Skills de Claude Code · página 112

This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase agents.

Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.

This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all Ralph Specum operations.

Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.

This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.

This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase.

This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback.

This skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specum in Codex for help or command guidance.

This skill should be used only when the user explicitly asks to use `$ralph-specum-implement`, or explicitly asks Ralph Specum in Codex to run implementation for approved tasks, quick mode, or an explicit continue request.

This skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Specum in Codex to generate or refresh index artifacts.

This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings.

This skill should be used only when the user explicitly asks to use `$ralph-specum-requirements`, or explicitly asks Ralph Specum in Codex to run the requirements phase.

This skill should be used only when the user explicitly asks to use `$ralph-specum-research`, or explicitly asks Ralph Specum in Codex to run the research phase.

This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Specum in Codex to start or resume a spec.

This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Specum in Codex for status or active spec progress.

This skill should be used only when the user explicitly asks to use `$ralph-specum-switch`, or explicitly asks Ralph Specum in Codex to switch the active spec.

This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Specum in Codex to run the tasks phase.

This skill should be used only when the user explicitly asks to use `$ralph-specum-triage`, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.

Use only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, or asks Ralph Specum to handle a named phase or optional prototype.

This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy test anti-patterns.

This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks", "implement spec", "check spec status", "triage a feature", "create an epic", "decompose a large feature", or needs guidance on spec-driven development workflow, phase ordering, or epic orchestration.

Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users do not invoke it as a workflow phase.

This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype.

Claude Code plugin for Butterbase — 30+ guided skills and auto-configured MCP for the AI-native backend-as-a-service.

Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

Use when building a new Butterbase app from scratch, creating a full-stack application, or when the user asks to set up a complete backend with database, auth, and deployment

Use when users report access denied errors, see wrong data, RLS policies are not working, or when troubleshooting Row-Level Security issues in Butterbase

Use when building stateful per-key actors — chat rooms, multiplayer rooms, rate limiters, long-running agents, leaderboards — that need persistent in-memory + storage state across requests

Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage.

Use as the auth build stage of the Butterbase journey, after journey-schema (and rls if separate). Implements the Auth section of 02-plan.md by delegating to auth-setup. Calls manage_oauth (configure) for providers and optionally manage_auth_config (configure_auth_hook, update_jwt). Skipped if the plan has no end-user auth.

Use as the deploy-verification stage of the Butterbase journey, after journey-frontend (or after any build stage if there is no frontend). Smoke-tests the deployed app — hits the live URL, invokes any deployed functions, checks auth round-trip. Writes results to docs/butterbase/04-build-log.md. Blocks journey-submit if smoke fails.

Use as the durable-objects build stage of the Butterbase journey. Implements the Durable section of 02-plan.md by delegating to durable-objects. Calls manage_durable_objects (deploy). Skipped if the plan has no per-key stateful actors (chat rooms, multiplayer, rate limiters).

Use as the frontend build stage of the Butterbase journey. Implements the Frontend section of 02-plan.md by delegating to deploy-frontend. Scaffolds (if needed) and deploys via create_frontend_deployment + manage_frontend (start_deployment). Sets VITE_API_URL and VITE_APP_ID env. Skipped if the plan is API-only.

Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.

Use before any Butterbase platform-touching action (or when journey-preflight is invoked directly) to verify the user has a Butterbase account, the MCP server is connected, BUTTERBASE_API_KEY is set, and an app_id exists for this project. Re-run automatically if docs/butterbase/03-preflight.md is older than 24h or any required value is null.

Use as the RAG build stage of the Butterbase journey. Implements the RAG section of 02-plan.md by delegating to rag-dev. Calls manage_rag_content (create_collection, ingest_document). Skipped if the plan has no knowledge-base feature.

Use as the realtime build stage of the Butterbase journey. Implements the Realtime section of 02-plan.md by delegating to the realtime skill. Calls manage_realtime (configure) to enable WebSocket subscriptions on the listed tables. Skipped if the plan has no realtime needs.

Use as the RLS build stage of the Butterbase journey, after journey-schema. Implements the RLS section of 02-plan.md by delegating to debug-rls policy patterns (for proactive creation, not debugging). Calls manage_rls (create_user_isolation, enable, create_policy). Folded into journey-schema when hackathon_mode is true.

