#103103rd of 149 in Skills, plugins and rules
prompt-master
Claude skill that rewrites vague requests into tool-specific prompts
- Stars
- 14.5k
- License
- MIT
- Last commit
- Oct 2026
2,230 on 25 Mar 202614,483 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Prompt Master is a Claude skill that takes a plain request and returns a single copyable prompt tailored to a target tool such as Cursor, Claude Code, Midjourney or Stable Diffusion. It detects the target, extracts nine intent dimensions, asks at most three clarifying questions, picks one of 13 templates, and can prepend a Memory Block of prior decisions. Install by uploading the ZIP in claude.ai or cloning into ~/.claude/skills.
Who it is for: Claude users who write prompts for coding agents and image models
Strengths
- Profiles for 30+ named tools, plus a four-question fallback for unlisted tools
- 13 prompt templates selected automatically, with a one-line strategy note per output
- Asks at most three clarifying questions before writing the prompt
- Installs as a skill folder via ZIP upload or git clone, no runtime needed
Weaknesses
- Output quality depends on Claude; no tests or benchmarks are shown in the README
- Memory Block must be re-supplied each new session; it does not persist
- Tool profiles name fast-moving models, so they can go stale without updates
- No tagged releases; versioning is unknown
What it needs
- no GPU
- Needs Claude.ai or Claude Code
- Models: Claude, ChatGPT, Gemini, Grok, DeepSeek-R1
Also in Skills, plugins and rules
See all 149| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 94 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |