recipe-design
Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval
shinpr · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add shinpr/claude-code-workflows --skill recipe-designAbout this skill
name: recipe-design description: Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval disable-model-invocation: true
Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.
Execute Skill: documentation-criteria before document routing or creation.
Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts.
Execute Skill: subagents-orchestration-guide before invoking agents or resolving findings.
Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.
Outcome and Ownership
Coordinate the design phase from repository evidence to an approved Design Doc. The user owns product requirements and exclusions; the orchestrator owns convergence readiness, Structural Scale, ADR qualification, evidence selection, and Review Resolution. Named specialists own semantic investigation and artifact authorship.
The Design Doc is always the complete implementation design for Medium/Large work. A qualifying ADR batch narrows technical choices before the Design Doc, which retains the complete flow and implementation boundary.
Requirements: $ARGUMENTS
Flow
requirement source -> codebase-analyzer -> scope/decision confirmation [Stop]
|
optional ADR batch -> batch review [Stop]
|
Design Doc -> code-verifier -> Review Resolution
|
document-reviewer -> design-sync -> approval [Stop]
Execute each dependent step after its prerequisite evidence exists. Use Review Resolution for every actionable verifier, reviewer, or design-sync finding. Wait at each [Stop] for explicit user confirmation.
At each Invoke below, build the Agent prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.
Step 1: Select the Governing Requirement Source
Use the approved PRD path when one exists. Otherwise use the requirements verbatim.
Set requirement_context to the approved PRD path exactly. Only when no approved PRD exists, use the orchestrator's convergence record unchanged.
Step 2: Collect Decision Material
Invoke dev-workflows-fullstack:codebase-analyzer:
prd_path: [approved PRD path]
or, when no approved PRD exists:
requirements: [requirements verbatim]
Invoke once for the complete scope. Require one valid JSON result and let the analyzer discover affected paths, responsibility boundaries, and cross-layer contracts. Treat its focus areas as existing-behavior safeguards, not as new requirements.
This independent discovery keeps scope and option convergence grounded in repository evidence rather than the orchestrator's unverified implementation hypothesis.
Step 3: Confirm Scope and ADR Decisions
Execute Skill: requirement-convergence. The orchestrator builds and judges the convergence record from the user request and Step 2 evidence.
Judge all four convergence fields by the rules in references/criteria.md of the requirement-convergence skill. Assign cost from Step 2 structural evidence and record its unknowns; run the hearing only for fields below ready.
Determine Structural Scale from outcomes and responsibility boundaries. File count is supporting evidence only.
Resolve decisionMaterials.candidateDecisionPoints against the governing requirement source, applicable simplifications, reuse, and invalidations. Remove a point when that evidence already converges on one sufficient approach. For each remaining item, apply documentation-criteria filters in order:
- Choice requires judgment between at least two credible, materially distinct options inside the scope of the requirements.
- The selection has durable material impact.
Record every passing item as adrDecisionPoints; an empty list routes directly to the Design Doc. ADR creation is limited to items that pass both filters.
Present the requirement-convergence Scope Confirmation. Place target responsibilities with their strongest file evidence, applicable simplifications with their conditions, and each qualifying ADR decision point with its filter evidence or none under Decision evidence; place Structural Scale with its boundary rationale and the recommended document route under Workflow.
Offer proceed, or correct scope and re-run analysis. Ask a question only when its answer can change a convergence field, the outcome, or scope. Continue only when every convergence field is ready or weak-but-explicit. [Stop: Scope confirmation].
Step 4: Create and Approve an ADR Batch When Needed
When adrDecisionPoints is non-empty:
- Invoke
dev-workflows-fullstack:technical-designeronce with exact inputs:document_to_create: ADRBatch;requirement_context;decision_pointsas the orderedadrDecisionPointsfrom Step 3, unchanged; anddecision_materialsas the corresponding objects from Step 2decisionMaterials.candidateDecisionPoints, copied unchanged in that order. - Invoke
dev-workflows-fullstack:document-revieweronce with exact inputs:doc_type: ADRBatch,targets: [all returned paths], andrequirement_context. - Route the reviewer verdict first:
passproceeds withissues: [];needs_revisionapplies Review Resolution, updates one ADR per path serially, and re-reviews the complete batch;rejectedresolves the governing-source conflict before another review. - Present one batch decision after Review Resolution converges, including a decline-only result; unresolved governing-source conflicts still block approval.
[Stop: ADR batch approval]. - After user approval,