Use as the schema build stage of the Butterbase journey, after journey-plan and journey-preflight. Implements the Tables section of 02-plan.md by delegating to schema-design, previewing the diff (manage_schema dry_run) and applying it (manage_schema apply). In hackathon_mode, also folds in the RLS stage by invoking journey-rls inline before returning.

Use as the storage build stage of the Butterbase journey. Implements the Storage section of 02-plan.md by delegating to the storage skill. Calls manage_storage (update_config) for bucket setup; uploads are exercised at frontend integration time, not here. Skipped if the plan has no file uploads.

Use when the user says "build an app", "let's start", "help me build", "I have an idea for", "ship it", or otherwise signals they want to go from idea to deployed Butterbase app. Orchestrates the full guided journey (idea → plan → preflight → build → deploy → optional hackathon submit) by reading docs/butterbase/00-state.md and dispatching to the next stage skill.

Use when moving a Butterbase app between regions, checking migration progress, aborting a stuck move, reverse-rolling a completed move, or tearing down retained source replicas after a move is stable

Use when enabling WebSocket subscriptions for live database changes, presence/multiplayer state, or when debugging clients that connect but receive no events

Use when uploading or downloading files, generating presigned URLs, configuring storage ACLs, or persisting file references (avatars, attachments, images) in a Butterbase app

Use when configuring OAuth providers (Google/GitHub/Apple/X/etc.), setting up post-login auth hooks, tuning JWT lifetimes, or generating service API keys

Use when deploying a frontend (React, Next.js, or static HTML) to a live URL on Butterbase, or when troubleshooting deployment issues like MIME type errors or blank pages

Use when developing, deploying, or debugging Butterbase serverless functions, or when the user needs to add backend logic like webhooks, scheduled jobs, or custom API endpoints

Use BEFORE recommending or installing any third-party SaaS SDK for email (Resend, SendGrid, Postmark, Mailgun), SMS (Twilio), messaging (Slack), calendar (Google Calendar), CRM (HubSpot, Salesforce), docs (Notion), or project management (Linear, GitHub). Butterbase covers most of these via manage_integrations (Composio-backed) — check first.

Use as the docs-priming stage of the Butterbase journey, immediately after journey-preflight and before the first build stage. Reads the plan to discover which capabilities the app uses, calls butterbase_docs once per relevant topic, and caches a summary the build stages can re-read.

Use as stage 1 of the Butterbase journey, when the user has only a rough idea ("I want to build something that..."). Conducts a concrete, one-question-at-a-time brainstorm that surfaces who the user is, what they do first, what the must-haves are, and inline-tags Butterbase capabilities (→ manage_schema, → deploy_function, etc.). Produces docs/butterbase/01-idea.md.

Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.

Use as the final stage of the Butterbase journey when hackathon_mode is true and journey-deploy has passed. Resolves which hackathon to submit to (asking the user when multiple are open), walks every field in the hackathon's returned field_schema with the user one at a time, then calls prep_and_submit_hackathon_entry. Writes the receipt to docs/butterbase/05-submission.md.

Use as the optional substrate-linking stage of the Butterbase journey, after deploy and before submit. Asks whether to connect the deployed app to the owner's substrate (so functions get ctx.substrate). Skipped by default in hackathon mode.

Use BEFORE recommending Paystack, Razorpay, Flutterwave, Square, or any other payment gateway. Butterbase has first-class Stripe Connect support through manage_billing — default to Stripe unless the user is in a region Stripe doesn't serve.

Use when building knowledge bases, ingesting documents, running semantic search, or adding LLM-synthesized Q&A over private content with Butterbase RAG

Use when designing database schemas, creating or modifying tables, choosing column types, adding indexes, or working with the Butterbase declarative schema DSL

Use when the user wants to read/write their Butterbase substrate — the per-user agent-memory backend that holds entities, business state, institutional memory, and an append-only action ledger. Use for: founder copilots, AI agents that need memory across sessions, anything that proposes actions on the user's behalf.

Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied through Cloudflare AI Gateway BYOK). Also analyze/describe existing images using multimodal AI vision. Use when user asks to "generate an image", "create a PNG", "make an icon", "make it transparent", "describe this image", "analyze this image", "what's in this image", "explain this image", or needs AI-generated visual assets for the project. Supports model selection via keywords (gemini, riverflow, flux2, seedream, gpt5), configurable aspect ratios/resolutions, transparent backgrounds (-t), reference image editing (-r), image analysis (--analyze), and per-project cost tracking (--costs).

