ai-collab-playbook

Provides a reusable prompt template framework that decomposes complex research, writing, and coding tasks into structured sections (context, constraints, examples, output format). Templates are designed to be chained together and adapted across different AI models (Claude, GPT, Codex) by maintaining consistent instruction patterns and role definitions that improve consistency and reproducibility across multi-turn conversations.

Defines a system for assigning specific roles and responsibilities to AI agents within multi-turn conversations (e.g., 'code reviewer', 'research synthesizer', 'writing editor'). Each role includes explicit behavioral rules, scope boundaries, and interaction patterns that persist across conversation turns, enabling the AI to maintain consistent context and decision-making authority without requiring full context re-specification in each message.

Provides a sequence of specialized prompts designed to guide AI through research tasks: paper summarization, cross-paper synthesis, gap identification, and argument extraction. Each prompt is optimized for a specific research subtask and includes examples of desired output formats, enabling researchers to decompose literature review work into AI-assisted steps that maintain academic rigor and citation accuracy across multiple sources.

Provides a structured sequence of prompts for writing tasks: outline generation, draft creation, editing passes (clarity, tone, structure), and final polish. Each step includes specific feedback mechanisms and revision instructions that guide the AI to improve writing iteratively. The workflow maintains document context across steps, allowing writers to refine arguments and style without restarting from scratch.

Defines a set of prompts for code generation, review, and refactoring that embed project-specific coding standards, architecture patterns, and quality constraints. Prompts include examples of desired code style, error handling patterns, and testing requirements, enabling AI code generation to align with team standards. The system supports both single-file generation and multi-file architectural changes by maintaining context about project structure and dependencies.

Provides a collection of modular, reusable prompt components (skills) that can be combined to build complex AI workflows. Skills are organized by function (e.g., 'extract key points', 'generate examples', 'identify contradictions') and include clear input/output specifications, enabling users to compose custom workflows by chaining skills together without writing prompts from scratch.

Provides guidance for adapting prompts across different LLM platforms (Claude, GPT, Codex, local models) by documenting model-specific behaviors, instruction formats, and output patterns. The playbook includes examples of how to adjust prompts for different model capabilities (e.g., Claude's strong reasoning vs GPT's broader knowledge) while maintaining consistent intent, enabling users to switch models or use multiple models in parallel without complete prompt rewrites.

Provides patterns for managing long-form AI collaboration sessions that maintain context, conversation history, and task state across multiple turns without losing information or requiring full context re-specification. Includes techniques for summarizing conversation history, managing token limits, and preserving key decisions and constraints across session boundaries, enabling researchers and developers to maintain productive AI partnerships over extended periods.