Antony Sure

Automatically generates API documentation and changelogs from your codebase and commit history.

Context rot prevention and subagent orchestration rules. Enforces clean context windows, file-based state, and delegation patterns. Auto-invoked during any Bayes Ship execution phase.

Enforces complete output during implementation tasks to prevent lazy coding practices.

REST API endpoint design, request/response patterns, versioning, error handling, and authentication patterns. Use during architecture and implementation phases. Source: everything-claude-code.

Build AI agents using LangChain's create_agent, tools, and middleware patterns.

Define system architecture based on approved PRD and research, producing comprehensive documentation.

Complete a feature branch with flexible merge options and automated cleanup.

Manage Git worktrees for isolated feature development and testing.

UI audit and upgrade skill that identifies design issues and suggests structured fixes.

Eval-driven development framework for AI features to ensure quality and reliability.

React and Next.js patterns for state management, component architecture, rendering, forms, and data fetching. Use when implementing frontend tasks. Source: everything-claude-code.

API design, query optimization, repository/service layer patterns for Node.js, Express, and Next.js backends. Use when implementing backend tasks. Source: everything-claude-code.

Bayes Ship is an end-to-end product delivery system for Claude Code, streamlining the journey from idea to deployed prototype.

Implement human-in-the-loop approval flows and custom middleware with LangChain.

Create isolated git worktrees for feature implementation with a verified test baseline.

Investigates a specific tech area based on project requirements. Writes findings to a research file.

Systematic bug diagnosis and fix using a structured 4-phase approach.

Create atomic execution plans for specific project phases with detailed task breakdowns.

Execute plans with fresh subagents using TDD and a mandatory two-stage review process.

Enhance frontend design with a premium skill that ensures unique layouts, typography, and motion.

Stage 2 of two-stage review. Reviews code style, patterns, bugs, security, test quality. Only runs AFTER spec compliance passes.

Configure preferences for the Bayes Ship framework with customizable settings.

Evidence-based verification pattern. Never trust "it works" without running actual checks. Verify every acceptance criterion against observable behavior. Use before marking any task or phase as complete.

Build Retrieval-Augmented Generation pipelines for effective document retrieval and context-based responses.

WCAG accessibility patterns: ARIA labels, keyboard navigation, screen reader support, color contrast, focus management. Use during QA phase for any product with a UI. Source: everything-claude-code.

Automate deployments to Railway, Vercel, and other platforms with built-in checks.

Automate production deployments with a comprehensive checklist and health verification.

Systematic 4-phase root cause analysis. Reproduce, hypothesize, test, confirm. Includes defense-in-depth considerations.

Spawn parallel research subagents to investigate tech choices and libraries based on requirements.

Display a comprehensive progress dashboard for project tracking.

Establishes universal coding conventions for TypeScript, JavaScript, React, and Node.js.

Enforces RED-GREEN-REFACTOR TDD cycle during implementation. Write the failing test first, watch it fail, write minimal code, watch it pass, commit. Code written before tests must be deleted and restarted. Use when writing any implementation code within the Bayes Ship pipeline.

Implement persistent memory and checkpointers for LangGraph agents to enhance conversation history and session durability.

Ensures comprehensive test coverage and performs AI-specific regression testing.

Atomic Planning is a task decomposition methodology for Bayes Ship that streamlines project planning.

Extracts product requirements through structured Q&A and generates CONTEXT.md.

Verification-before-completion agent. Runs actual checks against acceptance criteria. Evidence over claims.

Automate comprehensive QA verification for your projects with Ship Test.

AI regression testing for model output drift, prompt sensitivity, and embedding consistency.

Trigger a manual code review of recent changes with a two-stage process.

Writes code following TDD discipline. Receives a single task, writes failing test first, implements minimal code, reports status signal.

Patterns for building agentic systems to enhance AI-powered product features.

Ensures PRD documents are complete, clear, and free of scope creep before user review.

Automate your build process with fully autonomous or semi-autonomous modes.

Implement a two-stage code review process to ensure spec compliance and code quality.

Automated security scanning against OWASP Top 10 vulnerabilities and secret detection.

A premium UI aesthetic designed for fintech and professional tools, emphasizing trust and quality.

Minimalist Skill offers a clean, editorial-style UI aesthetic for content-heavy applications.

4-phase root cause debugging process. Gather evidence, form hypotheses, test hypotheses, confirm root cause. Use for any bug diagnosis within the Bayes Ship pipeline. Includes defense-in-depth and condition-based-waiting techniques.

Facilitates interactive requirements gathering through structured Q&A with users.

Create complex, stateful AI workflows using LangGraph's StateGraph for multi-step processes.

Creates atomic execution plans with file decomposition, task sizing, model routing, TDD blocks, and wave grouping.

Manage package versions and dependencies for the LangChain ecosystem in Python and TypeScript.

Designs system architecture from PRD and research. Produces ARCHITECTURE.md, data model, API contracts, ADRs.

Consolidates research files into a unified RESEARCH.md with clear recommendations and trade-offs.

Initialize a new Bayes Ship product project quickly and efficiently.

Generate a structured PRD from discovery and research outputs with automated review.

Resume from the last checkpoint after a session restart or compaction.

Ensures implementation strictly adheres to specifications, identifying missing requirements and over-building.