CLAUDE CODE PLAYBOOKS
Ready-to-use workflows, templates & skills for your Claude Code projects
Copy-paste playbooks for Claude Code, Codex CLI, Windsurf, Cursor, Antigravity & more AI coding agents. Browse templates, skills and workflows to supercharge your development.
Browse Playbooks
Find a playbook that matches your workflow
claude /search file-organizationCopy CLAUDE.md
Copy the template to your project folder
cp playbook.md ~/project/CLAUDE.mdStart Using
Launch Claude Code with your new configuration
*Search Playbooks
└ Find your personalized automation stack
Playbooks(1200 total)
Recipe Development Lab
Track every version of a recipe with exact measurements, modifications, and lessons learned so you can actually recreate your best results.
Personal OS & Life Tracker
Build a markdown-based personal operating system with daily logs, habit tracking, fitness data, task management, and automated daily reviews — all managed by Claude Code.
Personal Feedback Analyzer
Analyze journal entries, code commits, and work patterns to identify behavioral insights and improvement opportunities.
Photo Organizer by Event
Organize photos by reading EXIF metadata and analyzing content to create Year > Month > Event folder structures automatically.
HTML Presentation Builder
Create clean, structured HTML presentations with speaker notes that can be presented directly or exported to PowerPoint.
Product Analysis
Multi-path parallel product analysis with cross-model test-time compute — spawn parallel agents to explore your product from multiple angles, then synthesize an actionable optimization plan.
Prompt Optimizer (EARS)
Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) — ideal for AI-generated code, products, and docs.
Promptfoo Evaluation
Configure and run LLM evaluations with Promptfoo — build promptfooconfig.yaml, write Python custom assertions, implement llm-rubric judges, and compare models systematically.
QA Expert
Establish a comprehensive QA process — test strategies, Google-standard test cases, P0–P4 bug tracking, quality metrics, OWASP security testing, and 90% coverage targets.
AI Prompt Builder
Turn rough ideas into optimized, high-performance prompts for any AI model — eliminates ambiguity, adds the right context, and structures output expectations so you get better results on the first try.
Product Marketing Context
Create and maintain a foundational product marketing context document that other marketing skills reference automatically.
Press Release (Amazon Working Backwards)
Write a customer-perspective press release before building — Amazon's Working Backwards forcing function for clarity. If you can't write a compelling PR, the idea may be weak.
Prioritization Framework Advisor
Pick the right prioritization framework (RICE, ICE, Value/Effort, Kano, Buy-a-Feature) based on product stage, team context, decision needs, and data availability — avoid framework whiplash.
Problem Framing Canvas (MITRE)
Run MITRE's three-phase canvas — Look Inward (your biases), Look Outward (who's affected and who's left out), Reframe (problem + How Might We) — to solve the right problem before solutions.
Problem Statement (User-Centered)
Write an empathy-driven problem statement (I am / Trying to / But / Because / Which makes me feel) that frames product work around user outcomes — not feature requests or business symptoms.
Product Sense Interview Answer
Six-part spine (clarify → rationale → goal → segmentation → pain → solution) for PM product-sense interviews — sound thoughtful out loud instead of over-scripted on paper.
Product Strategy Session
End-to-end product strategy workflow orchestrating positioning, problem framing, discovery, prioritization, and roadmap across 6 phases over 2-4 weeks — with explicit decision points.
Proto-Persona
Create a lightweight, hypothesis-driven persona in hours from existing research, market signals, and team knowledge — a working customer profile before deeper validation.
Processize Before You Productize
Turn any product idea into a manual process you can deliver today — before writing a line of code. Document the 'magic piece of paper,' charge for it, then automate only what you've proven works.
Pricing Test
Test pricing strategies with synthetic data.
Programmatic Seo
Plan programmatic SEO pages.
Prompt Test
A/B test content variations.
Publish Blog
Publish blog posts.
Qbr Plan
Prepare a Quarterly Business Review.
Page 41 of 50
?Frequently Asked Questions
└ Everything you need to know about Claude Code workflows, templates and skills
Claude Code Playbooks are ready-to-use workflows, templates and skills that you copy-paste as a CLAUDE.md file in your project folder. They tell Claude Code exactly how to behave — what to build, how to structure files, what rules to follow — so you get consistent, high-quality results without writing complex prompts from scratch.
It takes three steps: browse the directory to find a playbook that matches your use case, copy the CLAUDE.md template into your project folder, then launch Claude Code. The agent reads the configuration automatically and follows the workflow. No setup, no configuration files, no coding required.
Not at all. These playbooks are designed for non-developers — marketers, analysts, founders, researchers, students, and anyone who wants to automate work with AI. Each template is a plain-text file you copy-paste. If you can create a folder and paste text into a file, you can use a playbook.
Yes. Every playbook on this directory is completely free to use, modify and share. The entire project is open source on GitHub under a permissive license. There are no paywalls, no premium tiers, no sign-up required.
Every playbook is a real-world use case that has been submitted and tested by the community before being curated on this directory. These are not theoretical templates — they are workflows that people actually rely on for their daily work, verified to produce reliable results.
Playbooks are built for Claude Code, but many templates and skills also work with other AI coding agents including Codex CLI, Windsurf, Cursor, Antigravity, Perplexity and more. The CLAUDE.md format is simple enough that most agents can interpret and follow the instructions.
Absolutely. The directory is community-driven and we encourage submissions. You can contribute a new playbook directly through our GitHub repository or use the submission form on the homepage. Share a workflow that works for you so others in the community can replicate and benefit from it.