racecraft-lab

racecraft-lab/Paddock

Command Claude Code

Error handling review — silent failure detection, catch block analysis, error logging.

racecraft-lab/Paddock

Command Claude Code

Comprehensive code review using specialized agents — orchestrates code, comments, tests, errors, types, and simplify agents sequentially.

racecraft-lab/Paddock

Command Claude Code

Code simplification suggestions — clarity, unnecessary complexity, redundant abstractions. Advisory only.

racecraft-lab/Paddock

Command Claude Code

Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.

racecraft-lab/Paddock

Command Claude Code

Type design analysis — encapsulation, invariant expression, usefulness, and enforcement.

racecraft-lab/Paddock

Agent Claude Code

Auto-generated from all feature plans. Last updated: 2026-03-12.

racecraft-lab/Paddock

Agent Claude Code

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

racecraft-lab/Paddock

Agent Claude Code

Generate a custom checklist for the current feature based on user requirements.

racecraft-lab/Paddock

Agent Claude Code

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

racecraft-lab/Paddock

Agent Claude Code

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

racecraft-lab/Paddock

Agent Claude Code

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

racecraft-lab/Paddock

Agent Claude Code

Execute the implementation planning workflow using the plan template to generate design artifacts.

racecraft-lab/Paddock

Agent Claude Code

Create or update the feature specification from a natural language feature description.

racecraft-lab/Paddock

Agent Claude Code

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

racecraft-lab/Paddock

Agent Claude Code

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

racecraft-lab/Paddock

Command Claude Code

Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).

racecraft-lab/Paddock

Command Claude Code

Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.

racecraft-lab/Paddock

Command Claude Code

Generate a custom checklist for the current feature based on user requirements.

racecraft-lab/Paddock

Command Claude Code

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

racecraft-lab/Paddock

Skill Claude CodeCodex

Interact with Paddock — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via Paddock APIs.

racecraft-lab/racecraft-plugins-public

Plugin Claude Code

Bundles 12 skills, 16 agents, 3 hooks, 3 MCP servers · 1,379 tokens together

Autonomous Spec-Driven Development powered by GitHub SpecKit. Includes archive-aware autopilot startup, SDD coaching, multi-spec project management, and a fully autonomous workflow executor with multi-agent clarification consensus.

racecraft-lab/racecraft-plugins-public

Plugin Claude Code

Bundles 2 skills · 294 tokens together

Ask Jev for typed judgments with calibrated probabilities instead of parsing prose, through TypeSafe directly or OpenRouter's Decisions API, with the backend chosen explicitly.