Repository
Yeachan-Heo/oh-my-claudecode agent skills
- skills
- 47
- GitHub stars
- 40k
GitHub description: “Teams-first Multi-agent orchestration for Claude Code”
- Stars
- 39,751 (3,559 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jan 2026
- Homepage
- oh-my-claudecode.dev
- agentic-coding
- ai-agents
- claude
- claude-code
- oh-my-opencode
- opencode
- vibe-coding
- automation
- multi-agent-systems
- parallel-execution
Install all skills
npx skills add Yeachan-Heo/oh-my-claudecodeAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Yeachan-Heo/oh-my-claudecode, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Sends a question or task to another locally installed agent CLI, such as Codex or Gemini, through omc ask and saves the answer as a file. | Yeachan-Heo/ | 40k | — | ~572 | Automated safety check: Pass | MIT | 2 days ago |
| 2 | Charts a foggy effort into a map of decision tickets on the repo's issue tracker and works through them one per session, producing decisions rather than deliverables. | Yeachan-Heo/ | 40k | — | ~4.1k | Automated safety check: Pass | MIT | 2 days ago |
| 3 | Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted. | Yeachan-Heo/ | 40k | — | ~5.3k | Automated safety check: Warn | MIT | 2 days ago |
| 4 | Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code. | Yeachan-Heo/ | 40k | — | ~4.4k | Automated safety check: Pass | MIT | 2 days ago |
| 5 | Detects and gracefully cancels whichever OMC mode, autopilot, ralph, swarm, pipeline, or team, is currently active, then clears its state. | Yeachan-Heo/ | 40k | — | ~4.6k | Automated safety check: Pass | MIT | 2 days ago |
| 6 | Maps a codebase directory by directory and writes linked AGENTS.md files, each pointing to its parent, to document what each area contains. | Yeachan-Heo/ | 40k | — | ~2.3k | Automated safety check: Pass | MIT | 2 days ago |
| 7 | Picks the smallest visual that carries structure when prose alone would not: pseudocode, call tree, component or file tree, Mermaid or diff, and skips it when prose is enough. | Yeachan-Heo/ | 40k | — | ~885 | Automated safety check: Pass | MIT | 2 days ago |
| 8 | Breaks a research question into two to five facets and sends parallel document-specialist agents to search the web and documentation, then merges the results. | Yeachan-Heo/ | 40k | — | ~545 | Automated safety check: Pass | MIT | 2 days ago |
| 9 | Runs deterministic DAG pipelines from a JSON descriptor with journal-based crash recovery, so an interrupted run resumes without repeating finished nodes. | Yeachan-Heo/ | 40k | — | ~1.3k | Automated safety check: Pass | MIT | 2 days ago |
| 10 | Installs and configures the oh-my-claudecode heads-up display in the Claude Code statusline, with minimal, focused and full layouts. | Yeachan-Heo/ | 40k | — | ~2.5k | Automated safety check: Pass | MIT | 2 days ago |
| 11 | Turns a pasted chat log or spoken problem report from support or ops staff into a reviewed five-section intent.md through numbered batches of questions. | Yeachan-Heo/ | 40k | — | ~1.5k | Automated safety check: Pass | MIT | 2 days ago |
| 12 | Manages local oh-my-claudecode skills with slash subcommands to list, add, remove, search and edit them, plus a setup wizard. | Yeachan-Heo/ | 40k | 1 repo | ~5.6k | Automated safety check: Pass | MIT | 2 days ago |
| 13 | Settles stalled design questions by building a throwaway artifact: either a pure logic module in a clickable shell, or three structurally different UI variants. | Yeachan-Heo/ | 40k | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 14 | Routes a request to the right oh-my-claudecode skill by listing which skill owns each job, in delivery-loop order, without running anything itself. | Yeachan-Heo/ | 40k | — | ~746 | Automated safety check: Pass | MIT | 2 days ago |
| 15 | 15.OMC Doctor Diagnoses and fixes oh-my-claudecode installation problems by checking plugin versions, legacy hooks, leftover scripts and the CLAUDE.md configuration. | Yeachan-Heo/ | 40k | — | ~3.1k | Automated safety check: Pass | MIT | 2 days ago |
