Clarify and intake
Skill keithhegit/ultra-orchestration/skills/clarify-and-intake
Ultra Orchestration 是一套开源的 AI 工程编排技能体系。它将 OpenSpec 规格主线（Program → Milestone → Change → Slice）与 Ultra-Orchestrator 执行阶段（Intake → Plan → Dispatch → Execute → Review → QA → Deliver → Retro）结合，提升交付稳定性与可审计性。
npx -y skills add keithhegit/ultra-orchestration --skill clarify-and-intakeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 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.
What its author says it does
Copied from the file, not written here
Normalize ambiguous user requests into a structured intake artifact with task description, context, success criteria, constraints, and task type. Use before planning or implementation whenever requirements are incomplete, mixed, or implicit.
SKILL.md
1.1 KB, as published. Nobody here has run it
Clarify And Intake
Convert the raw request into an intake artifact before planning starts.
Produce
Return a compact JSON-like structure with:
task_descriptioncontextsuccess_criteriaconstraintstask_typeopen_questions
Rules
- Resolve discoverable facts from the repo or environment before asking questions.
- Prefer concrete, testable success criteria.
- Separate constraints from preferences.
- Produce artifacts that downstream roles can consume without inheriting the full chat history.
- If information is missing but low risk, choose a reasonable default and record it.
- If missing information would change architecture or public behavior, escalate clearly.
Hand off
Pass the intake artifact to $decision-complete-planner.
If external tools or unfamiliar skills may be needed, flag $risk-vetter.