Senior Prompt Engineer

🌐Community
by borghei · vlatest · Repository

Crafts highly effective prompts for complex AI models, maximizing output quality and streamlining workflows for optimal results.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add borghei-senior-prompt-engineer npx -- -y @trustedskills/borghei-senior-prompt-engineer
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "borghei-senior-prompt-engineer": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/borghei-senior-prompt-engineer"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

Senior Prompt Engineer

What it does

This skill acts as an expert-level prompt engineer, optimizing your instructions to maximize AI model performance and output quality. It refines complex requests into precise, structured prompts that reduce ambiguity and improve task accuracy.

When to use it

  • You need to extract specific data formats or structured outputs from unstructured text.
  • Your current prompts are yielding inconsistent results or hallucinations in critical tasks.
  • You require the AI to adopt a specialized persona with strict constraints for creative writing or coding.
  • You want to optimize prompt length and token usage without losing essential context.

Key capabilities

  • Advanced prompt structuring and optimization techniques.
  • Persona adoption and role-playing configuration.
  • Constraint enforcement and output formatting control.
  • Iterative refinement of ambiguous user requests.
  • Context window management for complex multi-step tasks.

Example prompts

  • "Act as a senior prompt engineer to rewrite my request for generating Python unit tests so it produces fewer errors."
  • "Optimize this instruction set for summarizing legal contracts into bullet points while maintaining strict confidentiality constraints."
  • "Refine the following prompt to ensure the AI outputs JSON only, with no markdown formatting or conversational filler."

Tips & gotchas

Ensure you provide enough context about your specific goals and desired output format before asking for optimization. This skill works best when paired with clear initial instructions rather than vague generalities.

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
borghei
Installs
53

🌐 Community

Passed automated security scans.