Automation

MCP Attribution Worktree triages MCP and skills-related attribution issues from the report API, checks runs and traces, and decides whether they map to code or skill content. It then updates attribution evidence and carries actionable cases through isolated worktree fixes, PRs, and follow-up iteration.

Review Automation Orchestrator routes recurring repository reviews to the right specialized checks, then normalizes and escalates findings into reports, issues, or small corrective PRs. Use it when you need one coordinated review cycle across API contracts, docs freshness, code quality, and skill quality.

Human Review opens HTML, Markdown, or localhost pages in a browser for direct text edits and comments. Use it after writing specs, drafts, reports, or local pages that need human feedback.

Analyze design projects and match them to suitable design award programs, tracks, and categories. Apply eligibility rules, verify current official criteria, compare with winner trends, and output fit scores, evidence confidence, and submission priority.

Orchestrates a complete design award workflow, routing tasks like winner research, evaluation, award matching, and submission checking. Ideal when you need coordinated stages or aren't sure which specialist skill to use.

Finds verified award-winning designs from official sources like iF Design and Red Dot, using eight relevance dimensions to match your design's category and characteristics. Ideal for gathering comparable precedents, benchmarks, or appearance-related award winners.

Planning With Files uses persistent markdown files for task plans, notes, and final deliverables. Use it for complex, multi-step work, research, or when you need structured progress tracking.

Waku Computer Use controls local Mac apps through the Waku Computer Use runtime for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.

Wiki Query performs fast, read-only, index-first lookups in an llm-wiki with bounded file reads and exact citations. Use it for inventory questions or factual questions where you need evidence and clear gaps.

Wiki Query runs fast, read-only lookups against llm-wiki indexes and topic files. Use it to answer inventory questions, find exact files, or verify wiki evidence without editing anything.

Wiki Query provides fast, read-only llm-wiki lookups for factual questions, evidence checks, lists, and inventory status. Use it when you need exact wiki files without writing or indexing changes.

Adding A Skill explains how to register a new installable skill in OMH, update routing and prompts, and regenerate the generated docs. Use it when adding a skill and you need to satisfy the repo's required checks and fixtures.