Skip to main content
skill CX Codex

recipe-design — Claude Code skill: what it does, how to install

recipe-design is a Claude Code skill that coordinates software design from repository analysis to an approved Design Doc, pausing for user confirmation at key decisions.

MIT ★ 720 updated 2026-11-11

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-code
Open on GitHub

What recipe-design does

This skill drives technical design directly from codebase evidence. It calls the codebase-analyzer subagent to inspect affected paths, responsibility boundaries, and cross-layer contracts from a PRD or raw requirements.

When architectural choices have durable impact, it routes them through technical-designer and document-reviewer to produce an ADR batch. Once decisions settle, the skill generates a full Design Doc and runs code-verifier to check claims against actual code.

Execution relies on subagents from dev-workflows-fullstack along with helper skills documentation-criteria, requirement-convergence, and subagents-orchestration-guide.

What it helps with

  • build a Design Doc grounded in actual repository structure
  • isolate major architectural choices into formal ADR records
  • verify technical design claims against codebase reality before coding
  • establish clear responsibility boundaries for medium and large features

Example prompts for the agent

  • /recipe-design docs/prd/auth-service.md
  • /recipe-design Add multi-tenant isolation to the billing service
  • /recipe-design Implement background job worker for batch exports

How to install recipe-design

1Skills CLI (Vercel)

npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-code

2Manually: put the files in place

~/.claude/skills/recipe-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/recipe-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about recipe-design

How to install recipe-design in Claude Code?

Run npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-code.

What does recipe-design do?

It orchestrates repository analysis, evaluates ADR candidate points, and drives subagents to assemble a verified Design Doc.

What is required to run recipe-design?

It requires subagents from dev-workflows-fullstack (codebase-analyzer, technical-designer, document-reviewer, code-verifier) and complementary workflow skills.

Source text

SKILL.md · MIT
---
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

```text
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`:

```text
prd_path: [approved PRD path]
```

or, when no approved PRD exists:

```text
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:

1. Choice requires judgment between at least two credible, materially distinct options inside the scope of the requirements.
2. 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:

1. Invoke `dev-workflows-fullstack:technical-designer` once with exact inputs: `document_to_create: ADRBatch`; `requirement_context`; `decision_points` as the ordered `adrDecisionPoints` from Step 3, unchanged; and `decision_materials` as the corresponding objects from Step 2 `decisionMaterials.candidateDecisionPoints`, copied unchanged in that order.
2. Invoke `dev-workflows-fullstack:document-reviewer` once with exact inputs: `doc_type: ADRBatch`, `targets: [all returned paths]`, and `requirement_context`.
3. Route the reviewer verdict first: `pass` proceeds with `issues: []`; `needs_revision` applies Review Resolution, updates one ADR per path serially, and re-reviews the complete batch; `rejected` resolves the governing-source conflict before another review.
4. Present one batch decision after Review Resolution converges, including a decline-only result; unresolved governing-source conflicts still block approval. `[Stop: ADR batch approval]`.
5. After user approval, update each ADR status to `Accepted` and verify the changed status.

## Step 5: Create the Design Doc

Create the complete MVP implementation design from reviewed artifacts and unchanged repository evidence; this keeps the Design Doc traceable to approved sources instead of an orchestrator-authored shadow design.

Invoke `dev-workflows-fullstack:technical-designer` with exactly:

- `document_to_create: DesignDoc`;
- `requirement_context`;
- `structural_scale`;
- `adr_paths: [accepted paths or []]`;
- `codebase_analysis: [complete Step 2 JSON unchanged]`.

The Design Doc owns the full end-to-end design and retains all applicable downstream safeguards in the documentation-criteria template.

## Step 6: Verify and Resolve Repository Claims

Keep verifier observations unchanged so corrections remain traceable to observed repository evidence instead of becoming orchestrator-authored design instructions.

Invoke `dev-workflows-fullstack:code-verifier` with `doc_type: design-doc` and the Design Doc path to verify current premises and feasibility while treating planned behavior as intent.

Apply Review Resolution to every discrepancy before document review. Send only `apply` findings to a fresh technical-designer update invocation with `Operation Mode: update`, `Existing Document: [Design Doc path]`, and `correction_findings: [complete findings unchanged except for their dispositions]`. The designer applies its review-triggered bounded self-verification gate when a finding names an unverified decision-changing premise; this fresh designer is the sole correction specialist and selects the evidence route. Rerun code-verifier after a correction with the previous complete result, dispositions, and correction diff or paths as `prior_feedback`. Build the single `verification_evidence` object defined by Review Resolution from the latest result and continue at its convergence condition.

## Step 7: Review and Approve

Invoke `dev-workflows-fullstack:document-reviewer` with exact inputs: `doc_type: DesignDoc`, `target`, `review_context: creation`, the original user requirements verbatim as `requirements_verbatim`, `requirement_context`, `codebase_analysis`, and `verification_evidence` from Step 6.

- `pass`: continue.
- `needs_revision`: apply Review Resolution, update through a fresh technical-designer invocation using the existing path and complete applied findings, then re-review with `prior_feedback`.
- `rejected`: resolve technical governing-source conflicts through Review Resolution; ask the user only when the outcome, desired-future requirements, and non-goals cannot all remain true and the user must choose which changes.

Invoke `dev-workflows-fullstack:design-sync` for consistency with other Design Docs and apply Review Resolution to actionable conflicts. Report `SKIPPED` distinctly when only one Design Doc exists.

Present the Design Doc, accepted ADR paths, resolved limitations/declines, and design-sync result. `[Stop: Design approval]`.

## Completion Criteria

- Scope and Structural Scale were determined from outcomes and responsibility boundaries.
- ADRs exist only for decision points passing both filters, and the complete batch received one review and approval.
- A Design Doc exists regardless of whether ADRs were needed.
- Applicable existing-behavior, contract, assumption, equivalence, and verification safeguards reached the Design Doc.
- Review Resolution routed only `needs_revision` issues into correction work.
- All stop points received explicit user confirmation.

© shinpr · MIT · shinpr/claude-code-workflows

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set43

The whole set →
scope-discoverer scope-discoverer discovers functional scope across existing codebases for reverse documentation. Groups features into PRD-ready units. CX Codex ★ 720repo stars ui-spec-designer The ui-spec-designer Claude Code subagent turns interface requirements into a specification of screens, states, and components. It activates for frontend design work or requests to break a UI into components. CX Codex ★ 720repo stars integration-test-reviewer integration-test-reviewer reviews changed integration and E2E tests to see whether they actually prove the claim behind them. Returns the gaps that matter and the smallest fix for each. CX Codex ★ 720repo stars coding-principles The coding-principles Claude Code skill sets language-agnostic principles for readable, maintainable code. It activates during feature work, refactoring, and code quality reviews. CX Codex +1 ★ 720repo stars code-reviewer The code-reviewer Claude Code subagent reviews completed changes against project requirements, contracts, and quality rules. It runs after implementation or when a review or compliance check is requested. CX Codex ★ 720repo stars solver solver generates distinct fixes for verified root causes and evaluates tradeoffs. Helps select the right remedy strategy once cause investigation finishes. CX Codex ★ 720repo stars design-sync design-sync compares Design Docs to flag incompatible shared requirements and returns a structured report. Use it when several design documents need a consistency check. CX Codex ★ 720repo stars security-reviewer security-reviewer weighs finished code against the security rules your project set for itself and answers with the fixes that cannot be skipped. CX Codex ★ 720repo stars

Project sponsors

Companies that keep this analytics open