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(1263 total)
Add New Playbook
Suggest a new playbook for the community
Academic Research Skills for Claude Code: Install & Workflow
The academic-research-skills plugin (Imbad0202/academic-research-skills on GitHub): deep research, literature review, paper writing, citation checks, and peer review for Claude Code — with a project brief that keeps every /ars command on-topic.
Accessibility Engineering for Components
Build accessible UI components at the code level, not just the audit level — 14 concrete engineering principles (focus-visible over bare :focus, roving tabindex for composite widgets, inert-based modal focus trapping, WCAG 2.5.8 hit-area minimums), a common-mistakes table with fixes, and a severity-rated review format ending in a hard Block/Needs-changes/Approve verdict.
Adversary Emulation: MuddyWater
An intelligence-grounded, authorized purple-team emulation profile for MuddyWater (MITRE ATT&CK G0069), Iran's MOIS-linked cyber-espionage group — attribution, targeting, representative TTPs by ATT&CK tactic, emulation guidance mapped to generic red-team tooling, and paired detection/defense recommendations for every offensive technique, all under an explicit authorized-use caveat.
Adversary Emulation: Turla
An intelligence-grounded, authorized purple-team emulation profile for Turla (MITRE ATT&CK G0010), Russia's FSB-linked espionage group — attribution, distinctive TTPs (satellite C2 hijacking, steganographic email backdoors, parasitizing rival APT infrastructure), emulation guidance mapped to generic red-team tooling, and paired detection recommendations, under an explicit authorized-use and lab-only caveat for rootkit techniques.
AI Agent Red Team Methodology
A first-principles methodology for authorized red-team exercises against AI products, agents, MCP servers, skills, and repositories — capability and trust-boundary modeling, AI-specific attack hypothesis families (prompt injection, tool misuse, data leakage, SSRF), harmless-proof testing with canaries, one-variable-at-a-time adaptive iteration, and business-language evidence-based reporting.
Contribution PR Review
Review an external contributor's PR the way an open-source maintainer should — check automated bot security findings first (across every channel they might post to), watch specifically for suspicious AGENTS.md or workflow-permission changes, scale size and test-coverage expectations by contributor experience, and separate intent/scope alignment from code quality that bots already covered.
Datadog Error Triage to PR
Take Datadog Error Tracking issues from raw occurrence counts to a reviewable, tested PR — a five-class bug taxonomy that filters out infra noise and deploy-skew before ranking, a recency premium that catches fresh regressions early, a mandatory approval gate before any fix is written, and a test-first fix workflow that generalizes past the one reported occurrence.
Detecting Pharmacovigilance Signals
Mine FDA FAERS adverse-event data for drug-reaction disproportionality signals — PRR, ROR, EBGM, and IC (BCPNN) computed from a real 2x2 contingency table, working Python against the free public OpenFDA API, and the gotchas (404-means-zero, .exact required for phrase counting, small-count instability) that produce silently wrong numbers if missed.
I Have ADHD Skill for Claude: ADHD-Shaped Output
The i-have-adhd Claude skill (ayghri/i-have-adhd on GitHub): shape every response for an ADHD reader — lead with the next action, number bounded steps, restate state every turn, suppress tangents, give concrete time estimates, and make wins visible — grounded in five specific facts about how ADHD changes reading, not just 'be brief.'
Agent DX CLI Scale
A 7-axis, 0-21 scoring scale for evaluating how well a CLI is designed for AI agents rather than humans — machine-readable output, raw payload input, schema introspection, context-window discipline, input hardening, safety rails, and agent knowledge packaging.
Elon Musk Engineering & First-Principles Thinking Partner
A thinking-partner lens for hard engineering, manufacturing, and execution questions, built from documented first-principles methodology across SpaceX and Tesla — the five-step engineering process, the idiot index, 10x vs 10% thinking — deliberately scoped away from politics and personal topics, with a standing simulation disclaimer.
Energy Procurement Strategy
Codified expertise for electricity and gas procurement, tariff optimization, demand-charge management, and renewable PPA evaluation — the working knowledge of a senior C&I energy procurement manager running a $15M-$80M annual spend across dozens of facilities.
Agent Design Philosophy
A mental model for designing AI agents in any domain — the model already knows how to be an agent, so design is about capabilities, knowledge, and context, added only as far as a Progressive Complexity ladder (basic → planning → subagents → skills) that real usage actually demands.
Business Analysis Framework Toolkit
A two-phase consulting-report system: build a rigorous analysis framework from a 20+ framework catalog (SWOT, Porter's Five Forces, BCG Matrix, TAM-SAM-SOM, DCF, and more) with per-chapter data requirements, then synthesize collected data into a McKinsey-voice report under a strict no-hallucinated-numbers rule.
Documentation Review System
Mode-routed documentation review that diagnoses a page against its doc type and seven quality dimensions before touching a sentence, then picks the intervention level — maintenance, improve, rewrite, author, or strategy — that actually matches what's wrong.
Agent Prompt Architect
A compact seven-field skeleton (Role, Goal, Inputs, Constraints, Process, Output, Verification, Fallback) and a fast refinement loop for turning vague intent into a prompt an agent can execute reliably every time.
CEO-Mode Plan Review
Review a technical or product plan the way a great CEO would — pick a mode (expand scope, cherry-pick expansions, hold scope, or cut ruthlessly), then apply nine prime directives and eleven cognitive patterns to catch every silent failure, missing edge case, and unnamed error before it ships.
Designer's Figma-to-Production Workflow
A structured discuss-plan-execute-verify loop that takes a designer from a Figma file to a deployed, pixel-perfect production site — using Claude Code plus the GSD meta-prompting system, no traditional coding required.
Academic Rebuttal Writer
Classify reviewer comments, choose a deliberate response strategy per comment (Accept/Defend/Clarify/Experiment), and draft a professional rebuttal using success patterns distilled from spotlight-accepted papers.
Agent SDK App Builder
Scaffold new Claude Agent SDK applications in TypeScript or Python, and verify existing ones against official SDK patterns before you ship.
Blog-to-Social Publisher
Turn one blog post into an X thread, LinkedIn post, Medium article, and Dev.to RSS feed — zero dependencies, works in any repo type.
Bulk Legal Document Review to Excel Matrix
Turn dozens or hundreds of contracts, NDAs, or leases into a single sourced Excel matrix — one row per document, one column per review question, color-coded risk flags.
Compounding PM Operating System
A persistent PM profile that learns your frameworks, vocabulary, and decision patterns across product cycles — comparing predictions to actuals so each cycle gets sharper than the last.
Distinctive Frontend Design
Design lead guidance for building frontends that don't read as AI-generated — deliberate palette, typography, and layout choices grounded in the actual subject, with a built-in self-critique pass before you write code.
Page 1 of 53
?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.