Algo Trader / Bloated AI Slop Creator AI-Driven Software / Research Factory Massive Layoff Solutions
Bellman publishes skills that help an AI agent route questions to outside advisors such as Claude, Codex and Gemini, run parallel web and documentation research, and keep a persistent markdown knowledge base across sessions. The rest of the catalogue covers structured requirements interviews before execution, visual QA verdicts for screenshot comparisons, drafting pull request bodies from verification records, and release management driven by cached repository rules.
Oh My Claudecode
48 skills · 40,648 stars · MIT
Agent Doc Discipline Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/ski…
Ai Slop Cleaner Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewe…
Architecture Survey Periodic architecture survey — walks the module graph and reports ranked deepening candidates (sh…
Ask Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `…
Ask Navigator Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) in…
Autopilot Full autonomous execution from idea to working code
Autoresearch Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs,…
Cancel Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and c…
Configure Notifications Configure notification integrations (Telegram, Discord, Slack) via natural language
Debug Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
Deep Interview Socratic deep interview with mathematical ambiguity gating before explicit execution approval
Deepinit Deep codebase initialization with hierarchical AGENTS.md documentation
Diagram Use the smallest visual when prose must carry structure—control flow, call depth, module ownershi…
Drydock Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rule…
Execute Carry an approved task through to working, verified code
External Context Invoke parallel document-specialist agents for external web searches and documentation lookup
Graph Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash re…
Harbor Harbor intake for external work — the captain only handles unresolved decisions.
Hud Configure HUD display options (layout, presets, display elements)
Intent Shipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a past…
Launch Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompos…
Loft Loft the shape before cutting steel — answer a design question that prose cannot settle by buildi…
Map The yard's skill map — which skill owns which job, in delivery-loop order.
Minimal Code Discipline YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, depen…
Minimal Prose Discipline Writing-time discipline for the prose an agent speaks to a human (replies, reports, pointers): a…
Omc Doctor Diagnose and fix oh-my-claudecode installation issues
Omc Plan Strategic planning with optional interview workflow
Omc Review Evaluate finished work for defects, risk, and simplification before it ships
Omc Setup Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setu…
Pr Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence con…
Project Session Manager Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Ralph Self-referential loop until task completion with configurable verification reviewer
Ralplan Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Refit Cross-session environment retrospective driven by OMC's own instrumentation — trace timelines, fr…
Release Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, the…
Remember Review reusable project knowledge and decide what belongs in project memory, notepad, or durable…
Research Investigate an open question and return grounded, sourced findings
Self Improve Autonomous evolutionary code improvement engine with tournament selection
Session Flow Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outc…
Skill Manage local skills - list, add, remove, search, edit, setup wizard
Skillify Turn a repeatable workflow from the current session into a reusable OMC skill draft
Tdd Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independe…
Team N coordinated agents on shared task list using Claude Code implicit agent teams
Trace Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in tea…
Ultragoal Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints C…
Verify Verify that a change really works before you claim completion
Visual Verdict Structured visual QA verdict for screenshot-to-reference comparisons
Wiki LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)