| 16 | 16.OMC Setup Installs, refreshes or repairs oh-my-claudecode for plugin, npm and local-dev installs through a phased setup flow with help, local, global and force flags. | Yeachan-Heo/ | 40k | — | ~2.5k | Automated safety check: Pass | MIT | 2 days ago |
| 17 | Drafts a pull request body from the session's paper trail: a one-line claim with the smallest proving visual, verify evidence, a reversibility note and glossary terms. | Yeachan-Heo/ | 40k | — | ~773 | Automated safety check: Pass | MIT | 2 days ago |
| 18 | Creates isolated git worktrees, with optional tmux sessions, for PR reviews, issue fixes and feature work across projects and repositories. | Yeachan-Heo/ | 40k | — | ~4k | Automated safety check: Pass | MIT | 2 days ago |
| 19 | Works out a repository's release rules from its files and CI, caches them in .omc/RELEASE_RULE.md, then walks you through a release using those rules. | Yeachan-Heo/ | 40k | — | ~2k | Automated safety check: Pass | MIT | 2 days ago |
| 20 | 20.Skillify Turns a repeatable workflow from the current session into a draft oh-my-claudecode skill, after a quality gate on whether it is worth capturing. | Yeachan-Heo/ | 40k | — | ~641 | Automated safety check: Pass | MIT | 2 days ago |
| 21 | Explains why something happened by generating competing hypotheses, gathering evidence in parallel, ranking explanations and proposing the next discriminating probe. | Yeachan-Heo/ | 40k | — | ~2.6k | Automated safety check: Pass | MIT | 2 days ago |
| 22 | 22.LLM Wiki Keeps a persistent markdown wiki of project and session knowledge that the agent can ingest into, query, lint and read across sessions. | Yeachan-Heo/ | 40k | — | ~721 | Automated safety check: Pass | MIT | 2 days ago |
| 23 | 23.Ralplan Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution | Yeachan-Heo/ | 40k | — | ~2.7k | Automated safety check: Pass | MIT | 2 days ago |
| 24 | Interviews you with Socratic questions and an ambiguity score until a vague idea becomes a clear spec, then holds execution until you approve. | Yeachan-Heo/ | 40k | — | ~12k | Automated safety check: Pass | MIT | 2 days ago |
| 25 | Sets up a shared repo environment for people and agents: CLAUDE.md, a CONTEXT.md glossary, ADRs, standards and a design-system folder, and audits drift with --check. | Yeachan-Heo/ | 40k | — | ~5.2k | Automated safety check: Pass | MIT | 2 days ago |
| 26 | Triages incoming issues and pull requests for a maintainer: verifies claims, reuses past decisions and delivers a docket of open questions, and never merges. | Yeachan-Heo/ | 40k | — | ~5.4k | Automated safety check: Pass | MIT | 2 days ago |
| 27 | Delivery pipeline from mission brief to verified change: writes a spec, splits it into tickets, runs them in parallel, verifies and reports a decision log after a repo audit gate. | Yeachan-Heo/ | 40k | — | ~7.3k | Automated safety check: Pass | MIT | 2 days ago |
| 28 | Spawns a team of coordinated agents on a shared task list, with optional agent types, a team size from one to twenty and a Ralph retry loop. | Yeachan-Heo/ | 40k | — | ~16k | Automated safety check: Pass | MIT | 2 days ago |
| 29 | Compares a generated UI screenshot with reference images and returns a strict JSON verdict with a score, differences and suggested edits to drive the next iteration. | Yeachan-Heo/ | 40k | — | ~609 | Automated safety check: Pass | MIT | 2 days ago |
| 30 | 30.Autoresearch Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior | Yeachan-Heo/ | 40k | — | ~894 | Automated safety check: Pass | MIT | 2 days ago |
| 31 | 31.Ultragoal Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session | Yeachan-Heo/ | 40k | — | ~1.7k | Automated safety check: Pass | MIT | 2 days ago |
| 32 | Writing standards for documents that agents read in order to act, such as CLAUDE.md, specs and tickets, so a fresh session can follow them without chat history. | Yeachan-Heo/ | 40k | — | ~1.5k | Automated safety check: Pass | MIT | 2 days ago |
