ai-kit

Synthesizes the chosen (or only) candidate flow into the canonical execution-context Markdown + JSON artifacts under .claude/clarifications/. Activates after flow-detector returns a single candidate, or after flow-selector confirms the user's choice. Never asks follow-up questions.

Analyzes a task description plus the surrounding codebase and produces a list of candidate end-to-end flows. Activates when a developer describes a task using vague verbs (send, notify, sync, handle, process, integrate) without specifying entity, trigger, or recipient. Returns 1 candidate when the flow is unambiguous, 2+ when multiple plausible interpretations exist. Each candidate is a complete proposed execution context, never a question.

Presents 2+ candidate flows from flow-detector and asks the user to pick one. Issues exactly one AskUserQuestion. Never activates when flow-detector returns a single candidate, and never asks cluster-by-cluster questions.

This skill activates when managing environment variables, configuring .infisical.json, organizing workspace environments, or discussing secret management patterns with Infisical CLI. It provides conventions for secret naming, folder organization, auth selection, and local development workflows.

This skill activates when configuring CI/CD pipelines, writing GitHub Actions workflows, GitLab CI configs, Dockerfiles, Kubernetes manifests, or serverless deployment configs that need secret injection. It provides patterns for integrating Infisical into build and deployment pipelines.

This skill activates when detecting hardcoded strings that look like API keys or credentials, creating .env files, referencing process.env or os.environ without Infisical, or working with configuration files that contain sensitive values. It enforces secret hygiene practices and recommends moving secrets to Infisical.

This skill should be used when the user mentions "worktree", "wt", "new branch workspace", "parallel development", "feature branch setup", "work on multiple branches", "separate workspace for branch", "docker port conflict", "database isolation", "worktreeinclude", "env isolation", or wants to manage git worktrees for parallel feature development.

Auto-enforce authentication security best practices. Activates when implementing password policies, rate limiting, session security, CSRF protection, or security headers in auth flows.

Auto-enforce Better Auth implementation patterns. Activates when setting up authentication, configuring providers, creating auth forms, or implementing session management in React applications.

This skill should be used when the user asks to "plan a feature", "prepare for dev loop", "structure TDD approach", "break down this task", "create development plan", or when generating structured prompts for iterative development. Creates dev-loop-ready plans with TDD phases, file tables, code snippets, and framework-specific guidance.

Automatically validate and fix Django import patterns to use absolute modular imports with aliases. Use when writing imports, creating new Python files, modifying existing files, or seeing import statements in code.

This skill should be used when the user asks to "create a migration", "run makemigrations", "modify a model field", "rename a column", or mentions "schema change", "alter table", "database migration". Validates migrations are production-safe.

This skill should be used when the user asks to "create a model", "add a Django model", "create database table", "add entity", "define schema", or when writing class definitions inheriting from models.Model. Validates BaseModel inheritance pattern.

This skill should be used when the user asks to "optimize queries", "fix slow queries", "improve performance", "detect N+1", "add indexes", or when writing Django ORM queries that access related objects. Detects and fixes performance issues.

This skill should be used when the user asks to "write tests first", "run TDD", "verify red phase", "check failing tests", or when practicing test-driven development. Ensures tests fail before implementation.

This skill should be used when the user asks to "create an API endpoint", "add a view", "write a viewset", "create a serializer", or when writing Django REST Framework code. Enforces security requirements (permissions, authentication, rate limiting).

This skill should be used when the user asks to "write tests", "generate tests", "check coverage", "add test cases", or when completing features and saying "done", "finished", "ready for review". Suggests tests for 90%+ coverage.

This skill should be used when the user asks to "check tests", "validate tests", "review test quality", "verify test coverage", or when writing test files or running pytest. Ensures tests are meaningful.

This skill should be used when the user asks to "log a failure", "remember this mistake", "add to failure log", "what mistakes to avoid", "check failure log", or when a mistake is detected that should be recorded for future reference. Manages persistent failure memory.

Provides Fastlane configuration patterns for Flutter apps including iOS and Android lanes, code signing with match, CI/CD integration with GitHub Actions, and environment management. Use when user asks about Fastlane setup, deployment automation, code signing, or CI/CD for mobile.

Provides Flutter app architecture patterns with feature-first structure, clean architecture, and state management (Bloc, Riverpod, Provider). Use when user asks about Flutter project structure, state management selection, dependency injection, or designing Flutter app architecture.

Provides App Store and Google Play publishing requirements, metadata management, screenshot specifications, review guidelines, and compliance requirements. Use when user asks about publishing apps, store requirements, app review, or store metadata.

This skill activates when working with Cloudflare Workers bindings like D1, KV, R2, Durable Objects, or environment variables. It provides patterns for database access, caching, file storage, and secrets management.

This skill activates when writing Hono routes, handlers, middleware, or discussing Hono application architecture. It provides patterns for routing, middleware composition, error handling, and TypeScript integration.

This skill activates when setting up Hono RPC client, configuring type-safe API calls, or discussing client-server type sharing. It provides patterns for the hc client, type inference, and React Query integration.

This skill activates when writing form validation, request validation, or Zod schemas in Hono. It provides patterns for validating JSON bodies, query parameters, path parameters, and headers with proper error handling.

This skill should be used when the user asks to "create barrel exports", "add index.ts", "organize exports", "create entity", "add DTO", "create service", or when adding files to NestJS module directories. Auto-maintains barrel exports.

Automatically enforce absolute imports from barrel exports in NestJS. Use when writing imports, creating TypeScript files, or organizing NestJS module structure.

Automatically validate React/Next.js components meet WCAG 2.1 AA standards. Use when creating components, forms, buttons, modals, navigation, or any interactive UI elements.

Automatically enforce consistent import patterns using Next.js path aliases and proper organization. Use when writing imports, creating new files, or organizing code structure.

This skill should be used when the user asks to "create a form", "add validation", "handle form submission", "use React Hook Form", or when creating login, signup, or data entry forms. Enforces React Hook Form + Zod pattern.

Automatically validate Vue 3/Nuxt.js components meet WCAG 2.1 AA standards. Use when creating components, forms, buttons, modals, navigation, or any interactive UI elements.

Automatically enforce consistent import patterns using Nuxt.js ~/ path aliases and proper organization. Use when writing imports, creating new Vue/TS files, or organizing code structure.

This skill should be used when the user asks to "create a form", "add validation", "handle form submission", "use VeeValidate", or when creating login, signup, or data entry forms in Nuxt.js/Vue 3. Enforces VeeValidate + Zod pattern.

Provides personalized assistance based on engineer's onboarding profile. Activates when engineer asks "how do I", "where should I", "what's the pattern for", shows confusion about conventions, or writes code that doesn't match project patterns. Reads .claude/onboard-profile.local.md for context.

TanStack AI patterns for unified AI SDK integration. Activates when implementing AI chat, streaming responses, or AI-powered features. NOTE: Alpha library - API may change.

TanStack DB patterns for client-first reactive data stores. Activates when implementing offline-first apps, local-first data, or reactive client databases. NOTE: Beta library - API may change.

TanStack DevTools patterns for debugging and development. Activates when setting up development tools, debugging queries, or configuring developer experience in React applications.

Auto-enforce TanStack Form best practices with Zod validation. Activates when creating forms, handling form state, implementing validation, or building input components in React applications.

TanStack Pacer patterns for rate limiting, debouncing, and throttling. Activates when implementing search inputs, API rate limiting, or performance optimization. NOTE: Beta library - API may change.