Recipe Driven Development — Development skill for Claude Code
a framework for creating specs to keep claude and you in sync.
How to install Recipe Driven Development
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lstebner/recipe-driven-development and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Recipe Driven Development does
a framework for creating specs to keep claude and you in sync.
Alternatives in Development
- Fix Cookbook Recipe — Fix Cookbook Recipe Validation Failures 2.1k ★
- Purpose — Orient yourself in pi-vs-cc — a collection of Pi coding agent extensions and agent specs that progressively de 527 ★
- Claude Code iOS Dev Guide — A comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink) 492 ★
README
Recipe-Driven Development
A workflow for building with AI coding tools, borrowed from the kitchen:
- You're the head chef. You decide what goes on the menu. Each recipe is a spec in constrained markdown that says what a screen, component, flow, data model, API or policy should be, with rules that can be checked. Claude can draft them for you, but nothing is built until you approve the recipe.
- The AI is the cook. Claude Code reviews the recipe, builds against it and checks its own work against it. It can't change an approved recipe without your sign-off: if it finds a problem, it proposes an amendment and you accept or reject it with one click.
- You taste it. Nothing is done until you say so. Claude can only mark a spec
verifiedwith a report showing every rule passing, and even then you're asked to confirm right in the session. You never have to leave your flow to edit a file.
Why does this exist?
Since I started working closely with Claude at the beginning of 2026, my role as a developer has shifted. I no longer write every line of code, and as a result I've started to lose track of everything my app does. That's mostly fine: the code should be written and organized however Claude can best work with it. But I still need to stay in control of the architecture and the core functionality.
Losing track shows up as two closely related problems:
- Claude makes assumptions faster than I can keep up with, especially in auto mode.
- Claude changes existing behaviour to get a task done when my request is too vague.
Recipe-driven development is my answer to both. It's sort of an evolution of test-driven development for AI coding: you write specs first, Claude builds against them, and the same specs are used to check the result afterwards.
That said, specs are not a replacement for testing your code. You still need tests to make sure the code works. Specs are for you as the developer, to make sure everything is working towa
Related Skills
New Recipe
Research a real thing (specs + photos) and build it as a ts23d recipe at real-asset quality
Sdlc Atlas
Agent-driven SDLC platform for Claude Code. Takes a requirement to production-ready code through governed pipe
TDD Sdd
Use-case-driven (SDD) and TDD harness for Claude Code and opencode. Human-approved specs, red → green → review
Specpilot Sync
Compare .specs/ against actual project state and propose fixes for drift
Source Agents
Keep AGENTS.md and CLAUDE.md in sync across your projects.
Agentsmd Sync
agentsmd-sync propagates a canonical AGENTS.md into the tool files assistants read (CLAUDE.md, Copilot, Cursor
Related Agents
Audit Agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md aga
Metadata Flow Structuring Agent
Take ONE metadata-driven application (its MAPL recipe + module info) plus its resolved personas, read the MAPL
Seam Analyzer
Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to