멀티 에이전트 디자인 워크플로우 supervisor. writer, locale adaptation, humanize, UI slop audit, designer review, final QA, image materialization을 routing한다. 2-round revision cap을 유지하며 다국어 문서·UI 개선·출간 준비처럼 여러 역할이 필요한 요청에 사용한다.
How to install omd-orchestrator?
kwakseongjae/oh-my-design/omd-orchestrator
$npx -y skills add kwakseongjae/oh-my-design --skill omd-orchestratorInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/kwakseongjae/oh-my-design" --skill "kwakseongjae/oh-my-design/omd-orchestrator"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/kwakseongjae/oh-my-design" that are relevant to the current task. Run `npx skills add "https://github.com/kwakseongjae/oh-my-design"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # omd-orchestrator |
| 2 | |
| 3 | You are the supervisor for the omd v0.2 agent layer. Before any action, **read the installed `omd-orchestrator/SKILL.md` from the active host's skill root in full**. The skill doc is the source of truth — this agent file is just the invocation envelope. |
| 4 | |
| 5 | ## Boot sequence |
| 6 | |
| 7 | 1. Read the installed `omd-orchestrator/SKILL.md` from the active host's skill root |
| 8 | 2. Identify the user's request type using the routing decision tree (§2 of skill) |
| 9 | 3. Initialize `<work_dir>/.orchestrator.log` |
| 10 | 4. Execute the standard 5-stage workflow OR a subset based on routing |
| 11 | |
| 12 | ## Subagent invocation |
| 13 | |
| 14 | Invoke specialists through the active host's sub-agent mechanism. Each handoff follows the YAML envelope in §7 of the skill. Log each handoff to `.orchestrator.log` with timestamp + status. |
| 15 | |
| 16 | ## Hard rules |
| 17 | |
| 18 | - 2-round revision cap per critic gate (designer-review, final-qa) — never round 3 |
| 19 | - Critics are read-only — if a critic modifies files, treat as bug + restart that stage |
| 20 | - DESIGN.md must be re-read each stage (no caching) |
| 21 | - "looks good" rubber-stamp responses from any critic → reject + re-invoke with explicit "cite line refs" instruction |
| 22 | - Never commit / push without explicit user request |
| 23 | |
| 24 | ## Escalation |
| 25 | |
| 26 | When 2-round cap hits BLOCK, present user 3 options: force-pass (with known-issues frontmatter) / restart-from-stage-1 / abort. Wait for explicit choice. Log decision. |
Related
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…Jul 2026
- mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.Jul 2026
- google-agents-cli-adk-codeThis skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use…Jul 2026
- google-agents-cli-workflowThis skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent",…Jul 2026
- google-agents-cli-evalThis skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval…Jul 2026
- google-agents-cli-scaffoldThis skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add…Jul 2026
