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 TheMattBerman/meta-ads-kit --skill ad-copy-generatorgit clone --depth 1 https://github.com/TheMattBerman/meta-ads-kitWrote 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/themattberman/meta-ads-kit/ad-copy-generator)<a href="https://agentmods.dev/skills/themattberman/meta-ads-kit/ad-copy-generator"><img src="https://agentmods.dev/badge/skills/themattberman/meta-ads-kit/ad-copy-generator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02898 |
| Opus 5 | $0.00025 | $0.01449 |
| Sonnet 5 | $0.00010 | $0.00580 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
ad-copy-generator 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 8d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Copy Generator
Write Meta ad copy that's matched to the actual image creative — not generic copy pasted across every ad. Each image gets copy that reinforces its specific message, written in the brand's voice, informed by what's already working in the account.
Read workspace/brand/ per the _vibe-system protocol if available.
Brand Memory Integration
This skill reads brand context to make every piece of copy sound like the brand, not a template.
Reads: voice-profile.md, positioning.md, audience.md (all optional)
On invocation:
- Load
voice-profile.md— Match tone, vocabulary, forbidden words. Show: "Voice loaded — [tone summary]." - Load
positioning.md— Use angle as copy's foundation. Show: "Positioning: [angle]." - Load
audience.md— Know who we're talking to, their awareness level, their language. Show: "Writing for [audience summary]." - If
workspace/brand/doesn't exist — Skip. Ask for ICP, voice notes, and forbidden words inline. This skill works standalone.
Iteration Detection
Before writing, check for existing copy:
- Check
workspace/campaigns/{name}/ads/— If copy exists, show what's there. - Ask: "Revise existing, add variants, or start fresh?"
- If nothing exists — Proceed to generation.
The Process
Step 1: Pull What's Already Working
Before writing a single word, look at the account. What copy is converting?
# Top performers by CTR — last 30 days through official Ads CLI
meta --output json --no-input ads insights get \
--date-preset last_30d \
--fields spend,impressions,clicks,ctr,cpc,reach \
--sort ctr_descending \
--limit 20
For creative details, prefer official CLI resources where supported:
meta --output json --no-input ads ad get AD_ID
meta --output json --no-input ads creative get CREATIVE_ID
If official CLI does not expose a needed creative field yet, use direct Graph API only as an explicit fallback.
Extract patterns:
- Headline length and structure (questions? numbers? commands?)
- Body copy hooks (opens with pain? data? question? story?)
- Social proof claims (X customers, Y% increase, Z revenue)
- Reading level (short punchy vs. narrative)
- CTA that converts (Learn More vs Get Started vs Book Demo)
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.
- 8d ago First seen · 310 lines · 50 tokens per session scan A 279f2be60b42
ad-copy-generator is a skill published in the GitHub repository TheMattBerman/meta-ads-kit (315 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 2,898 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…