Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/nidhinjs/prompt-master/llms.txt

Use this file to discover all available pages before exploring further.

Prompt Master doesn’t ask you to choose a prompt framework. It reads your request, identifies the target AI tool, infers the task type, and silently routes to whichever of the 12 built-in templates will produce the most accurate, token-efficient output. You never see the framework name — you see a single, copyable prompt that’s already been structured, audited, and trimmed. The routing happens in one step inside Prompt Master’s 7-stage pipeline. Every template carries its own set of required components and anti-pattern checks, so the final prompt always has what the target tool needs and never has what wastes its context window.
Silent routing is intentional. Exposing the framework name would add noise to the output. The goal is a prompt you can paste, not a lesson in prompt engineering. If you want to understand which framework was used and why, ask: “What template did you use for that prompt, and why?”

The 12 Templates at a Glance

TemplateBest For
RTF (Role, Task, Format)Fast one-shot tasks
CO-STAR (Context, Objective, Style, Tone, Audience, Response)Professional documents, reports, business writing
RISEN (Role, Instructions, Steps, End Goal, Narrowing)Complex multi-step projects
CRISPE (Capacity, Role, Insight, Statement, Personality, Experiment)Creative work, brand voice, iterative content
Chain of ThoughtMath, logic, debugging, multi-step analysis
Few-ShotConsistent structured output, pattern replication
File-Scope TemplateCursor, Windsurf, Copilot — any code editing AI
ReAct + Stop ConditionsClaude Code, Devin, AutoGPT — any autonomous agent
Visual DescriptorMidjourney, DALL-E, Stable Diffusion, Sora — generation
Reference Image EditingEditing an existing image — detects edit vs. generate automatically
ComfyUINode-based image workflows — positive/negative split per checkpoint
Prompt DecompilerBreaking down, adapting, simplifying, or splitting existing prompts
Template MAgentic or multi-step tasks for Claude Code with Opus 4.7/4.8
Template M is the newest addition to the library (added in v1.7.0). It handles scope definition, acceptance criteria, stop conditions, and session strategy specifically for Claude Code running on Opus 4.7 or 4.8. If your task involves Claude Code doing autonomous multi-step work, Template M takes precedence over standard ReAct routing.

How Auto-Selection Works

Prompt Master evaluates three signals before committing to a template:
1

Target tool detection

The tool name (Cursor, Midjourney, Claude Code, GPT-4o, etc.) determines which template family is eligible. Image generation tools route to the image template family. Autonomous coding agents route to the agentic family. LLMs route to text templates.
2

Task type classification

Within the eligible family, the task type narrows the choice. A creative brief routes to CRISPE rather than RTF. A logic problem routes to Chain of Thought rather than CO-STAR. A pattern-replication task routes to Few-Shot.
3

Component completeness check

Prompt Master checks whether the required components for the candidate template are satisfiable from the information you’ve provided. If critical components are missing, it asks at most 3 clarifying questions before generating.

Template Families

The 12 templates are organized into three families. Each family has its own documentation page with component breakdowns, routing logic, and real generated examples.

Text Templates

RTF, CO-STAR, RISEN, CRISPE, Few-Shot, and Chain of Thought — the core text-generation frameworks for LLMs and writing tasks.

Agentic Templates

File-Scope Template, ReAct + Stop Conditions, and Template M — structured frameworks for coding agents and autonomous AI systems.

Image Templates

Visual Descriptor, Reference Image Editing, ComfyUI, and Prompt Decompiler — output-calibrated formats for every image and media AI.

What You Never See

Prompt Master excludes several techniques that carry a high fabrication risk or produce unstable outputs in practice. These are permanently off the routing table regardless of the task:
TechniqueReason excluded
Mixture of ExpertsUnstable cross-model outputs; fabrication-prone
Tree of ThoughtProduces branching structures that most models don’t resolve reliably
Graph of ThoughtNo consistent implementation across target tools
Universal Self-ConsistencyAdds token cost without measurable accuracy gains for standard tasks
Prompt chaining as a layered techniqueLayered chaining masks errors and makes debugging impossible
None of these techniques appear in any generated prompt. If you explicitly request one, Prompt Master will explain why it’s excluded and offer the safest equivalent alternative.

Safe Techniques Applied Inline

Beyond the 12 templates, Prompt Master applies four safe techniques within a template when the task genuinely benefits from them. They are never added by default.
TechniqueApplied when
Role AssignmentA domain-specific expert identity measurably improves output precision
Few-Shot ExamplesFormat consistency is easier to show than describe (2–5 examples)
Grounding AnchorsThe task involves factual claims, citations, or recall-sensitive information
XML Structural TagsThe target is a Claude-based tool and the prompt has 3+ distinct logical sections
Chain of Thought is also a safe technique, but it is never applied to o3, o4-mini, R1, or Qwen3-thinking models. Those models perform their own internal reasoning — adding explicit CoT instructions degrades their output.

Build docs developers (and LLMs) love