plugins/dev/skills/blueprint-archive/SKILL.md
Archives a completed PRD to the archives directory with associated features and closure summary.
npx skillsauth add rp1-run/rp1 blueprint-archiveInstall 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.
Archives completed PRD docs from active -> archives dir with associated features.
/rp1-dev:blueprint-archive <prd-name>
.rp1/work/prds/<PRD_NAME>.md -> .rp1/work/archives/prds/<PRD_NAME>/prd.md.rp1/work/archives/features/closure_summary.md with archive metadata/knowledge-build if needed{% dispatch_agent "rp1-dev:prd-archiver" %} MODE: scan PRD_NAME: {PRD_NAME} KB_ROOT: {kbRoot} WORK_ROOT: {workRoot} {% enddispatch_agent %}
Parse JSON response from agent.
Error Response (type: "error"):
{"type":"error","message":"...","available_prds":["prd1","prd2"]}
Output error message with available PRDs list, then STOP.
Needs Confirmation (type: "needs_confirmation"):
{
"type": "needs_confirmation",
"prd_name": "...",
"prd_title": "...",
"associated_features": [...],
"message": "..."
}
Continue to Step 3.
{% ask_user "Archive PRD '{PRD_NAME}' ({prd_title})? {message}", options: "Yes - Objectives fully met", "Partial - Some objectives met", "No - Cancel" %}
Handle response:
CLOSURE_STATUS=completeArchive aborted by user. + STOP{% ask_user "Document the gaps or unmet objectives:" %}
Capture response as GAPS.
{% dispatch_agent "rp1-dev:prd-archiver" %} MODE: archive PRD_NAME: {PRD_NAME} CLOSURE_STATUS: {complete|partial} GAPS: {user-provided gaps or empty} KB_ROOT: {kbRoot} WORK_ROOT: {workRoot} {% enddispatch_agent %}
Display agent success output directly. 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.