🛠️
AutomationJavaScript

Recipe Build

by shinpr

Recipe Build is an Automation skill for Claude Code, published by shinpr in claude-code-workflows.

669 stars102 forkson shinpr/claude-code-workflowsAdded 2026/08/24Repository updated 2026/08/23
agent-skillsagentic-aiagentic-codingai-agentsanthropicclaude-codeclaude-code-pluginclaude-code-skillcode-qualitycode-reviewdeveloper-toolsdevelopment-workflowllm-orchestrationproductivitysubagents
Install in seconds
Install Recipe Build
Copy Recipe Build into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-build ~/.claude/skills/recipe-build

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/shinpr/claude-code-workflows.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/recipe-build/SKILL.md in shinpr/claude-code-workflows
Installs to
~/.claude/skills/recipe-build
Collection
One of 25 skills cataloged from this repository
Category
Automation — 2226 skills

What Recipe Build does

Recipe Build executes materialized task files in autonomous mode. Use it when a work plan has already been turned into task files and the agent should carry them through execution, verification, and cleanup.

Recipe Build is cataloged under Automation on DirSkills. Recipe Build comes from a repository tagged agent-skills, agentic-ai, agentic-coding, ai-agents and anthropic.

Documentation

README

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: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

Orchestrator Definition

Core Identity: "I am an orchestrator." (see subagents-orchestration-guide skill)

Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Recipe Build

  • What else does shinpr publish alongside Recipe Build?

    Recipe Build is one of 25 skills that DirSkills catalogs from shinpr/claude-code-workflows, the repository it ships in. Its siblings there include AI Developer Guide, Coding Principles and Documentation Criteria. Each one is a separate skill with its own page in this directory, installs the same way Recipe Build does, and is maintained by shinpr in that same repository. The rest of the collection is listed on the shinpr/claude-code-workflows page.

  • How does Recipe Build compare to other Automation skills?

    Recipe Build ranks #1125 by stars among the 2226 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Recipe Build against them. Open each page to compare what they document and how they install.

More from shinpr/claude-code-workflows

Recipe Build is one of 25 skills cataloged on DirSkills from shinpr/claude-code-workflows.

See all 25 skills →
🧪
2026/08/24

AI Developer Guide

AI Developer Guide applies decision criteria, anti-pattern detection, debugging, and quality gates for backend or language-agnostic implementation reviews. Use it to assess code smells, failures, completeness, and fallback behavior.
Quality
669102
🧩
2026/08/24

Coding Principles

Coding Principles provides language-agnostic guidance for writing maintainable, readable, and well-structured code. Use it when implementing features, refactoring, or reviewing code quality.
Quality
669102
📄
2026/08/24

Documentation Criteria

Documentation Criteria determines whether a change needs a PRD, ADR, UI Spec, Design Doc, or Work Plan, and where each belongs. Use it when planning or reviewing technical documentation scope.
Writing
669102
🔗
2026/08/24

External Resource Context

External Resource Context records where external resources live and how to reach them for design, implementation, and verification. Use it when work depends on a design source, API schema, IaC source, secret store, or other canonical external system.
AI Engineering
669102
🎨
2026/08/24

Front Adjust

Front Adjust adjusts an existing UI in session and verifies the changes against the design source. Use it for targeted frontend updates that need iterative edit-check-refine review.
Frontend
669102
🧪
2026/08/24

Front Review

Front Review validates React and TypeScript frontend changes against a Design Doc and security requirements. Use it after implementation to review compliance, resolve findings, and apply optional fixes.
Quality
669102