القائمة
Bridge between Superpowers workflow roles and oh-my-opencode agents. Automatically maps SP roles to OmO agents. Loads before any skill dispatches sub-agents.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
| name | omo-sp-omo-bridge |
| description | Bridge between Superpowers workflow roles and oh-my-opencode agents. Automatically maps SP roles to OmO agents. Loads before any skill dispatches sub-agents. |
When Superpowers workflow dispatches a sub-agent role, use this mapping to route to the correct oh-my-opencode agent.
| SP Role | OMO Tool | Parameters |
|---|---|---|
| Implementer (simple) | task() | category="quick", load_skills=["omo-test-driven-development"] |
| Implementer (complex) | task() | category="deep", load_skills=["omo-test-driven-development"] |
| Implementer (hard logic) | task() | category="ultrabrain", load_skills=["omo-test-driven-development"] |
| Implementer (frontend) | task() | category="visual-engineering", load_skills=["omo-test-driven-development", "frontend-ui-ux"] |
| Spec Reviewer | task() | subagent_type="momus" |
| Code Quality Reviewer | task() | subagent_type="oracle" |
| Codebase Search | task() | subagent_type="explore", run_in_background=true |
| External Research | task() | subagent_type="librarian", run_in_background=true |
| Pre-planning Analysis | task() | subagent_type="metis" |
| Plan Creation | task() | subagent_type="prometheus" or /start-work command |
| Plan Review | task() | subagent_type="momus" |
When dispatching implementation tasks, ALWAYS inject relevant skills:
| Task Type | load_skills |
|---|---|
| Any implementation | ["omo-test-driven-development"] |
| Bug fix | ["omo-test-driven-development", "omo-systematic-debugging"] |
| Feature work | ["omo-test-driven-development", "omo-verification-before-completion"] |
| Frontend | ["omo-test-driven-development", "frontend-ui-ux"] |
| Git operations | ["git-master"] |
When executing subagent-driven-development workflow:
subagent_type="momus" with spec compliance promptsubagent_type="oracle" with code quality promptsession_idFor complex features, use the full planning pipeline:
Always use session_id to continue a sub-agent's work:
// First dispatch → get session_id in result
task(category="quick", load_skills=["omo-test-driven-development"], description="Task 1", prompt="...", run_in_background=false)
// Result includes session_id: "ses_abc123"
// Continue same agent with full context preserved
task(session_id="ses_abc123", load_skills=["omo-test-driven-development"], description="Fix issues in Task 1", prompt="Fix: ...", run_in_background=false)
Independent exploration/research tasks should run in background:
task(subagent_type="explore", description="Find auth patterns", prompt="...", run_in_background=true)
task(subagent_type="librarian", description="Research JWT best practices", prompt="...", run_in_background=true)
// Continue working → collect results later with background_output(task_id="...")