@skills · Owner

Agent skills by yeachan-heo

41 skills indexed from github.com/yeachan-heo. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• ai-slop-cleaner · Skill · 38,398 stars

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

• ask · Skill · 38,398 stars

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

• autopilot · Skill · 38,398 stars

  Full autonomous execution from idea to working code

• autoresearch · Skill · 38,398 stars

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

• cancel · Skill · 38,398 stars

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

• configure-notifications · Skill · 38,398 stars

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

• debug · Skill · 38,398 stars

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

• deep-interview · Skill · 38,398 stars

  Socratic deep interview with mathematical ambiguity gating before explicit execution approval

• deepinit · Skill · 38,398 stars

  Deep codebase initialization with hierarchical AGENTS.md documentation

• external-context · Skill · 38,398 stars

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

• hud · Skill · 38,398 stars

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

• oh-my-claudecode · Collection · 38,398 stars
• omc-doctor · Skill · 38,398 stars

  Diagnose and fix oh-my-claudecode installation issues

• omc-plan · Skill · 38,398 stars

  Strategic planning with optional interview workflow

• omc-setup · Skill · 38,398 stars

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

• project-session-manager · Skill · 38,398 stars

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

• ralph · Skill · 38,398 stars

  Self-referential loop until task completion with configurable verification reviewer

• ralplan · Skill · 38,398 stars

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

• release · Skill · 38,398 stars

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

• remember · Skill · 38,398 stars

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

• self-improve · Skill · 38,398 stars

  Autonomous evolutionary code improvement engine with tournament selection

• skill · Skill · 38,398 stars

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

• skillify · Skill · 38,398 stars

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

• skills · Collection · 38,398 stars
• team · Skill · 38,398 stars

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

• trace · Skill · 38,398 stars

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

• ultragoal · Skill · 38,398 stars

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

• verify · Skill · 38,398 stars

  Verify that a change really works before you claim completion

• visual-verdict · Skill · 38,398 stars

  Structured visual QA verdict for screenshot-to-reference comparisons

• wiki · Skill · 38,398 stars

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

• agent-doc-discipline · Skill

  Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps bef

• ask-navigator · Skill

  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,

• drydock · Skill

  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,

• execute · Skill

  Carry an approved task through to working, verified code

• graph · Skill

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

• harbor · Skill

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

• launch · Skill

  Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the fron

• loft · Skill

  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 clickabl

• minimal-code-discipline · Skill

  YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables

• omc-review · Skill

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

• research · Skill

  Investigate an open question and return grounded, sourced findings

Browse the @skills marketplace