REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Inicia sesión para dar me gusta0 me gusta
★ Stars are for the whole repo, not each skill
This repo is a collection of 85 skills
Teams-first Multi-agent orchestration for Claude CodeSi lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.
[](https://mcp.popnx.com/en/skills/yeachan-heo-oh-my-claudecode)Servidores MCP que conectan la IA a servicios para el mismo trabajo
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Mismo tipo de trabajo, ordenadas como la lista de Skills
| Este oh-my-claudecode | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Autor | Yeachan-Heo | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 85 | 1 | 1 | 1 | 1 |
| Estrellas de GitHub | 40.943 | 468.733 | 234.332 | 150.287 | 144.566 |
| Último cambio de código | 19 nov 2026 | 19 nov 2026 | 20 abr 2026 | 18 nov 2026 | 18 nov 2026 |
| Licencia | MIT | MIT | – | Apache-2.0 | MIT |
85 skills (conjuntos de instrucciones) de Yeachan-Heo que la IA lee y sigue · no es un MCP server
Install only the ones you use. Open a skill to see how to install it
This set has 85 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
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 s…
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Settle types and module shape before cross-boundary code — competing designs explored in parallel, compared on API surface and invariants, decision recorded with rejected alternatives and an accepted-deviations register.
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.
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 one attempt would lock in the wrong shape.
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `omc ask`, with artifact capture and no raw CLI assembly
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. Wayfinding…
Full autonomous execution from idea to working code
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
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 green' or 'babysit PR #N'.
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, regression, or score you are about to report.
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 checks. Before risky refactors or signature changes.
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.
Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state
No description from the maker
Configure notification integrations (Telegram, Discord, Slack) via natural language
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 enforcement proven to fire.
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 deliverable. For properties tests cannot reach.
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 once per repo.
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
Deep codebase initialization with hierarchical AGENTS.md documentation
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.
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 anyone…
Carry an approved task through to working, verified code
Invoke parallel document-specialist agents for external web searches and documentation lookup
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 and anchor-validated. For recurring unusual task shapes.
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 evidence. Use when CI is red and the failure is yours to fix.
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-pushes shared branches.
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 feedback.
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery
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, i…
Sustained single-metric improvement loop — hypothesis, before/after measurement against a fixed baseline, decision log, one accepted commit per verified win. For targets climbed over multiple rounds; not one-off fixes.
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 before changing a subsystem you cannot yet explain.
Configure HUD display options (layout, presets, display elements)
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 is caught cheaply. Not for well-specified or routine tasks.
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 acce…
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 verdict. For contested or high-risk changes.
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 stepping away.
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.
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 the…
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 art…
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 rerun.
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 actually earned.
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.
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 away
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 misleads
Interactive setup for role-based model routing: edit team.roleRouting (provider, tier, per-provider reasoning effort; orchestrator model-only), check panel diversity, warn on missing provider CLIs.
Diagnose and fix oh-my-claudecode installation issues
Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
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 the way you work. For 'make agents work like me'.
Strategic planning with optional interview workflow
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.
Twenty-four engineering principles in five groups, mapped to the lane carrying each — premise testing, root causes, honest verification, domain modeling, convergence, context discipline. For design, debugging, or delegation briefs.
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Self-referential loop until task completion with configurable verification reviewer
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
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 action. After a break or crash.
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 appr…
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 banking marathon-session lessons.
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs
Investigate an open question and return grounded, sourced findings
Evaluate finished work for defects, risk, and simplification before it ships
Spec-Driven Development. Interview → spec with acceptance criteria → plan → test-first execution. `/sdd full` runs the 6-phase pipeline instead.
Autonomous evolutionary code improvement engine with tournament selection
Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.
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 remains.
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 will audit later.
Manage local skills - list, add, remove, search, edit, setup wizard
Turn a repeatable workflow from the current session into a reusable OMC skill draft
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. For 'stack them, I'll land them' or review-gated queues.
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 state that breaks a rule. Use for /statechart.
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.
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 knowledge transfer.
N coordinated agents on shared task list using Claude Code implicit agent teams
One layered standard for shipping prose — docs, RFCs, readmes, PR descriptions, commit messages: outcome first, one meaning one home, checkable statements, no filler. Composes with minimal-prose-discipline.
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
TypeScript grounding for type-system discipline: discriminated unions over flags, satisfies, parse-don't-validate at boundaries, branded primitives, no non-null assertions on external data.
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session
Verify that a change really works before you claim completion
Structured visual QA verdict for screenshot-to-reference comparisons
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 done'.
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. For 'why was this built this way'.
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
MCP = las manos
Conecta la IA a un servicio o dato externo, como leer Notion o crear una factura. Necesita un programa o servidor en marcha.
Skill = el manual
Un archivo de texto que enseña a la IA cómo hacer una tarea. No se conecta a nada.
A veces se parecen: algunas Skills ejecutan scripts que llaman herramientas y algunos MCP solo envían conocimiento. Empieza por la tarea que quieres hacer.
Claude CodeCodexCursorGemini CLI
Según el README del autor y las carpetas del repo
This repo has 85 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Ocultamos el comando del autor · no instala desde este repositorio de GitHub · Ocultamos los comandos porque no pasaron la revisión · instálalo desde la página de GitHub del autor
Copiado del README del autor; descarga y ejecuta su código
Pregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.