From oh-my-colab
Transform a goal into a precise executable task list saved to .ohc/plans/. Run before any task >30 minutes. Includes deep interview, approach selection, task decomposition with success criteria. Triggers on keyword "plan".
npx claudepluginhub iadr-dev/colab --plugin oh-my-colabThis skill is limited to using the following tools:
Run before building anything estimated at >30 minutes.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Run before building anything estimated at >30 minutes.
If PRDs, RFCs, or other authoritative docs live outside oh-my-colab conventions, run document-intake first so .ohc/doc-sources.md and reconciliation are settled. Shorten Step 1 to unanswered questions, document↔repository conflicts, and ambiguous acceptance. Always include Sources and Traceability (assets/plan-template.md).
Clarify before designing:
Use .ohc/PROJECT.md as the primary project context. Also use optional domain
docs (CONTEXT.md / CONTEXT-MAP.md) when present. If the plan creates a
durable architectural decision, record whether an ADR is needed.
Propose 2-3 approaches with tradeoffs. Get user confirmation on approach before writing the full plan. See brainstorming skill for format.
Each task must be:
Save to: .ohc/plans/{kebab-case-name}.md
Use template from assets/plan-template.md.
Do NOT proceed to BUILD without explicit user confirmation. "Plan ready. Does this look right? Reply 'go' to start building."
See references/plan-template.md for canonical format. See references/task-decomposition.md for splitting rules. See references/domain-docs.md for glossary and ADR-aware planning.