Claude Skills by Yeachan-Heo

Full autonomous execution from idea to working code

Cancel any active OMC mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline)

Deep codebase initialization with hierarchical AGENTS.md documentation

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

Setup and configure oh-my-claudecode (the ONLY command you need to learn)

Strategic planning with optional interview workflow

Manage isolated dev environments with git worktrees and tmux sessions

Self-referential loop until task completion with architect verification

Iterative planning with Planner, Architect, and Critic until consensus

Automated release workflow for oh-my-claudecode

Orchestrate parallel scientist agents for comprehensive research with AUTO mode

Review a plan with Critic

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

Show agent flow trace timeline and summary

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

Autonomous evolutionary code improvement engine with tournament selection

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

N coordinated agents on shared task list using Claude Code native teams

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

Verify that a change really works before you claim completion

Structured visual QA verdict for screenshot-to-reference comparisons

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

This compatibility command keeps `/oh-my-claudecode:skill` available without loading the full `skill` skill description in every Claude Code session.

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

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

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

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

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

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

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

Diagnose and fix oh-my-claudecode installation issues

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 that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.

Carry an approved task through to working, verified code

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

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 verification, and report with a full decision log. Humans own the checkpoints where there is no unique answer or the error cost is severe; agents continuously run everything repeatable and acceptable-by-evidence.

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