Claude Skills by Notysoty

Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.

Writes a high-quality CLAUDE.md, .cursorrules, or .windsurfrules file that gives a coding agent the right project context, conventions, and constraints to work effectively.

Designs an eval suite for an LLM agent or pipeline including success metrics, trajectory scoring, LLM-as-judge setup, and regression test cases.

Writes a complete product spec for an AI-powered feature including user stories, model requirements, fallback behavior, and evaluation criteria.

Generates OpenAPI-compatible documentation for REST API endpoints from code or route definitions.

Designs RESTful API endpoints following OpenAPI spec and industry best practices.

Reads a codebase or system description and produces a clear, structured architecture overview with diagrams.

Takes a long-form article and repurposes it into multiple formats: tweet thread, LinkedIn post, TL;DR, and key quotes.

Designs a secure authentication and authorization flow for any application, covering login, sessions, roles, and edge cases.

Generates a detailed, SEO-optimized blog post outline with H2/H3 structure, key points per section, and a hook.

Compares two versions of a codebase or API and flags all breaking changes with migration hints.

Systematically diagnoses bugs by tracing execution flow and identifying root causes vs symptoms.

Recommends the right caching layer, TTL strategy, and invalidation approach for any application bottleneck.

Maintains and formats a CHANGELOG.md following Keep a Changelog conventions from git history or PR list.

Runs a systematic checklist review on any code diff or file, covering correctness, security, performance, and readability.

Reviews database schemas for normalization issues, missing indexes, naming inconsistencies, and scalability risks.

Generates production-ready docker-compose.yml files for any application stack.

Audits a codebase or docs folder and lists everything that is undocumented, outdated, or unclear.

Systematically identifies edge cases and boundary conditions for any function, API, or user flow.

Parses raw error logs and produces a concise, prioritized summary of unique issues with root cause hints.

Generates a comprehensive FAQ section for any product, API, or documentation page.

Diagnoses why tests pass inconsistently and suggests fixes for timing, ordering, and state isolation issues.

Reviews web forms for usability issues — field ordering, validation messages, error states, and accessibility.

Generates conventional commit messages from staged changes or a diff.

Reviews an AI-generated response or LLM application output for factual risks, hallucination patterns, and confidence calibration issues.

Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.

Writes a blameless incident postmortem document from an incident timeline or Slack thread.

Takes a GitHub issue and produces a step-by-step implementation plan with file locations and code changes needed.

Rewrites landing page copy to be more compelling, benefit-focused, and conversion-optimized.

Converts a workflow description into a LangGraph node/edge graph with typed state, conditional routing, and human-in-the-loop checkpoints.

Audits an AI application for unnecessary token spend and recommends prompt caching, model routing, and token reduction techniques to cut costs.

Configures end-to-end tracing for an LLM application using OpenTelemetry with LangSmith, Langfuse, or Helicone — span naming, metadata tagging, latency thresholds, and cost tracking.

Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.

Step-by-step guidance for creating a new MCP server with FastMCP or the TypeScript SDK — tool definitions, resource handlers, error responses, and usage examples.

Writes clear migration guides for library upgrades, breaking API changes, or framework version bumps.

Condenses long articles, threads, or documents into concise, engaging newsletter-ready summaries.

Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.

Generates robust Playwright end-to-end tests for web pages and user flows.

Writes clear, thorough pull request descriptions from a diff or list of changes.

Reviews LLM application prompts and input handling for direct and indirect prompt injection vulnerabilities, then writes defensive scaffolding.

Improves AI prompts to be clearer, more specific, and produce more consistent outputs.

Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.

Given a document type and retrieval goal, recommends the optimal chunking strategy for a RAG pipeline to minimize retrieval failures.

Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.

Analyzes React components for performance, accessibility, and modern hook usage.

Generates a professional, comprehensive README.md for any project from its codebase or description.

Creates a safe, step-by-step plan to refactor messy code without breaking existing behavior.

Generates clear, user-friendly release notes from a git log or list of PRs.

Reviews HTML/CSS or component code for responsive design issues across mobile, tablet, and desktop breakpoints.

Generates a concise, copy-paste-ready quickstart guide for any SDK or library.