recipe-design — скилл для Claude Code: что делает и как установить
Скилл recipe-design для Claude Code координирует проектирование архитектуры от анализа кодовой базы до утверждения Design Doc. Процесс включает промежуточные остановки для подтверждения решений человеком.
MIT ★ 720 обновлён 2026-11-11
npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-codeЧто делает recipe-design
Скилл управляет фазой технического проектирования на основе репозитория. Сначала запускается субагент codebase-analyzer для сбора границ ответственности и затронутых путей. Затем отбираются спорные архитектурные вопросы, требующие фиксации в ADR.
Если найдены решения с долгосрочным влиянием, субагент technical-designer формирует пакет ADR, а document-reviewer проверяет их до одобрения пользователем. После этого создаётся единый Design Doc, верифицируемый агентом code-verifier по коду репозитория.
Для работы требуются субагенты пакета dev-workflows-fullstack и вспомогательные скиллы documentation-criteria, llm-friendly-context, subagents-orchestration-guide и requirement-convergence.
Какие задачи решает
- составить Design Doc с опорой на фактический код репозитория
- выделить спорные архитектурные решения в отдельные ADR
- проверить проектные решения субагентами перед началом кодинга
- зафиксировать границы изменений и контракты между слоями системы
Примеры запросов агенту
- /recipe-design docs/prd/auth-service.md
- /recipe-design Добавить поддержку шардирования базы данных PostgreSQL
- /recipe-design Реализовать фоновый воркер для экспорта отчётов
Как установить recipe-design
1Через Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-code2Вручную: положить файлы
~/.claude/skills/recipe-design/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/recipe-design/
1Через Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill recipe-design -a codex2Вручную: положить файлы
.agents/skills/recipe-design/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill recipe-design -a cursor2Вручную: положить файлы
.cursor/skills/recipe-design/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install shinpr/claude-code-workflows dev-workflows-fullstack/skills/recipe-design2Вручную: положить файлы
.github/skills/recipe-design/SKILL.md1Через Skills CLI (Vercel)
npx skills add shinpr/claude-code-workflows --skill recipe-design -a gemini-cli2Командой платформы
gemini skills install https://github.com/shinpr/claude-code-workflows --path dev-workflows-fullstack/skills/recipe-designВручную: положить файлы
.devin/skills/recipe-design/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о recipe-design
Как установить recipe-design в Claude Code?
Выполните команду npx skills add shinpr/claude-code-workflows --skill recipe-design -a claude-code.
Что делает recipe-design?
Координирует подготовку архитектурных документов: анализирует кодовую базу, при необходимости готовит ADR и сводит итоговый Design Doc.
Что нужно для работы recipe-design?
Требуются субагенты dev-workflows-fullstack:codebase-analyzer, technical-designer, document-reviewer, code-verifier, а также скиллы requirement-convergence и documentation-criteria.
Исходный текст
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