prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
npx skills add majiayu000/claude-skill-registry --skill prompt-master-nidhinjs-prompt-master --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Operates as a prompt engineer to transform a rough idea into a single production-ready prompt tailored for a specific AI tool (e.g., LLMs, Cursor, Midjourney, image/video/Coding agents). Activates only when the user explicitly requests writing, fixing, improving, or adapting a prompt for a named tool; does not activate for general conversation or non-prompt-engineering tasks.
How it works
- It identifies the target AI tool and the exact user intent from the request.
- It extracts the concrete prompt goal and formats a single, production-ready prompt optimized for the specified tool.
- It adheres to a strict output format: a copyable prompt block, a target tool line, and optional setup notes.
- It should not include explanations or extraneous content beyond the required prompt block unless the user asks for setup guidance.
- It enforces a limit of up to 3 clarifying questions before producing a prompt and prioritizes simple prompting techniques over complex meta-reasoning frameworks in single-prompt contexts.
- It may include placeholders for copywriting prompts: [TONE], [AUDIENCE], [BRAND VOICE], [PRODUCT NAME].
When to use it
Use when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (e.g., LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). It does not activate for general conversation, coding tasks, or other non-prompt-engineering work.
What it can touch
Follows the tool-specific guidance to craft a prompt block ready to paste into the target tool. It must read the target tool and produce a prompt accordingly.
Caveats
Activated only upon explicit user request to work on a prompt for a named tool; avoids adding extraneous features beyond the requested prompt. Follow-up clarifications are limited to at most 3 questions before generating the prompt.
## PRIMACY ZONE — Identity, Hard Rules, Output Lock **Who you are** When generating or improving prompts, operate as a prompt engineer. Take the rough idea, identify the target AI tool, extract the actual intent, and output a single production-ready prompt optimized for that specific tool with zero wasted tokens. This role applies only to prompt generation; for all other tasks, follow default behavior and safety guidelines. Do not discuss prompting theory unless explicitly asked. Do not show framework names in output. Build prompts one at a time, ready to paste. --- **Hard rules — NEVER violate these** - Do not output a prompt without first confirming the target tool — ask if ambiguous - Prefer simpler techniques (role assignment, few-shot, grounding anchors, chain of thought) over complex meta-reasoning frameworks in single-prompt contexts. The following techniques carry higher fabrication risk when used in a single prompt and should only be applied when the user explicitly requests them and the target tool supports them: - **Mixture of Experts** -- simulated multi-persona routing in a single forward pass - **Tree of Thought** -- simulated branching without real parallel execution
- PRIMACY ZONE — Identity, Hard Rules, Output Lock
- MIDDLE ZONE — Execution Logic, Tool Routing, Diagnostics
- Intent Extraction
- Tool Routing
- Credential Safety
- Input Sanitization -- Pasted Prompts
- Diagnostic Checklist
- Memory Block
- Safe Techniques — Apply Only When Genuinely Needed
- Agentic Output Warning
- RECENCY ZONE — Verification and Success Lock
- Reference Files
What does the prompt-master skill do?
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-master-nidhinjs-prompt-master --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.