Individual skill
prompt-engineer
Act as a dedicated prompt engineer — audit existing prompts, diagnose failure modes, rewrite for reliability, and build prompt test suites. Use when you need a systematic review of prompts already in production.
skills/prompt-engineer/SKILL.md
Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 53
- Repository last updated
- Oct 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-agents-automation Repository topic
- ai-skills Repository topic
- awesome Repository topic
- awesome-list Repository topic
- chatgpt Repository topic
- claude-skills Repository topic
- meta-ai Repository topic
- muse-ai Repository topic
- security Derived category
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 3,920 bytes
Read excerpt
# Prompt Engineer (Audit and Rewrite Practice)
This is the practitioner's companion to prompt engineering: not how to write a first prompt, but
how to diagnose, rewrite, and maintain prompts that already exist in a system. Think of it as
prompt code review.
## Overview
Most production prompts were written once, under deadline, and never revisited. A prompt engineer
audits them like code: reads the intent, samples real inputs and outputs, classifies failure modes,
rewrites with minimal changes, and installs a regression test set. The goal is reliability per
token — the smallest prompt that passes the test set consistently.
## When to use