Deepplan
Start structured planning that produces an executable DeepWork planFrom its SKILL.md
npx -y skills add ai-outfitter/deepwork --skill deepplanAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, as published. Nobody here has run it
DeepPlan
DeepPlan is a structured planning workflow that explores the codebase, compares implementation approaches, and produces an executable DeepWork job or plan. This native Pi package uses Pi tools directly; it does not use MCP.
How to Use
- Clarify the planning goal if the user request is ambiguous.
- Call
deepwork_start_workflowwith:job_name:deepplanworkflow_name:create_deep_plangoal: the user's planning request
- Follow the returned step instructions exactly.
- Submit required outputs with
deepwork_finished_step. - Continue until the workflow completes or the user explicitly stops.
Intent Parsing for /deepplan
/deepplan <goal>— start the DeepPlan workflow using<goal>./deepplanwith useful conversation context — summarize the context as the goal and start the workflow./deepplanwithout enough context — ask what the user wants to plan.
Planning Discipline
- Keep exploration proportional to the scope.
- Capture assumptions and open questions explicitly.
- Prefer implementation-ready plans with file targets, validation commands, and risk notes.
- If planning discovers that requirements are unclear, pause and ask the user rather than inventing product behavior.