بنقرة واحدة
think
Deep structured thinking with parallel expert analysis before implementation (INTERNAL)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Deep structured thinking with parallel expert analysis before implementation (INTERNAL)
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
| name | think |
| description | Deep structured thinking with parallel expert analysis before implementation (INTERNAL) |
Used by @idea, @design, @feature. Three stages: breakdown → parallel expert analysis → summary.
Identify aspects to think through. Choose main expert. Output: Understanding + Aspects table (5-10 rows).
Launch expert agents (max 4 concurrent) — one per aspect:
Task(subagent_type="expert"):
"Aspect: [name]. Task context: [brief]. Study project and propose options."
Each expert: study project → apply expert principles → propose 2-4 options → make decision.
When experts return, create unified document. Save to docs/plans/YYYY-MM-DD-[topic]-design.md. Ask: "Which aspects to discuss? Or ready to implement?"
Skip parallel agents: Study → Analyze (named experts) → Propose options → Recommend.
Quality bug fixes (P1/P2). Full TDD cycle, branch from master via feature/, no production deploy.
Execute ONE executable leaf workstream with TDD, guard enforcement, and ws-verdict output
Deployment orchestration. Creates PR to master (after @oneshot) or merges for release.
System design with progressive disclosure, produces workstream files
Feature planning orchestrator (discovery -> idea -> ux -> design -> workstream tree)
Emergency P0 fixes. Fast-track production deployment with minimal changes. Branch from master, immediate deploy.