Recipe Task

Recipe Task is an AI Engineering 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 Task

Copy Recipe Task 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-task ~/.claude/skills/recipe-task

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-task/SKILL.md in shinpr/claude-code-workflows
Installs to: ~/.claude/skills/recipe-task
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Recipe Task does

Recipe Task executes work by selecting rules with rule-advisor and following a dependency-ordered sequence. Use it when a task needs metacognitive analysis, subagent coordination, and rule-based execution.

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

Documentation

README

Excerpt

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.

Task Execution with Metacognitive Analysis

Task: $ARGUMENTS

Mandatory Execution Process

Step 1: Rule Selection via rule-advisor (REQUIRED)

Invoke rule-advisor using Agent tool:

subagent_type: "dev-workflows:rule-advisor"
description: "Rule selection"
prompt: "Task: $ARGUMENTS. Select appropriate rules and perform metacognitive analysis."

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

Frequently asked about Recipe Task

What else does shinpr publish alongside Recipe Task?
Recipe Task 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 Task 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 Task compare to other AI Engineering skills?
Recipe Task ranks #1815 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Task against them. Open each page to compare what they document and how they install.