Skip to content
Back to skills

Fieldops Prompt Refiner

ASecurity

Transforms rough, ambiguous, overloaded, or reusable requests into precise, execution-ready prompts for coding agents. Use when asked to improve, rewrite, refine, tighten, structure, modularize, audit, or professionalize a prompt, AGENTS.md instruction set, task brief, system prompt, or agent workflow. Preserves intent while clarifying outcome, scope, inputs, constraints, authority, verification, and deliverables. Does not apply when merely executing an already well-specified task.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 6, 2026
ai-agents

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add download4you/n2-fieldops --skill fieldops-prompt-refiner --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fieldops Prompt Refiner?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Fieldops Prompt Refiner
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/download4you-fieldops-prompt-refiner/badge)](https://www.skillsdirectory.com/skills/download4you-fieldops-prompt-refiner)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: fieldops-prompt-refiner
description: Transforms rough, ambiguous, overloaded, or reusable requests into precise, execution-ready prompts for coding agents. Use when asked to improve, rewrite, refine, tighten, structure, modularize, audit, or professionalize a prompt, AGENTS.md instruction set, task brief, system prompt, or agent workflow. Preserves intent while clarifying outcome, scope, inputs, constraints, authority, verification, and deliverables. Does not apply when merely executing an already well-specified task.
---

# Prompt Refiner

1. Extract outcome, audience/agent, inputs, environment, and completion condition.
2. Separate hard constraints from preferences and examples.
3. Ask only about ambiguities that materially change safe execution.
4. Remove duplication, conflict, unenforceable claims, and low-value prose.
5. Organize with `references/prompt-architecture.md`.
6. Add proportional evidence and verification requirements.
7. Preserve language, terminology, intent, and authority boundary.
8. Return a copy-ready prompt plus a short design note when useful.

For large reusable profiles, prefer modular skills and references over one always-loaded prompt. Never claim a prompt can override higher-priority runtime instructions.

Files in this skill

  • SKILL.md1.2 KB
  • agents/openai.yaml227 B
  • references/prompt-architecture.md402 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.