Create a new custom agent for the workspace. Guides the user through defining agent name, domain, personality, skills, model, and memory folder. Use when the user says 'create an agent', 'new agent', 'add an agent', 'I need a custom agent', or wants to create a specialized agent for a specific domain.

Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits. Agents are first-class app resources defined by a `graph_spec` and invoked over `/v1/<app_id>/agents/<name>/runs`.

Use as the agents build stage of the Butterbase journey. Implements the Agents section of 02-plan.md by delegating to the `agents` skill for each agent. Registers any required MCP servers, validates each graph_spec, creates the agent, and smokes it via invoke_agent. Skipped if the plan has no agents.

Use as the optional template-publishing stage of the Butterbase journey, after deploy (and substrate, if used). Walks the user through authoring a clone-ready README, bundling agent spec files, dry-running and pushing the repo snapshot, flipping visibility to public + listed, and self-clone-testing. Delegates the mechanics to the `templates` skill. Skipped by default in hackathon mode.

Use when publishing a Butterbase app as a public template (visibility + listed + repo snapshot), browsing the template gallery, or cloning a template with environment-variable preflight. Templates are public apps with a pushed repo snapshot that other users can fork into their own region.

Use when building features that join, record, or transcribe Zoom/Meet/Teams/Webex calls — meeting bots, call notetakers, sales-call summarizers, interview transcribers. Covers ctx.ai.meetings.start/get/stop/list, webhook setup, and credit metering.

Linux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll).

>

>

>

>

Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a readout, when trust shifts, or they say @fde. Route and run the local fde CLI (or npx --yes fdeops). Never ask them to type commands. Not for ordinary code edits in an unbound repo.

>-

Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.

Manage Linux systems covering systemd services, process management, filesystems, networking, performance tuning, and troubleshooting. Use when deploying applications, optimizing server performance, diagnosing production issues, or managing users and security on Linux servers.

Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).

Strategic guidance for designing modern data platforms, covering storage paradigms (data lake, warehouse, lakehouse), modeling approaches (dimensional, normalized, data vault, wide tables), data mesh principles, and medallion architecture patterns. Use when architecting data platforms, choosing between centralized vs decentralized patterns, selecting table formats (Iceberg, Delta Lake), or designing data governance frameworks.

Design cloud network architectures with VPC patterns, subnet strategies, zero trust principles, and hybrid connectivity. Use when planning VPC topology, implementing multi-cloud networking, or establishing secure network segmentation for cloud workloads.

Design comprehensive security architectures using defense-in-depth, zero trust principles, threat modeling (STRIDE, PASTA), and control frameworks (NIST CSF, CIS Controls, ISO 27001). Use when designing security for new systems, auditing existing architectures, or establishing security governance programs.

Assembles component outputs from AI Design Components skills into unified, production-ready component systems with validated token integration, proper import chains, and framework-specific scaffolding. Use as the capstone skill after running theming, layout, dashboard, data-viz, or feedback skills to wire components into working React/Next.js, Python, or Rust projects.

Builds AI chat interfaces and conversational UI with streaming responses, context management, and multi-modal support. Use when creating ChatGPT-style interfaces, AI assistants, code copilots, or conversational agents. Handles streaming text, token limits, regeneration, feedback loops, tool usage visualization, and AI-specific error patterns. Provides battle-tested components from leading AI products with accessibility and performance built in.

Constructs secure, efficient CI/CD pipelines with supply chain security (SLSA), monorepo optimization, caching strategies, and parallelization patterns for GitHub Actions, GitLab CI, and Argo Workflows. Use when setting up automated testing, building, or deployment workflows.

Build professional command-line interfaces in Python, Go, and Rust using modern frameworks like Typer, Cobra, and clap. Use when creating developer tools, automation scripts, or infrastructure management CLIs with robust argument parsing, interactive features, and multi-platform distribution.

