yeachan-heo
GitHub28 skills
ai-slop-cleaneryeachan-heo1.4KClean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only modeaskyeachan-heoProcess-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assemblyautopilotyeachan-heoFull autonomous execution from idea to working codeautoresearchyeachan-heoStateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behaviorcancelyeachan-heoCancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy stateconfigure-notificationsyeachan-heoConfigure notification integrations (Telegram, Discord, Slack) via natural languagedebugyeachan-heoDiagnose the current OMC session or repo state using logs, traces, state, and focused reproductiondeep-interviewyeachan-heoSocratic deep interview with mathematical ambiguity gating before explicit execution approvaldeepinityeachan-heoDeep codebase initialization with hierarchical AGENTS.md documentationexternal-contextyeachan-heoInvoke parallel document-specialist agents for external web searches and documentation lookuphudyeachan-heoConfigure HUD display options (layout, presets, display elements)omc-doctoryeachan-heoDiagnose and fix oh-my-claudecode installation issuesomc-planyeachan-heoStrategic planning with optional interview workflowomc-setupyeachan-heoInstall or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flowproject-session-manageryeachan-heoWorktree-first dev environment manager for issues, PRs, and features with optional tmux sessionsralphyeachan-heoSelf-referential loop until task completion with configurable verification reviewerralplanyeachan-heoConsensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before executionreleaseyeachan-heoGeneric release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the releaserememberyeachan-heoReview reusable project knowledge and decide what belongs in project memory, notepad, or durable docsself-improveyeachan-heoAutonomous evolutionary code improvement engine with tournament selectionskillyeachan-heoManage local skills - list, add, remove, search, edit, setup wizardskillifyyeachan-heoTurn a repeatable workflow from the current session into a reusable OMC skill draftteamyeachan-heoN coordinated agents on shared task list using Claude Code implicit agent teamstraceyeachan-heoEvidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team modeultragoalyeachan-heoDurable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active sessionverifyyeachan-heoVerify that a change really works before you claim completionvisual-verdictyeachan-heoStructured visual QA verdict for screenshot-to-reference comparisonswikiyeachan-heoLLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)