smicolon

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

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.

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Command Claude Code

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

smicolon/ai-kit

Agent Claude Code

System architect specialist supporting native Mermaid.js and Eraser.io diagram-as-code. Creates ERDs, flowcharts, system architecture, sequence diagrams, class diagrams, cloud diagrams, and BPMN/swimlane diagrams using text-based syntax.

smicolon/ai-kit

Command Claude Code

Create system architecture diagrams using native Mermaid.js or Eraser.io diagram-as-code.

smicolon/ai-kit

Agent Claude Code

Authentication architect for designing Better Auth implementations. Use for auth architecture, provider setup, security flows, and enterprise auth patterns.

smicolon/ai-kit

Command Claude Code

Add a new authentication provider to Better Auth.

smicolon/ai-kit

Command Claude Code

Initialize Better Auth with configuration and optional auth pages.

smicolon/ai-kit

Agent Claude Code

Pre-implementation clarification expert. Use when a developer has been handed a vague task and needs the scope nailed down before writing code. Detects whether the task has a single flow (explains and proceeds) or multiple flows (lists them and asks the user to pick one). Never asks cluster-by-cluster questions…

smicolon/ai-kit

Command Claude Code

Resolve ambiguity in a task before implementation. Detects whether the task has a single clear flow (explains and proceeds) or multiple flows (lists them and asks the user to pick one). Produces a structured execution context (Markdown + JSON) under .claude/clarifications/.

smicolon/ai-kit

Command Claude Code

Cancel active dev loop.

smicolon/ai-kit

Command Claude Code

Generate a structured TDD plan for dev-loop execution.

smicolon/ai-kit

Skill Claude CodeCodex

This skill should be used when the user asks to "plan a feature", "prepare for dev loop", "structure TDD approach", "break down this task", "create development plan", or when generating structured prompts for iterative development. Creates dev-loop-ready plans with TDD phases, file tables, code snippets, and…

smicolon/ai-kit

Agent Claude Code

Senior Django architect specializing in cookiecutter-django projects. Use for system design, data modeling, API endpoint planning, and architectural decisions for Django backends.

smicolon/ai-kit

Agent Claude Code

Expert Django developer for implementing production-ready features with absolute imports and company conventions.

smicolon/ai-kit

Agent Claude Code

Architect for large-scale Django projects using feature-based architecture with strong module isolation.

smicolon/ai-kit

Agent Claude Code

Security-focused code reviewer for Django applications checking vulnerabilities and convention compliance.

smicolon/ai-kit

Agent Claude Code

Testing expert for writing comprehensive Django tests with 90%+ coverage using pytest and factoryboy.