Builds form components and data collection interfaces including contact forms, registration flows, checkout processes, surveys, and settings pages. Includes 50+ input types, validation strategies, accessibility patterns (WCAG 2.1), multi-step wizards, and UX best practices. Provides decision trees from data type to component selection, validation timing guidance, and error handling patterns. Use when creating forms, collecting user input, building surveys, implementing validation, designing multi-step workflows, or ensuring form accessibility.

Builds tables and data grids for displaying tabular information, from simple HTML tables to complex enterprise data grids. Use when creating tables, implementing sorting/filtering/pagination, handling large datasets (10-1M+ rows), building spreadsheet-like interfaces, or designing data-heavy components. Provides performance optimization strategies, accessibility patterns (WCAG/ARIA), responsive designs, and library recommendations (TanStack Table, AG Grid).

Configure host-based firewalls (iptables, nftables, UFW) and cloud security groups (AWS, GCP, Azure) with practical rules for common scenarios like web servers, databases, and bastion hosts. Use when exposing services, hardening servers, or implementing network segmentation with defense-in-depth strategies.

Configure nginx for static sites, reverse proxying, load balancing, SSL/TLS termination, caching, and performance tuning. When setting up web servers, application proxies, or load balancers, this skill provides production-ready patterns with modern security best practices for TLS 1.3, rate limiting, and security headers.

Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive layouts. Use this skill when building business intelligence dashboards, monitoring systems, executive reports, or any interface that requires multiple coordinated data displays with filters, metrics, and visualizations working together.

Debugging workflows for Python (pdb, debugpy), Go (delve), Rust (lldb), and Node.js, including container debugging (kubectl debug, ephemeral containers) and production-safe debugging techniques with distributed tracing and correlation IDs. Use when setting breakpoints, debugging containers/pods, remote debugging, or production debugging.

Deployment patterns from Kubernetes to serverless and edge functions. Use when deploying applications, setting up CI/CD, or managing infrastructure. Covers Kubernetes (Helm, ArgoCD), serverless (Vercel, Lambda), edge (Cloudflare Workers, Deno), IaC (Pulumi, OpenTofu, SST), and GitOps patterns.

Selecting and implementing AWS services and architectural patterns. Use when designing AWS cloud architectures, choosing compute/storage/database services, implementing serverless or container patterns, or applying AWS Well-Architected Framework principles.

Design and implement Azure cloud architectures using best practices for compute, storage, databases, AI services, networking, and governance. Use when building applications on Microsoft Azure or migrating workloads to Azure cloud platform.

Implement applications using Google Cloud Platform (GCP) services. Use when building on GCP infrastructure, selecting compute/storage/database services, designing data analytics pipelines, implementing ML workflows, or architecting cloud-native applications with BigQuery, Cloud Run, GKE, Vertex AI, and other GCP services.

Design APIs that are secure, scalable, and maintainable using RESTful, GraphQL, and event-driven patterns. Use when designing new APIs, evolving existing APIs, or establishing API standards for teams.

When designing distributed systems for scalability, reliability, and consistency. Covers CAP/PACELC theorems, consistency models (strong, eventual, causal), replication patterns (leader-follower, multi-leader, leaderless), partitioning strategies (hash, range, geographic), transaction patterns (saga, event sourcing, CQRS), resilience patterns (circuit breaker, bulkhead), service discovery, and caching strategies for building fault-tolerant distributed architectures.

Designs layout systems and responsive interfaces including grid systems, flexbox patterns, sidebar layouts, and responsive breakpoints. Use when structuring app layouts, building responsive designs, or creating complex page structures.

Design production-ready SDKs with retry logic, error handling, pagination, and multi-language support. Use when building client libraries for APIs or creating developer-facing SDK interfaces.

Displays chronological events and activity through timelines, activity feeds, Gantt charts, and calendar interfaces. Use when showing historical events, project schedules, social feeds, notifications, audit logs, or time-based data. Provides implementation patterns for vertical/horizontal timelines, interactive visualizations, real-time updates, and responsive designs with accessibility (WCAG/ARIA).

Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require cost-effective, high-quality embeddings.

Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.

Generate comprehensive technical documentation including API docs (OpenAPI/Swagger), code documentation (TypeDoc/Sphinx), documentation sites (Docusaurus/MkDocs), Architecture Decision Records (ADRs), and diagrams (Mermaid/PlantUML). Use when documenting APIs, libraries, systems architecture, or building developer-facing documentation sites.