| 33 | Cleans up AI-generated code that works but is bloated or repetitive, locking behavior with tests first and deleting before adding, with a reviewer-only mode. | Yeachan-Heo/ | 40k | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 34 | Periodic survey that walks a repo's module graph and reports ranked candidates for deepening, without changing any code itself. | Yeachan-Heo/ | 40k | — | ~1.3k | Automated safety check: Pass | MIT | 2 days ago |
| 35 | Takes an agreed task from intent to working code: splits it into units, implements the smallest correct change, verifies as it goes and reports what is left. | Yeachan-Heo/ | 40k | — | ~431 | Automated safety check: Pass | MIT | 2 days ago |
| 36 | A YAGNI-style checklist for planning and writing code changes: skip what is not needed, reuse what exists and ship the shortest correct diff. | Yeachan-Heo/ | 40k | — | ~746 | Automated safety check: Pass | MIT | 2 days ago |
| 37 | Keeps an agent's chat replies and reports short by cutting filler and narration while leaving code, commands, paths, errors and numbers untouched. | Yeachan-Heo/ | 40k | — | ~2.1k | Automated safety check: Pass | MIT | 2 days ago |
| 38 | Reviews finished work for correctness, risk, reuse and simplification, and reports verified findings most severe first without authoring the change. | Yeachan-Heo/ | 40k | — | ~655 | Automated safety check: Pass | MIT | 2 days ago |
| 39 | Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval. | Yeachan-Heo/ | 40k | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 40 | Test-first loop at pre-agreed seams: write one failing test, make it pass with the smallest change, repeat, with expected values taken from an independent source. | Yeachan-Heo/ | 40k | — | ~477 | Automated safety check: Pass | MIT | 2 days ago |
| 41 | 41.Ralph Self-referential loop until task completion with configurable verification reviewer | Yeachan-Heo/ | 40k | — | ~7.5k | Automated safety check: Pass | MIT | 2 days ago |
| 42 | Diagnoses a broken oh-my-claudecode session or repository state from logs, traces, state and a narrow reproduction, then names the smallest next fix. | Yeachan-Heo/ | 40k | — | ~361 | Automated safety check: Pass | MIT | 2 days ago |
| 43 | Sorts what a session has learned into the right place, project memory, notepad or durable docs, and flags duplicate, stale or conflicting entries. | Yeachan-Heo/ | 40k | — | ~356 | Automated safety check: Pass | MIT | 2 days ago |
| 44 | Answers an open question with sourced findings, searching the repo and official docs first, separating verified facts from inference and not implementing anything. | Yeachan-Heo/ | 40k | — | ~350 | Automated safety check: Pass | MIT | 2 days ago |
| 45 | Has the agent prove that a feature, fix or refactor works, using existing tests first, then narrow commands and manual checks, and report only what was actually verified. | Yeachan-Heo/ | 40k | — | ~277 | Automated safety check: Pass | MIT | 2 days ago |
| 46 | 46.Omc Plan Strategic planning with optional interview workflow. An agent skill from Yeachan-Heo/oh-my-claudecode. | Yeachan-Heo/ | 40k | — | ~6.2k | Automated safety check: Warn | MIT | 2 days ago |
| 47 | Configure notification integrations (Telegram, Discord, Slack) via natural language | Yeachan-Heo/ | 40k | — | ~9.1k | Automated safety check: Warn | MIT | 2 days ago |
Questions, answered from the data.
What is the best skill in Yeachan-Heo/oh-my-claudecode?
Ask Advisor Routing from Yeachan-Heo/oh-my-claudecode ranks first of the 47 skills in Yeachan-Heo/oh-my-claudecode listed here, with the highest score: its repository has 40k GitHub stars, its SKILL.md loads about 572 tokens and it passes the automated safety check with no findings. Next come Ask Navigator and Self-Improve Evolutionary Loop.
Are the skills in Yeachan-Heo/oh-my-claudecode official?
None yet. All 47 skills in Yeachan-Heo/oh-my-claudecode listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from Yeachan-Heo/oh-my-claudecode?
Run npx skills add Yeachan-Heo/oh-my-claudecode in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.