All authors
Claude Skills by Yeachan-Heo
github.com/Yeachan-Heo50 skills8 installs221 views
- AutopilotFull autonomous execution from idea to working codeVotes: 0GitHub stars: 39,612
- CancelCancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy stateVotes: 0GitHub stars: 39,612
- DeepinitDeep codebase initialization with hierarchical AGENTS.md documentationVotes: 0GitHub stars: 39,612
- HudConfigure HUD display options (layout, presets, display elements)Votes: 0GitHub stars: 39,612
- Learn About OmcAnalyze your OMC usage patterns and get personalized recommendationsVotes: 0GitHub stars: 39,612
- Local Skills SetupSet up and manage local skills for automatic matching and invocationVotes: 0GitHub stars: 39,612
- Omc SetupSetup and configure oh-my-claudecode (the ONLY command you need to learn)Votes: 0GitHub stars: 39,612
- PlanStrategic planning with optional interview workflowVotes: 0GitHub stars: 39,612
- Project Session ManagerManage isolated dev environments with git worktrees and tmux sessionsVotes: 0GitHub stars: 39,612
- RalphSelf-referential loop until task completion with configurable verification reviewerVotes: 0GitHub stars: 39,612
- RalplanIterative planning with Planner, Architect, and Critic until consensusVotes: 0GitHub stars: 39,612
- ReleaseAutomated release workflow for oh-my-claudecodeVotes: 0GitHub stars: 39,612
- ResearchOrchestrate parallel scientist agents for comprehensive research with AUTO modeVotes: 0GitHub stars: 39,612
- ReviewEvaluate finished work for defects, risk, and simplification before it shipsVotes: 0GitHub stars: 39,612
- SkillManage local skills - list, add, remove, search, editVotes: 0GitHub stars: 39,612
- TddTest-Driven Development enforcement skill - write tests first, alwaysVotes: 0GitHub stars: 39,612
- TraceShow agent flow trace timeline and summaryVotes: 0GitHub stars: 39,612
- RememberReview reusable project knowledge and decide what belongs in project memory, notepad, or durable docsVotes: 0GitHub stars: 39,612
- Self ImproveAutonomous evolutionary code improvement engine with tournament selectionVotes: 0GitHub stars: 39,612
- SkillifyTurn a repeatable workflow from the current session into a reusable OMC skill draftVotes: 0GitHub stars: 39,612
- TeamN coordinated agents on shared task list using Claude Code implicit agent teamsVotes: 0GitHub stars: 39,612
- UltragoalDurable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active sessionVotes: 0GitHub stars: 39,612
- VerifyVerify that a change really works before you claim completionVotes: 0GitHub stars: 39,612
- Visual VerdictStructured visual QA verdict for screenshot-to-reference comparisonsVotes: 0GitHub stars: 39,612
- WikiLLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)Votes: 0GitHub stars: 39,612
- CommandsThis compatibility command keeps `/oh-my-claudecode:skill` available without loading the full `skill` skill description in every Claude Code session.Votes: 0GitHub stars: 39,612
- Ai Slop CleanerClean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only modeVotes: 0GitHub stars: 39,612
- AskProcess-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assemblyVotes: 0GitHub stars: 39,612
- AutoresearchStateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behaviorVotes: 0GitHub stars: 39,612
- Configure NotificationsConfigure notification integrations (Telegram, Discord, Slack) via natural languageVotes: 0GitHub stars: 39,612
- DebugDiagnose the current OMC session or repo state using logs, traces, state, and focused reproductionVotes: 0GitHub stars: 39,612
- Deep InterviewSocratic deep interview with mathematical ambiguity gating before explicit execution approvalVotes: 0GitHub stars: 39,612
- External ContextInvoke parallel document-specialist agents for external web searches and documentation lookupVotes: 0GitHub stars: 39,612
- Omc DoctorDiagnose and fix oh-my-claudecode installation issuesVotes: 0GitHub stars: 39,612
- DrydockLay 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.Votes: 0GitHub stars: 39,612
- ExecuteCarry an approved task through to working, verified codeVotes: 0GitHub stars: 39,612
- GraphDeterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recoveryVotes: 0GitHub stars: 39,612
- LaunchShipyard'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 the fog gate (an effort whose destination is unclear is routed to /ask-navigator before this pipeline starts). Humans own the checkpoints where there is no unique answer or the error cost is severe; ag...Votes: 0GitHub stars: 39,612
- Minimal Code DisciplineYAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized awayVotes: 0GitHub stars: 39,612
- Agent Doc DisciplineWriting-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 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.Votes: 0GitHub stars: 39,612
- Ask NavigatorShipyard'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. Wayfinding, not building: it produces decisions, never deliverables.Votes: 0GitHub stars: 39,612
- HarborHarbor 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, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.Votes: 0GitHub stars: 39,612
- LoftLoft 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 artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches "we would have to see it".Votes: 0GitHub stars: 39,612
- Architecture SurveyPeriodic 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.Votes: 0GitHub stars: 39,612
- DiagramUse 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.Votes: 0GitHub stars: 39,612
- IntentShipyard'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 accepted intent to /launch as its mission brief. Produces decisions, not code.Votes: 0GitHub stars: 39,612
- Minimal Prose DisciplineWriting-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 misleadsVotes: 0GitHub stars: 39,612
- MapThe 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.Votes: 0GitHub stars: 39,612
- PrDraft 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.Votes: 0GitHub stars: 39,612
- RefitCross-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 approval.Votes: 0GitHub stars: 39,612