Yeachan-Heo/oh-my-claudecode: 48 Agent Skills
Teams-first Multi-agent orchestration for Claude Code
| Repository | Yeachan-Heo/oh-my-claudecode · website |
|---|---|
| GitHub stars | 40,193 |
| Skills | 48 · 2 with scripts |
| Category | Software engineering |
| License | MIT |
| Last updated | Oct 23, 2026 |
| Install counts | Yeachan-Heo/oh-my-claudecode on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
Install Yeachan-Heo/oh-my-claudecode
| All skills, any agent | npx skills add Yeachan-Heo/oh-my-claudecode |
|---|---|
| One skill | npx skills add Yeachan-Heo/oh-my-claudecode --skill agent-doc-discipline |
| Only for Claude Code | npx skills add Yeachan-Heo/oh-my-claudecode -a claude-code, or copy a skill folder to ~/.claude/skills/ (all projects) or .claude/skills/ (one project) |
npx skills is the open-source skills CLI; it asks which agents to install for. Skills can include scripts that your agent will run: read a skill before installing it, as you would any code.
Skills in Yeachan-Heo/oh-my-claudecode
| Skill | What it does |
|---|---|
| agent-doc-discipline | 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 restating what the environment already says. Mandatory at drydock seed generation and the launch C5…npx skills add Yeachan-Heo/oh-my-claudecode --skill agent-doc-discipline |
| ai-slop-cleaner | Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only modenpx skills add Yeachan-Heo/oh-my-claudecode --skill ai-slop-cleaner |
| architecture-survey | 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 candidates and hands them to the captain; it never refactors on its own.npx skills add Yeachan-Heo/oh-my-claudecode --skill architecture-survey |
| ask-navigator | 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 until the way is clear, and hand the collapsed decisions to /launch as a mission brief.…npx skills add Yeachan-Heo/oh-my-claudecode --skill ask-navigator |
| ask | Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `omc ask`, with artifact capture and no raw CLI assemblynpx skills add Yeachan-Heo/oh-my-claudecode --skill ask |
| autopilot | Full autonomous execution from idea to working codenpx skills add Yeachan-Heo/oh-my-claudecode --skill autopilot |
| autoresearch | Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behaviornpx skills add Yeachan-Heo/oh-my-claudecode --skill autoresearch |
| cancel | Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy statenpx skills add Yeachan-Heo/oh-my-claudecode --skill cancel |
| configure-notifications | Configure notification integrations (Telegram, Discord, Slack) via natural languagenpx skills add Yeachan-Heo/oh-my-claudecode --skill configure-notifications |
| debug | Diagnose the current OMC session or repo state using logs, traces, state, and focused reproductionnpx skills add Yeachan-Heo/oh-my-claudecode --skill debug |
| deep-interview | Socratic deep interview with mathematical ambiguity gating before explicit execution approvalnpx skills add Yeachan-Heo/oh-my-claudecode --skill deep-interview |
| deepinit | Deep codebase initialization with hierarchical AGENTS.md documentationnpx skills add Yeachan-Heo/oh-my-claudecode --skill deepinit |
| diagram | 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 prose already answers the question.npx skills add Yeachan-Heo/oh-my-claudecode --skill diagram |
| drydock | Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface appearing on first use, so that every human and agent inherits the same design language and…npx skills add Yeachan-Heo/oh-my-claudecode --skill drydock |
| execute | Carry an approved task through to working, verified codenpx skills add Yeachan-Heo/oh-my-claudecode --skill execute |
| external-context | Invoke parallel document-specialist agents for external web searches and documentation lookupnpx skills add Yeachan-Heo/oh-my-claudecode --skill external-context |
| graph | Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recoverynpx skills add Yeachan-Heo/oh-my-claudecode --skill graph |
| harbor | 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 the maintainer a docket whose pending items each carry one question with options, recommendation,…npx skills add Yeachan-Heo/oh-my-claudecode --skill harbor |
| hud | Configure HUD display options (layout, presets, display elements)npx skills add Yeachan-Heo/oh-my-claudecode --skill hud |
| intent | 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 with a completion gate, walk it through tracker review with harbor's four records, and hand the…npx skills add Yeachan-Heo/oh-my-claudecode --skill intent |
| launch | 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. Two entry gates — the yard gate (drydock audit) and…npx skills add Yeachan-Heo/oh-my-claudecode --skill launch |
