GSD

Analyzes codebases and generates structured documentation for various focus areas.

A powerful collection of tools for efficient AI-driven development and context management.

Verifies cross-phase integration and end-to-end workflows in applications.

Synthesizes research outputs from multiple agents into a cohesive summary for roadmap creation.

Automates the writing and updating of project documentation based on specific assignments.

Conducts a retroactive audit of AI evaluation coverage against planned strategies.

Automated code reviewer that identifies bugs, security issues, and code quality problems.

Creates executable phase plans with task breakdown and dependency analysis.

Verifies phase goal achievement through goal-backward analysis, ensuring codebase aligns with promised outcomes.

Conducts a thorough visual audit of frontend code against design standards, producing actionable insights.

Researches pre-planning phases and produces structured documentation for planners.

Automate bug investigation using a scientific approach and manage debug sessions effectively.

Generates tests to fill Nyquist validation gaps and verifies coverage for phase requirements.

Executes GSD plans with atomic commits and deviation handling.

Analyzes developer session messages to create a detailed behavioral profile across 8 dimensions.

Automates code fixes based on review findings, ensuring intelligent and atomic updates.

Researches gray area decisions and provides structured comparison tables.

Analyzes codebases and generates structured intelligence files for project insights.

Generates UI-SPEC.md design contracts for frontend phases based on upstream artifacts.

Classifies planning documents into categories like ADR, PRD, SPEC, or DOC, ensuring accurate extraction of information.

Analyzes codebases to extract structured assumptions for specific phases.

Manages multi-cycle debugging sessions, ensuring efficient checkpoint handling and agent spawning.

Consolidates classified planning documents into a unified context while managing conflicts.

Researches business domain context for AI systems, identifying evaluation criteria and failure modes.

Interactive decision matrix for selecting the right AI/LLM framework based on user needs.

Automates the research of AI frameworks to deliver implementation-ready guidance and best practices.

Validates UI-SPEC.md design contracts against quality dimensions to ensure design integrity.

Audits code against threat mitigations in PLAN.md, producing a detailed SECURITY.md report.

Analyzes codebase patterns and generates a mapping file for new files.

Researches domain ecosystems to inform project roadmaps.

Creates detailed project roadmaps by mapping requirements to phases with clear success criteria.

Verifies phase plans will achieve their goals before execution through goal-backward analysis.

Designs structured evaluation strategies for AI phases, ensuring robust assessment and monitoring.