yunbow/ai-dev-os-plugin-claude-code

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Audits the health of the AI Dev OS 4-layer structure. Detects dependency rule violations (upper layers referencing lower layers), expiration, and coverage gaps. Used for monthly or quarterly periodic maintenance.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Checks code changes against AI Dev OS guidelines and automatically fixes violations. Based on benchmark Test 011: check+fix achieves +9.9 improvement vs report-only (+0.8). Supports git diff (default), branch comparison, and staged changes. Use --dry-run for report-only mode (no fixes applied).

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Supports the spiral evolution of AI Dev OS. Analyzes recent AI coding practices (commit history, review records) and generates update proposals for L1 philosophy and L2 principles. Used in monthly retrospectives or quarterly reviews.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Extracts rules from the gap between AI-generated code and ideal code. Used after code review to add new rules to AI Dev OS guidelines. A Rule Harvesting approach to rule discovery.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

AI Dev OS initial setup wizard. Asks about the project's tech stack and scale, then generates an optimal 4-layer structure from templates. Used when starting a new project or introducing AI Dev OS.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Creates an implementation plan with relevant AI Dev OS guideline checklists before writing any code. Analyzes the request, identifies affected files and applicable guidelines, then presents a plan with embedded checklist for user approval. Implementation begins only after approval.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Generates an AI Dev OS compliance report for teams and stakeholders. Includes compliance rate trends, major violations, and improvement proposals for a specified period. Used for weekly or monthly reporting.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Performs a comprehensive self-review before creating a PR. Combines guideline compliance checking (L3) with design-level review (L2) and philosophical alignment (L1). Unlike /ai-dev-os-check which only checks rules, this also evaluates architecture decisions and code design quality.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Scans ALL source files in the project against AI Dev OS guidelines. Unlike /ai-dev-os-check (which only checks git diff), this performs a full project-wide compliance scan. Use for initial audits, periodic full reviews, or after introducing new guidelines.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Creates a ticket (local file or GitHub Issue) containing an implementation summary and guideline checklist candidates. Analyzes the request the same way as /ai-dev-os-plan but outputs a ticket instead of executing the implementation. The ticket output destination follows the project's Ticket Settings in CLAUDE.md.

yunbow/ai-dev-os-plugin-claude-code

Skill Claude CodeCodex

Explains the "why" behind a specific AI Dev OS rule or guideline. Traces the path from L3 guideline → L2 principle → L1 philosophy, explaining the rationale and background of the rule. Used when team members question a rule.