Yeachan-Heo/oh-my-claudecode

Agent skills in the GitHub repository Yeachan-Heo/oh-my-claudecode, each with its code score out of 100.

Teams-first Multi-agent orchestration for Claude Code

Repository score

63 / 100 C

Skills

85

Verified

0

Average skill score

57

GitHub stars

40,780

License

MIT

Open Yeachan-Heo/oh-my-claudecode on GitHub

85 skills in this repository

1. ai-slop-cleaner

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

   77B
2. release

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

   74B
3. figure-it-out

   Design a rigorous bespoke playbook for a task no bundled skill fits — steps that each end in a check, verification commands, failure branches — stored where the checker validates…

   70B
4. sdd

   Spec-Driven Development. Interview → spec with acceptance criteria → plan → test-first execution. `/sdd full` runs the 6-phase pipeline instead.

   70B
5. skillify

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

   70B
6. verify

   Verify that a change really works before you claim completion

   70B
7. create-formal-verification-skill

   Verify the project's riskiest invariant with TLA+, Lean, or Kani — chosen by property shape — and leave a project-local skill the next agent reruns; assumptions are part of the de…

   69C
8. ralph

   Self-referential loop until task completion with configurable verification reviewer

   68C
9. omc-plan

   Strategic planning with optional interview workflow

   67C
10. 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) wit…

    66C
11. hud

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

    66C
12. 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 numbere…

    66C
13. omc-doctor

    Diagnose and fix oh-my-claudecode installation issues

    66C
14. ralplan

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

    66C
15. what-did-i-get-done

    Summarize authored commits over a period, grouped by theme with commit-range evidence, mechanical churn separated, and unfinished branches named. For standups and 'what did I get…

    66C
16. autopilot

    Full autonomous execution from idea to working code

    65C
17. babysit

    Drive an open PR to merge-ready on the watch-pr verdict policy — watch checks and review state, fix CI, address comments; never merges, rebases, or force-pushes. For 'get this gre…

    65C
18. create-verification-skill

    Generate the project's own verify skill: build/test/lint commands discovered by running them, a feature map of what each covers, manual checks, and an earned first verdict. Run on…

    65C
19. fix-ci

    Find the failing checks on the current PR, read their logs, classify the failure (real / flaky / environmental), fix the real ones with focused changes, and rerun to green with ev…

    65C
20. trace

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

    65C
21. 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),…

    64C
22. 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 o…

    62C
23. 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 tea…

    62C
24. maintain-formal-verification-skill

    Re-sync an existing formal verification skill after the covered code changed: re-check every assumption, update cited lines, rerun the tool; formally-verified only after a green r…

    62C
25. maintain-verification-skill

    Re-sync the project's verification skill when its commands drift — re-run each recorded command, update expectations and the feature map to what is true now, record the verdict ac…

    62C
26. arena

    Run N parallel candidates at one brief and synthesize: rubric-first framing, isolated fan-out, a cross-judge on a different model, criterion-by-criterion pick, hand grafting. When…

    61C
27. deep-interview

    Socratic deep interview with mathematical ambiguity gating before explicit execution approval

    61C
28. blast-radius

    Map what a change could break beyond the diff — dependents found by search and AST, classified certain/likely/unlikely — and prove the certain and likely ones by running their che…

    60C
29. fix-merge-conflicts

    Resolve merge conflicts non-interactively: start the integration, read both sides' intent from their commits, preserve both intents, validate on the resolved tree. Never force-pus…

    60C
30. 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 alr…

    60C
31. self-improve

    Autonomous evolutionary code improvement engine with tournament selection

    60C
32. benchmark-checklist

    Vet a measured number before reporting or acting on it: name the limiter, measure the claimed work, repeat with variance, rule out the observer, label every claim. For any speedup…

    59C
33. debug

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

    59C
34. 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…

    59C
35. configure-notifications

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

    58C
36. deepinit

    Deep codebase initialization with hierarchical AGENTS.md documentation

    58C
37. models

    Interactive setup for role-based model routing: edit team.roleRouting (provider, tier, per-provider reasoning effort; orchestrator model-only), check panel diversity, warn on miss…

    58C
38. personal-mode

    Draft a user-level behavior profile from recent transcripts — cross-project preferences, habits, and standing calls stored under the user skills dir so every project's agents work…

    58C
39. 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 minim…

    57C
40. session-flow

    Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.

