (use azure-immersive-reader).

Expert knowledge for Azure HDInsight development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Hive/Spark/Kafka/HBase jobs, tuning clusters, securing access, or integrating SQL, Cosmos DB, or Synapse, and other Azure HDInsight related development tasks. Not for Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics).

Azure Cosmos DB SDK best practices for .NET, Java, Python, Spring Boot, and LangChain: singleton client, async APIs, connection modes, retry handling, diagnostics, serialization, emulator configuration, ETags, and framework-specific patterns. USE FOR: CosmosClient singleton, async API, Direct vs Gateway mode, retry 429, preferred regions, excluded regions, availability strategy, circuit breaker, SDK diagnostics, serialization enums, emulator SSL, ETag concurrency, conditional create, patch increment, continuation token, content response, Spring Data Cosmos, Spring Boot versions, Newtonsoft dependency, namespace collision, Python async deps, local dev config, LangChain Cosmos DB saver, LangGraph checkpointer, MCP persistent session, tool content format, tool filtering, LangChain JS vectorstore, chat history, semantic cache. DO NOT USE FOR: data modeling (use cosmosdb-data-modeling), queries (use cosmosdb-query-optimization), partition keys (use cosmosdb-partition-key).

Expert knowledge for Azure Automation development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Azure Automation runbooks, DSC/State Configuration, Hybrid Runbook Workers, Private Link, or AMA-based Change Tracking, and other Azure Automation related development tasks. Not for Azure Functions (use azure-functions), Azure Logic Apps (use azure-logic-apps), Azure Scheduler (use azure-scheduler), Azure Update Manager (use azure-update-manager).

Expert knowledge for Azure Lighthouse development including decision making, security, configuration, integrations & coding patterns, and deployment. Use when configuring Lighthouse delegations, AOBO/PIM access, Arc/Sentinel integrations, policies/remediation, or Marketplace offers, and other Azure Lighthouse related development tasks. Not for Azure Arc (use azure-arc), Azure Managed Applications (use azure-managed-applications), Azure Resource Manager (use azure-resource-manager), Azure Role-based access control (use azure-rbac).

Expert knowledge for Azure Test Plans development including limits & quotas, security, and integrations & coding patterns. Use when configuring test run custom fields, data retention, permissions, access levels, or tcm.exe automation, and other Azure Test Plans related development tasks. Not for Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), Azure App Testing (use azure-app-testing), Azure Boards (use azure-boards).

Expert knowledge for Azure App Service development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when choosing App Service plans/ASE, configuring VNet/custom domains/certs, CI/CD slots, or managed identity access, and other Azure App Service related development tasks. Not for Azure Functions (use azure-functions), Azure Spring Apps (use azure-spring-apps), Azure Static Web Apps (use azure-static-web-apps), Azure Service Fabric (use azure-service-fabric).

Expert knowledge for Azure Cloud Shell development including troubleshooting, limits & quotas, and security. Use when debugging Cloud Shell storage/connectivity, session limits, required storage accounts, or private VNet access, and other Azure Cloud Shell related development tasks. Not for Azure Portal (use azure-portal), Azure Resource Manager (use azure-resource-manager).

Expert knowledge for Azure Payment Hsm development including troubleshooting, best practices, decision making, architecture & design patterns, security, and configuration. Use when configuring Payment HSM VNets/FastPath, payShield Manager access, HA/DR topologies, SKUs, or traffic inspection, and other Azure Payment Hsm related development tasks. Not for Azure Dedicated HSM (use azure-dedicated-hsm), Azure Cloud Hsm (use azure-cloud-hsm), Azure Key Vault (use azure-key-vault), Azure Information Protection (use azure-information-protection).

Expert knowledge for Azure VPN Gateway development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring S2S/P2S tunnels, IPsec/IKE/BGP, active-active gateways, NVA integrations, or cross-cloud VPNs, and other Azure VPN Gateway related development tasks. Not for Azure Virtual WAN (use azure-virtual-wan), Azure Virtual Network (use azure-virtual-network), Azure ExpressRoute (use azure-expressroute), Azure Virtual Network Manager (use azure-virtual-network-manager).

在创造之前先进行解构，突破当前限制的幻觉。当需要批判性思维、假设挑战或可能性扩展时调用。