meta-prompt-engineering
100 / 100 · Low risk
Fine to try.
Use when prompts produce inconsistent or unreliable outputs, need explicit structure and constraints, require safety guardrails or quality checks, involve multi-step reasoning that needs decomposition, need domain expertise encoding, or when user mentions improving prompts, prompt templates, structured prompts, prompt optimization, reliable AI outputs, or prompt patterns.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'meta-prompt-engineering' ] || [ -L ~/.agents/skills/'meta-prompt-engineering' ]; then echo 'A skill folder named meta-prompt-engineering already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/onfire7777/universal-ai-skills-library' "$d" && git -C "$d" checkout --quiet '2a76bf42ce5c860adf8d0f3fcf3f6804109ac65b' -- 'skills/meta-prompt-engineering' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/meta-prompt-engineering' ~/.agents/skills/'meta-prompt-engineering' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'meta-prompt-engineering' ~/.claude/skills/'meta-prompt-engineering' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/onfire7777/universal-ai-skills-library/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 2a76bf4 | 100 |