plugins/dev/skills/blueprint-audit/SKILL.md
Audits a PRD against implementation status and guides lifecycle decisions.
npx skillsauth add rp1-run/rp1 blueprint-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Audits PRD documents against implementation evidence, identifies stale or completed blueprints, and guides disposition decisions (archive, modify scope, defer).
/rp1-dev:blueprint-audit <prd-name>
{% dispatch_agent "rp1-dev:blueprint-auditor" %} MODE: audit PRD_NAME: {PRD_NAME} KB_ROOT: {kbRoot} WORK_ROOT: {workRoot} {% enddispatch_agent %}
Error Response:
{"type":"error","message":"...","available_prds":["..."]}
Output error message with available PRDs, then STOP.
Needs User Input (audit complete):
{"type":"needs_user_input","question":"relevance","phases":[...],"summary":{...}}
Display the audit table from agent output, then continue to Step 3.
{% ask_user "Is this PRD still relevant to your work?", options: "Archive", "Add scope", "Remove scope", "Continue", "Defer" %}
"Archive":
needs_user_input with question="closure_status"Question: "What is the closure status?"
Options:
- "Complete" - All planned work finished
- "Partial" - Some work deferred or abandoned
"Add scope":
"Remove scope":
"Continue":
"Defer":
Display agent's final output. Include:
tools
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
documentation
Ask about rp1 capabilities, discover skills, and get workflow guidance.
tools
Generate an evidence-grounded markdown walkthrough for a pull request.
development
Run a bounded, evidence-driven two-agent debate into a separate rp1 debate artifact with backend locks only.