Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Ad-Superpowers/ad-superpowers-plugin --skill meta-prompt-engineering-librarygit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/meta-prompt-engineering-library)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/meta-prompt-engineering-library"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/meta-prompt-engineering-library/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/meta-prompt-engineering-library"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/meta-prompt-engineering-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.03337 |
| Opus 5.5 | $0.00036 | $0.01335 |
| Sonnet 5.5 | $0.00018 | $0.00667 |
| Haiku 4.5 | $0.00009 | $0.00334 |
Grade A, and why
meta-prompt-engineering-library scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineering Library
Overview
This skill provides a collection of optimized prompts for leveraging AI (ChatGPT, Claude, Midjourney, etc.) within Meta Ads workflows, from creative briefing to data analysis and copy generation.
Prompt Fundamentals
Anatomy of a Good Prompt
┌─────────────────────────────────────────────────────────────────┐
│ PROMPT STRUCTURE (CRISP Framework) │
│ │
│ C - Context: Provide background and situation │
│ R - Role: Define the expertise you need │
│ I - Instructions: Give clear, specific directives │
│ S - Specifics: Add details, constraints, formats │
│ P - Parameters: Output format, length, style │
└─────────────────────────────────────────────────────────────────┘
Prompt Quality Levels
| Level | Example | Quality |
|---|---|---|
| Bad | "Write ad copy" | Vague, generic result |
| Better | "Write Facebook ad copy for a fitness app" | Better but still incomplete |
| Good | "You are a direct response copywriter. Write 3 Facebook ad copy variations for FitPro app targeting women 25-40 who want to lose weight. Use PAS framework. Max 125 characters primary text." | Specific, actionable |
Prompt Categories
Category 1: Ad Copy Generation
Primary Text Generator
PROMPT: AD COPY GENERATOR
You are an experienced Meta Ads copywriter specialized in
direct response advertising.
CONTEXT:
- Product: [PRODUCT/SERVICE]
- Target Audience: [DEMOGRAPHICS + PSYCHOGRAPHICS]
- Unique Selling Point: [USP]
- Funnel Stage: [TOFU/MOFU/BOFU]
- Offer: [IF APPLICABLE]
TASK:
Write 5 variations of primary text for a Meta ad.
SPECIFICATIONS:
- Framework: Alternate between PAS, AIDA, and BAB
- Hook: First sentence must grab attention within 3 seconds
- Length: 100-150 characters (first 125 visible)
- Tone: [Casual/Professional/Urgent/Friendly]
- CTA: End with a clear call-to-action
OUTPUT FORMAT:
For each variation:
1. [Framework used]
2. Primary text
3. Headline suggestion (max 40 characters)
4. CTA button recommendation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 522 lines · 91 tokens per session scan A eb6ebc60be4c
meta-prompt-engineering-library is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 91 tokens to every session and 3,337 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
ai-hive-simulate-datawhale
A research and content-planning workflow that studies Datawhale's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.
ai-hive-simulate-david-holz
A research and content-planning workflow that studies David Holz's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.
ai-hive-simulate-david-sacks
A research and content-planning workflow that studies David Sacks's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.
ai-hive-simulate-demis-hassabis
A research and content-planning workflow that studies Demis Hassabis's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.
ai-hive-simulate-dn-samuel
A research and content-planning workflow that studies DN-Samuel's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.
ai-hive-simulate-donbesilent
A research and content-planning workflow that studies Donbesilent's public material and turns its general methods into original work using your own facts and experience. It can also organise authorised documents into a source-linked reference library.