masriyan/gemini-security-skills · Archived

prompt-enhancement

Prompt engineering and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability.

Installation

$ npx skills add masriyan/gemini-security-skills --skill prompt-enhancement

Summary

  • Prompt engineering and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability.
  • Use when rewriting vague prompts, adding constraints, reducing ambiguity, improving safety, creating reusable prompt templates, or converting goals into actionable agent instructions.

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from masriyan/gemini-security-skills · top by installs.

npx skills add masriyan/gemini-security-skills

Browse all from masriyan/gemini-security-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 3
License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,540 B
  • docs SUMMARY.md 407 B

History

  1. First recorded snapshot · 1 installs

SKILL.md

Prompt Enhancement

Operating Rules

  • Preserve the user's intent; do not over-constrain creative or exploratory tasks.
  • Separate objective, context, inputs, constraints, output format, and verification criteria.
  • Make implicit assumptions explicit when they affect outcome quality.
  • Prefer testable instructions over personality-heavy wording.

Workflow

  1. Diagnose the prompt for missing context, ambiguous goals, conflicting constraints, and weak success criteria.
  2. Rewrite into a direct task with ordered steps and clear boundaries.
  3. Add output format only when structure improves usability.
  4. Add examples sparingly; use examples that demonstrate edge cases, not just happy paths.
  5. Include a short rationale when the user needs to understand tradeoffs.

Prompt Template

Objective: <what outcome is required>
Context: <facts, files, audience, constraints>
Inputs: <data the model should use>
Process: <important reasoning or execution steps>
Output: <format, length, tone, artifacts>
Validation: <how to check correctness>
Boundaries: <what to avoid or ask before doing>