| loft | 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 variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the…npx skills add Yeachan-Heo/oh-my-claudecode --skill loft |
| map | 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.npx skills add Yeachan-Heo/oh-my-claudecode --skill map |
| minimal-code-discipline | 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 awaynpx skills add Yeachan-Heo/oh-my-claudecode --skill minimal-code-discipline |
| minimal-prose-discipline | 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 narration, auto-clarity where terse misleadsnpx skills add Yeachan-Heo/oh-my-claudecode --skill minimal-prose-discipline |
| omc-doctor | Diagnose and fix oh-my-claudecode installation issuesnpx skills add Yeachan-Heo/oh-my-claudecode --skill omc-doctor |
| omc-setup | Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flownpx skills add Yeachan-Heo/oh-my-claudecode --skill omc-setup |
| omc-plan | Strategic planning with optional interview workflownpx skills add Yeachan-Heo/oh-my-claudecode --skill omc-plan |
| pr | 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, glossary language throughout.npx skills add Yeachan-Heo/oh-my-claudecode --skill pr |
| project-session-manager | Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions has scriptsnpx skills add Yeachan-Heo/oh-my-claudecode --skill project-session-manager |
| ralph | Self-referential loop until task completion with configurable verification reviewernpx skills add Yeachan-Heo/oh-my-claudecode --skill ralph |
| ralplan | Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before executionnpx skills add Yeachan-Heo/oh-my-claudecode --skill ralplan |
| refit | 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 (deterministic check, steering volume, tooling, or information access); nothing is written without user…npx skills add Yeachan-Heo/oh-my-claudecode --skill refit |
| release | Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the releasenpx skills add Yeachan-Heo/oh-my-claudecode --skill release |
| remember | Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docsnpx skills add Yeachan-Heo/oh-my-claudecode --skill remember |
| research | Investigate an open question and return grounded, sourced findingsnpx skills add Yeachan-Heo/oh-my-claudecode --skill research |
| omc-review | Evaluate finished work for defects, risk, and simplification before it shipsnpx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review |
| self-improve | Autonomous evolutionary code improvement engine with tournament selection has scriptsnpx skills add Yeachan-Heo/oh-my-claudecode --skill self-improve |
| session-flow | Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.npx skills add Yeachan-Heo/oh-my-claudecode --skill session-flow |
| skill | Manage local skills - list, add, remove, search, edit, setup wizardnpx skills add Yeachan-Heo/oh-my-claudecode --skill skill |
| skillify | Turn a repeatable workflow from the current session into a reusable OMC skill draftnpx skills add Yeachan-Heo/oh-my-claudecode --skill skillify |
| tdd | 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.npx skills add Yeachan-Heo/oh-my-claudecode --skill tdd |
| team | N coordinated agents on shared task list using Claude Code implicit agent teamsnpx skills add Yeachan-Heo/oh-my-claudecode --skill team |
| trace | Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team modenpx skills add Yeachan-Heo/oh-my-claudecode --skill trace |
| ultragoal | Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active sessionnpx skills add Yeachan-Heo/oh-my-claudecode --skill ultragoal |
| verify | Verify that a change really works before you claim completionnpx skills add Yeachan-Heo/oh-my-claudecode --skill verify |
| visual-verdict | Structured visual QA verdict for screenshot-to-reference comparisonsnpx skills add Yeachan-Heo/oh-my-claudecode --skill visual-verdict |
| wiki | LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)npx skills add Yeachan-Heo/oh-my-claudecode --skill wiki |
Names and descriptions come from each skill's SKILL.md and are written by the pack's authors.
More software engineering skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
obra/superpowers An agentic skills framework & software development methodology that works.
|
15 | 304K | 2026-10-23 |
| 2 |
mattpocock/skills Skills for Real Engineers. Straight from my .agents directory.
|
38 | 301K | 2026-10-22 |
| 3 |
multica-ai/andrej-karpathy-skills A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
|
1 | 223K | 2026-04-20 |
| 4 |
DietrichGebert/ponytail Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
|
6 | 174K | 2026-10-18 |
| 5 |
Shubhamsaboo/awesome-llm-apps 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
|
10 | 143K | 2026-10-22 |
| 6 |
addyosmani/agent-skills Production-grade engineering skills for AI coding agents.
|
25 | 110K | 2026-10-13 |