    57C
41. ultragoal

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

    57C
42. 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 te…

    56C
43. technical-writing

    One layered standard for shipping prose — docs, RFCs, readmes, PR descriptions, commit messages: outcome first, one meaning one home, checkable statements, no filler. Composes wit…

    56C
44. why

    Investigate why code is the way it is from evidence — human rulings verbatim, git archaeology, linked issues, incident records — every claim labeled evidence, inference, or guess.…

    56C
45. 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 meani…

    55C
46. omc-setup

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

    55C
47. 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 o…

    55C
48. sharpen

    Aim a vague task at its real target without overspecifying: name the consumer, the observable change, the done-check, and the non-goals; at most one question when a real fork rema…

    55C
49. 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…

    55C
50. cancel

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

    54D
51. correct

    Find the mistakes agents keep repeating in this repo and make each impossible at the highest enforcing level — lint rule, type guard, runtime check, script, then text — with every…

    54D
52. graph

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

    54D
53. ketchup

    Catch up on everything since your last message: a 1-3 sentence executive summary, one status line per action item with evidence links, and open questions. For 'catch me up' after…

    54D
54. 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 exe…

    54D
55. remember

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

    54D
56. research

    Investigate an open question and return grounded, sourced findings

    54D
57. skill

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

    54D
58. stacked-delivery

    Deliver a queue of changes as one linear stacked PR chain — each PR lands on the last, verdicts record patch-ids, rebases trigger re-verification, and landing goes bottom-up only.…

    54D
59. statechart

    Check a TLA+ model of a system that moves between states, such as a product flow or a protocol, and draw it as a Mermaid statechart. The report gives the shortest path to each sta…

    54D
60. teach

    Explain a subsystem to a learner by composing how and why — the walkthrough cited to code, the decisions that shaped it, paced with a prediction check. For onboarding and knowledg…

    54D
61. visual-verdict

    Structured visual QA verdict for screenshot-to-reference comparisons

    54D
62. execute

    Carry an approved task through to working, verified code

    53D
63. get-pr-comments

    Fetch and triage review threads on a PR: threads deduped with resolution state, each with a fix/dismiss/ask recommendation, bot findings read skeptically. Before addressing review…

    53D
64. how

    Walk through how a subsystem works — a fast explorer maps the territory, an explainer writes the layered walkthrough. Use for "how does X work", onboarding on unfamiliar code, or…

    53D
65. ask

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

    52D
66. autoresearch

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

    52D
67. external-context

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

    52D
68. in-your-own-words

    Play back the goal, the problem, and the success check in your own words when a brief is genuinely ambiguous — vague, contested, or leaving real forks open — so misunderstanding i…

    52D
69. omc-review

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

    52D
70. project-session-manager

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

    52D
71. ketchup-video

    Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

    51D
72. team

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

    51D
73. 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, o…

    50D
74. architect

    Settle types and module shape before cross-boundary code — competing designs explored in parallel, compared on API surface and invariants, decision recorded with rejected alternat…

    49D
75. bro

    Restate the last technical message in plain human language — no jargon, no shorthand, every fact and number kept. For 'say it plainly' or when a reply was too dense.

    49D
76. hillclimb

    Sustained single-metric improvement loop — hypothesis, before/after measurement against a fixed baseline, decision log, one accepted commit per verified win. For targets climbed o…

    49D
77. interrogate

    Adversarial pass over a diff or design: three reviewers on different models each try to break it — correctness, security, edge cases — findings merged by severity into a blocking…

    47D
78. recall

    Reconstruct working context from artifacts in trust order — state files, notepad, verification ledger, decision trail, transcript tail — then report where work stands and the next…

    47D
79. reflect

    After a long task, a three-reviewer panel audits the session transcript — tooling, judgment, missed alternatives — and proposes concrete skill edits. Findings feed skillify. For b…

    47D
80. show-me-your-work

    Append-only decision trail for long or autonomous work: one TSV row per non-obvious decision — what was chosen, what was rejected and why, the deciding evidence. For work a human…

    47D
81. principles

    Twenty-four engineering principles in five groups, mapped to the lane carrying each — premise testing, root causes, honest verification, domain modeling, convergence, context disc…

    46D
82. 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 rescu…

    43D
83. wiki

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

    43D
84. typescript-best-practices

    TypeScript grounding for type-system discipline: discriminated unions over flags, satisfies, parse-don't-validate at boundaries, branded primitives, no non-null assertions on exte…

    41D
85. commands
    31F

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.