This is a heavyweight planning orchestrator that breaks down feature development into 17 distinct steps, from initial research through stakeholder interviews to final spec generation. It's designed for projects that need serious upfront analysis, not quick implementations. The workflow launches parallel subagents for codebase exploration, web research, and external LLM review (Gemini and Codex critique your plan), then synthesizes everything into self-contained implementation sections. The skill writes aggressively to disk, creating markdown files for research, interviews, specs, plans, reviews, and sectioned work breakdowns. Use this when you're planning something complex enough that you want multiple AI perspectives and a paper trail of every planning decision.

skills.sh installs
1.6K
GitHub stars
2.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add softaworks/agent-toolkit --skill gepetto --agent claude-code

Installs into .claude/skills of the current project.

Files

Gepetto

Orchestrates a multi-step planning process: Research → Interview → Spec Synthesis → Plan → External Review → Sections

CRITICAL: First Actions

BEFORE anything else, do these in order:

1. Print Intro

Print intro banner immediately:

═══════════════════════════════════════════════════════════════
GEPETTO: AI-Assisted Implementation Planning
═══════════════════════════════════════════════════════════════
Research → Interview → Spec Synthesis → Plan → External Review → Sections

Note: GEPETTO will write many .md files to the planning directory you pass it

2. Validate Spec File Input

Check if user provided @file at invocation AND it's a spec file (ends with .md).

If NO @file was provided OR the path doesn't end with .md, output this and STOP:

═══════════════════════════════════════════════════════════════
GEPETTO: Spec File Required
═══════════════════════════════════════════════════════════════

This skill requires a markdown spec file path (must end with .md).
The planning directory is inferred from the spec file's parent directory.

Sponsors

Details

Repository
github.com/softaworks/agent-toolkit
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building, Data Science & ML, Productivity & Planning
First seen
May 16, 2026

More from softaworks/agent-toolkit

All 43
1alirezarezvani avatarstatusalirezarezvani/claude-skillsShow DAG state, agent progress, and branch status for an AgentHub session. Use when the user runs /hub:status or asks how the AgentHub agents are doing.1.6Kskills.sh installs
2railwayapp avatarservicerailwayapp/railway-skillsThis skill should be used when the user asks about service status, wants to rename a service, change service icons, link services, or create services with Docke1.6Kskills.sh installs
3adobe avatarcreate-siteadobe/skillsCreates a new AEM Edge Delivery site from scratch — GitHub repo from the boilerplate, aem-code-sync installation, initial DA content (nav, footer, homepage), an1.6Kskills.sh installs
4alirezarezvani avatarsenior-architectalirezarezvani/claude-skillsThis skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dep1.5Kskills.sh installs
5madteacher avatarflutter-testingmadteacher/mad-agents-skillsWrite, fix, review, debug, and validate Flutter tests for apps, packages, and plugins. Use when adding unit tests, widget tests, integration tests, MethodChanne1.5Kskills.sh installs
6loops-so avatarloops-email-sending-best-practicesloops-so/skillsUse this skill when the user wants to review, audit, improve, or plan email sending best practices. This includes deliverability, inbox placement, sender reputa1.5Kskills.sh installs