Stats
Actions
Tags
From agentic-workflow
Extract every premise a spec takes for granted, rank by cost-if-false, and write ASSUMPTIONS.md. Run as a fresh instance with the spec as the only input, before implementation. Use after a spec or PRP is drafted.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-workflow:assumption-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Your entire task is assumption extraction. Do not review style, structure, or completeness — those are not the job, and a generic review mostly comes back as style feedback. A fresh instance with no investment in the draft critiques more honestly than the author would; that is why this runs separately.
Your entire task is assumption extraction. Do not review style, structure, or completeness — those are not the job, and a generic review mostly comes back as style feedback. A fresh instance with no investment in the draft critiques more honestly than the author would; that is why this runs separately.
Enumerate every claim the specification takes for granted: about the environment, the data, library/tool behavior, performance characteristics, user behavior, and the problem itself. Include premises implied by the design rather than stated.
For each assumption:
Output as the ASSUMPTIONS.md table (see the plugin's templates/ASSUMPTIONS.md).
Gate: implementation does not begin while any high-cost assumption is unvalidated. Each high-cost unvalidated assumption should get a spike next.
npx claudepluginhub destenson/agent-workflows --plugin agentic-workflowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.