Prompt Master

Trust Score 89/100

from prompt-master8,737

Generates production-ready, token-efficient prompts tailored to specific AI tools and tasks.

triggers:write a promptimprove promptfix my promptadapt prompt forprompt engineer

GitHub SKILL.md

What it does

Prompt Master turns a user's intent into a single, production-ready prompt optimized for a target AI tool. It enforces strong rules for safety and efficiency (confirm tool, avoid unnecessary Chain-of-Thought for certain models, limit clarifying questions) and provides tool-specific guidance and templates for Claude, GPT, Gemini, Ollama, and image/video/3D generation tools.

When to use it

Use this skill when you need a copy-paste-ready prompt for an LLM, image, or video generator and want token-efficient, tool-specific instructions (e.g., "Write a DALL·E 3 prompt", "Create a Claude agentic prompt"). It activates only when the user explicitly asks to write, fix, improve, or adapt a prompt.

What's included

Scripts: none declared in the repo snapshot
References: the skill contains extensive in-markdown guidance and references/templates links (if present)
Instructions: detailed procedural rules (primacy zone, hard rules, execution logic, diagnostic checklist, agentic warnings) that guide prompt construction and routing

Compatible agents

Best suited for assistants that generate text prompts for remote models (Claude, OpenAI GPT-family, Gemini, Qwen) and for operators producing prompts for image/video tools (Midjourney, DALL·E, Stable Diffusion).

Audit Summary

Prompt Master is a comprehensive prompt-engineering skill that routes user requests to tool-specific templates and optimization strategies. It covers 20+ AI tools and platforms with detailed guidance per tool. The SKILL.md is well-structured with three zones (Primacy, Middle, Recency) and explicit hard rules. No scripts included — purely instructional. Credential safety section explicitly forbids embedding secrets. Very thorough diagnostic checklist and decompiler mode.

Watch Out

References external files (references/templates.md, references/patterns.md) that must exist in the skill directory
Long SKILL.md body (~3000 words) — could benefit from more aggressive progressive disclosure

Notes

No security concerns whatsoever — includes explicit credential safety and input sanitization rules. Well-crafted skill with broad tool coverage. No scripts to run, so scoring is based entirely on static analysis of SKILL.md.

Information

Repository: prompt-master
Stars: 8,737

Trust Score

Overall89

Security95

Code Quality85

Architecture78

Usefulness82

Related Skills

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Retriever (Membrane CLI)

Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.

Yielding Bear — Unified LLM Routing

A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

Seedance Prompt — Short

Build, validate, and compress short-form Seedance 2.0 prompts (30–100 words) using a layered compression engine and @Tag delegation for quad-modal (T2V/I2V/V2V/

Smalltalk MCP

Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.

Back to Skills