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 zubair-trabzada/ai-ads-claude --skill ads-audiencegit clone --depth 1 https://github.com/zubair-trabzada/ai-ads-claudeWrote 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/zubair-trabzada/ai-ads-claude/ads-audience)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-ads-claude/ads-audience"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-audience/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/zubair-trabzada/ai-ads-claude/ads-audience"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-ads-claude/ads-audience.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 | $0.00039 | $0.03607 |
| Opus 5 | $0.00019 | $0.01803 |
| Sonnet 5 | $0.00008 | $0.00721 |
| Haiku 4.5 | $0.00004 | $0.00361 |
Grade A, and why
Audience Persona Builder 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 13d 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audience Persona Builder
Skill Purpose
Build 5-7 hyper-detailed audience personas from a business URL. Each persona goes far beyond basic demographics — it maps psychographic profiles, buying triggers, objections, content consumption habits, platform presence, and ready-to-use targeting parameters for Meta, Google, LinkedIn, TikTok, and Pinterest. Includes persona relevance scoring (1-5) and a negative audience section defining who NOT to target. Produces a single, copy-paste-ready deliverable that an ad buyer can immediately use to build campaigns.
When to Use
- User runs
/ads audience <url> - User asks to build audience personas, customer profiles, or targeting research
- Called as a subagent from
/ads strategy(the main orchestrator) - User wants to know "who should I target?" for a business
- User needs platform-specific targeting parameters for campaign setup
Input Requirements
- Required: A business URL to analyze
- Optional: Industry context, existing customer data, geographic focus, budget range
How to Execute
Step 1: Business Intelligence Gathering
Fetch the business URL using WebFetch and extract:
| Data Point | Where to Find |
|---|---|
| Business name | Page title, logo, about page |
| Industry/category | Services offered, product types |
| Value proposition | Hero section, tagline, about page |
| Price positioning | Pricing page, product prices, "starting at" language |
| Geographic focus | Service areas, locations, shipping info |
| Current customers | Testimonials, case studies, reviews |
| Product/service types | Product pages, service descriptions |
| Brand tone | Copy style, imagery, color palette |
| Trust signals | Certifications, awards, years in business, client logos |
| Content topics | Blog posts, resources, FAQ sections |
Run supplementary searches:
WebSearch: "[Business Name]" reviews
WebSearch: "[Business Name]" customers testimonials
WebSearch: "[Industry]" target audience demographics
WebSearch: "[Industry]" buyer persona research 2025
WebSearch: "[Competitor]" "who buys" OR "target market" OR "customer profile"
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.
- 13d ago First seen · 371 lines · 39 tokens per session scan A 8da328b137fc
Audience Persona Builder is a skill published in the GitHub repository zubair-trabzada/ai-ads-claude (246 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 3,607 once invoked, about $0.0002 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…