nova: Skill for Claude Code

.claude/skills/meta-ads-manager/SKILL.md

meta-ads-manager is a skill for Claude Code from djbelieny/nova. It costs 73 tokens per session (3,279 once invoked), scanned A, original, MIT.

A skill for managing advertising campaigns on Meta, the company behind Facebook and Instagram. It covers campaign setup, audiences, budgets, ad content, testing, measurement, and optimization.

In plain words
What is it for?
Use it to create or manage Facebook and Instagram campaigns, write ad copy, choose audiences, set budgets, run A/B tests, build retargeting campaigns, and produce performance reports.
Why use it?
It organizes the many choices involved in running ads and helps assess whether campaigns are reaching the intended business goal. It also supports comparing different ad versions and improving weak results.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is djbelieny/nova's own configuration. It tells Claude Code how to work on nova itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nova configures →

Reuse

Borrowing it

Nothing to install: this file belongs to djbelieny/nova. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/djbelieny/nova/main/.claude/skills/meta-ads-manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/djbelieny/nova

Made for: Claude Code.

Wrote 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.

agentmods badge for meta-ads-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/djbelieny/nova/meta-ads-manager/github.svg)](https://agentmods.dev/skills/djbelieny/nova/meta-ads-manager)
Your own site
<a href="https://agentmods.dev/skills/djbelieny/nova/meta-ads-manager"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/meta-ads-manager/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.

agentmods 80×15 button for meta-ads-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/djbelieny/nova/meta-ads-manager"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/meta-ads-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.03279
Opus 5 $0.00036 $0.01639
Sonnet 5 $0.00015 $0.00656
Haiku 4.5 $0.00007 $0.00328

Measured 9d ago against content hash 34bada09557b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

meta-ads-manager 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 9d 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.

.claude/skills/meta-ads-manager/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta Ads Manager

This skill handles end-to-end Meta advertising — from campaign strategy and creation to optimization and reporting across Facebook and Instagram.

When to Use This Skill

  • Creating new ad campaigns (Facebook or Instagram)
  • Writing ad copy and headlines
  • Defining audience targeting (custom, lookalike, interest-based)
  • Setting and managing ad budgets
  • Analyzing campaign performance (ROAS, CPA, CTR)
  • A/B testing ad variations
  • Optimizing underperforming campaigns
  • Creating retargeting campaigns
  • Scaling winning ads
  • Generating performance reports

Campaign Architecture

Meta Ads Structure

Account
└── Campaign (objective: what you want)
    └── Ad Set (audience + budget + placement + schedule)
        └── Ad (creative + copy + CTA)

Campaign Objectives (choose one per campaign)

Objective Use When Key Metric
Awareness Brand building, reach CPM, Reach
Traffic Drive website visits CPC, CTR
Engagement Post likes, comments, shares CPE, Engagement Rate
Leads Collect emails/phone via form CPL, Lead Volume
App Promotion Drive app installs CPI, Install Volume
Sales E-commerce conversions ROAS, CPA, Conversion Rate

Budget Strategy

Daily vs. Lifetime Budget:

  • Daily budget: Best for always-on campaigns. Meta spends roughly this amount each day.
  • Lifetime budget: Best for time-limited promotions. Meta optimizes spend across the full period.

Budget Guidelines:

  • Minimum: $5/day per ad set (Meta's minimum)
  • Testing: $20-50/day per ad set to exit learning phase quickly
  • Learning phase: ~50 conversions per ad set per week needed
  • Scale: Increase budget by max 20% every 3 days (avoid resetting learning)

Advantage Campaign Budget (CBO):

  • Let Meta distribute budget across ad sets automatically
  • Best when you have 3+ ad sets and want Meta to find the best one
  • Set minimum/maximum spend per ad set if needed

Read the full file on GitHub · 369 lines

Changes

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.

  1. 9d ago First seen · 369 lines · 73 tokens per session scan A 34bada09557b

Subscribe to this mod's changes

meta-ads-manager is a skill published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 3,279 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

businesses

Business lifecycle skill (DOMAIN-AGNOSTIC). Creates, lists, inspects, validates, and migrates businesses — autonomous multi-agent organizations — following the Business Protocol v2 (v1 businesses still load unchanged). Works for ANY domain: marketing, healthcare, engineering, legal, real-estate, gaming, foodtech…

gutomec/nirvana-os-engine · 145 tokens

nirvana-os-hermes

Hermes runtime ONLY — the Nirvana-OS bridge for Hermes Agent. Every other runtime loads the first-class nirvana-os skill instead and must ignore this one. Lists and inspects the user's Nirvana-OS businesses (empresas) and squads and routes production briefs to the harness orchestrator via nrv dispatch. Trigger when…

gutomec/nirvana-os-engine · 132 tokens

nirvana-os

List and inspect the user's Nirvana-OS businesses (empresas), squads and mind-clones, and route production briefs to the harness orchestrator. Trigger on 'quais são minhas empresas/squads', 'what businesses/squads do I have', 'liste minhas empresas', 'quais mind-clones eu tenho', 'o que o nirvana pode fazer', 'use o…

gutomec/nirvana-os-engine · 114 tokens

harness

Nirvana-OS orchestrator: routes a brief across the user's own library of businesses, squads and mind-clones, dispatches the best combination, and gates the result before delivery. Use when the user asks for a concrete artifact (book, video, report, design, code, campaign, any deliverable) in a machine where Nirvana-OS…

gutomec/nirvana-os-engine · 154 tokens

squads

Squad lifecycle skill. Use when asked to create, validate, inspect, list, or migrate squads — portable AI agent teams with workflows. Triggers on: create squad, list squads, inspect squad, validate squad, migrate squad, adapters. For EXECUTION of production briefs ('use the squad X', 'orquestre via squad', 'rode via…

gutomec/nirvana-os-engine · 99 tokens

dispatch

Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…

jeremylongshore/tons-of-skills-marketplace · 81 tokens