Claude Skills

Manage tech stack and architecture decisions

Create or update the product vision document

Production-ready FastAPI project scaffolding templates including directory structure, configuration files, settings management, dependency injection, MCP server integration, and development/production setup patterns. Use when creating FastAPI projects, setting up project structure, configuring FastAPI applications, implementing settings management, adding MCP integration, or when user mentions FastAPI setup, project scaffold, app configuration, environment management, or backend structure.

Conducts a deep, multi-round interview to clarify ambiguous requirements and produces a structured specification document. Automatically discovers requirement files and asks probing, non-obvious questions across technical implementation, UX/UI, trade-offs, edge cases, and architectural decisions.

Multi-format document parsing tools for PDF, DOCX, HTML, and Markdown with support for LlamaParse, Unstructured.io, PyPDF2, PDFPlumber, and python-docx. Use when parsing documents, extracting text from PDFs, processing Word documents, converting HTML to text, extracting tables from documents, building RAG pipelines, chunking documents, or when user mentions document parsing, PDF extraction, DOCX processing, table extraction, OCR, LlamaParse, Unstructured.io, or document ingestion.

Document chunking implementations and benchmarking tools for RAG pipelines including fixed-size, semantic, recursive, and sentence-based strategies. Use when implementing document processing, optimizing chunk sizes, comparing chunking approaches, benchmarking retrieval performance, or when user mentions chunking, text splitting, document segmentation, RAG optimization, or chunk evaluation.

Model routing configuration templates and strategies for cost optimization, speed optimization, quality optimization, and intelligent fallback chains. Use when building AI applications with OpenRouter, implementing model routing strategies, optimizing API costs, setting up fallback chains, implementing quality-based routing, or when user mentions model routing, cost optimization, fallback strategies, model selection, intelligent routing, or dynamic model switching.

Guided plan revision with impact analysis. Supports explore mode (discover what to change) and direct mode (apply known changes). Always shows impact before execution.

Stripe integration templates with reusable code for Checkout, Payment Intents, and Subscriptions. Use when implementing Stripe payments, building checkout flows, handling subscriptions, or integrating payment processing.

C++20 coding standards, naming conventions, concepts, ranges, constexpr, file organization, and Doxygen documentation practices for high-performance computing.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Phase 2 - Define the logic flow for each function

Validate that a JSON Schema is well-formed and conforms to the JSON Schema specification. Use when the user asks to check if a schema is valid, verify schema syntax, validate schema structure, or check a JSON Schema file for errors.

Capture user intent as structured work requests without executing. Use when user describes work to be done. Separates intent from execution. Writes to do-work/requests/ queue.

Comprehensive error handling patterns for robust applications including custom errors, error boundaries, recovery strategies, and user-facing error messages. Use this skill when designing error hierarchies, implementing React error boundaries, adding retry logic or fallbacks, creating API error responses, integrating error tracking (Sentry), or improving user error communication. Triggers on "error handling", "error boundary", "custom error", "retry logic", "graceful degradation", "error tracking", "Sentry", "user error message", "try-catch", "Result type", "circuit breaker".

Use this skill when capturing learnings from our work together, or when starting work that might benefit from past knowledge. Triggers on: memory, remember, what did we learn, library, save this, before planning, decisions.

Use when building or publishing Python packages with uv, including dist artifacts and pre-publish checks.

Use this skill for knowledge bounties — creating, claiming, or fulfilling bounty requests. Triggers on: bounty, reward, knowledge request, fulfill, claim bounty.