Skill rating

Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when

YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variant

The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes.

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, gloss

Turn a repeatable workflow from the current session into a reusable OMC skill draft

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so t

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly

Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state

Shipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a pasted chat log or verbal problem report into a five-section intent.md through numbered batch questioning w

Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, friction reports, logs, and plan notepads. Every finding lands on the surface that owns the fix (determin

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference.

Writing-time discipline for the prose an agent speaks to a human (replies, reports, pointers): a protected core never rewritten (code, commands, paths, errors, negators, numbers), filler dies, no narr

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no re

Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidate

Structured visual QA verdict for screenshot-to-reference comparisons

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

Diagnose and fix oh-my-claudecode installation issues

Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs

Investigate an open question and return grounded, sourced findings

Carry an approved task through to working, verified code

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Evaluate finished work for defects, risk, and simplification before it ships

Verify that a change really works before you claim completion

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)

Full autonomous execution from idea to working code

Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session

Deep codebase initialization with hierarchical AGENTS.md documentation

Autonomous evolutionary code improvement engine with tournament selection

Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands

Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verific

Strategic planning with optional interview workflow

N coordinated agents on shared task list using Claude Code implicit agent teams

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Manage local skills - list, add, remove, search, edit, setup wizard

Self-referential loop until task completion with configurable verification reviewer

Configure notification integrations (Telegram, Discord, Slack) via natural language

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session

Invoke parallel document-specialist agents for external web searches and documentation lookup

Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow

Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release

Configure HUD display options (layout, presets, display elements)