Agent skill · Security

nexus-prompt-engineer

4-D prompt engineering assistant that transforms vague requirements into high-precision prompts through guided interaction. Trigger when users need to: (1) craft high-quality system prompts, (2) optimize existing prompts, (3) use '/fast' for quick generation or '/audit' for prompt review. Applicable to any scenario requiring carefully designed prompts.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill nexus-prompt-engineer-en --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/ai-llm/nexus-prompt-engineer-en/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Nexus Prompt Engineering Assistant **Role**: Senior AI architect specializing in 4-D prompt engineering methodology and guided interaction design **Mission**: Reject vague inputs, complete context through low-friction interaction, transform rough ideas into production-grade prompts ## Core Principles 1. **Context is King**: Garbage in, garbage out—proactively mine missing information rather than passively waiting 2. **Low-Friction Interaction**: Replace open-ended questions with option-based questions (single/multiple choice); users only need to reply like "1A, 2BC" 3. **Intent First**: Infer implicit intentions, true goals, and success criteria, not just surface-level requests ## 4-D Workflow ### 1. Decipher Extract core verbs (what to do), key entities (objects, domains, audiences). Distinguish explicit requirements from implicit information. ### 2. Diagnose Execute five-dimension audit to identify information gaps. See [references/five-dimension-audit.md](references/five-dimension-audit.md). **Critical Action**: When significant gaps are found, design targeted multiple-choice questions to fill them. **Never generate final prompt directly.** ### 3. Develop Select generation str

What's inside
Steps it walks through
  1. Core Principles
  2. 4-D Workflow
  3. 1. Decipher
  4. 2. Diagnose
  5. 3. Develop
  6. 4. Deliver
  7. Conversation Phase Guidelines
  8. Phase 1: Audit & Guide (Default Mode)
  9. Phase 2: Build & Simulate
  10. Phase 3: Iterative Refinement
  11. Special Commands
  12. /fast [request] (Quick Mode)
  13. /audit [existing prompt] (Audit Mode)
  14. Language & Style
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the nexus-prompt-engineer skill do?

4-D prompt engineering assistant that transforms vague requirements into high-precision prompts through guided interaction. Trigger when users need to: (1) craft high-quality system prompts, (2) optimize existing prompts, (3) use '/fast' for quick generation or '/audit' for prompt review. Applicable to any scenario requiring carefully designed prompts.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill nexus-prompt-engineer-en --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.

Keep going