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 Davidhevesi/marketing-skills-repo --skill audience-researchgit clone --depth 1 https://github.com/Davidhevesi/marketing-skills-repoWrote 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/davidhevesi/marketing-skills-repo/audience-research)<a href="https://agentmods.dev/skills/davidhevesi/marketing-skills-repo/audience-research"><img src="https://agentmods.dev/badge/skills/davidhevesi/marketing-skills-repo/audience-research/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/davidhevesi/marketing-skills-repo/audience-research"><img src="https://agentmods.dev/badge/skills/davidhevesi/marketing-skills-repo/audience-research.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 | $0.00033 | $0.05691 |
| Opus 5 | $0.00016 | $0.02846 |
| Sonnet 5 | $0.00007 | $0.01138 |
| Haiku 4.5 | $0.00003 | $0.00569 |
Grade A, and why
audience-research 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 12d 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 — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audience Research
You help users understand their audience at a level that makes every piece of marketing sharper. This skill covers review mining, competitor audience analysis, survey design, customer interview frameworks, and language pattern extraction. The output isn't a demographic profile — it's the specific language, fears, desires, and decision triggers that make copy convert and content resonate.
Works for any business that wants to stop guessing what their audience cares about and start knowing.
Before You Start
Check for Context
Look for a Business Context document in the project knowledge files.
If it exists: Read Sections 3 (Target Audience), 4 (The Problem You Solve), and 7 (Customer Language) before doing anything. These sections may already capture audience knowledge — the goal is to go deeper, fill gaps, or update what's there with new research.
If it doesn't exist: Say — "Audience research is most useful when it's connected to a clear picture of your business and what you're trying to learn. Do you have a Business Context document in this project? If not, tell me: what does your business do, who do you think your audience is right now, and what specifically do you want to understand better about them?"
Workflow
Step 1: Identify the Research Goal
Audience research without a goal produces interesting data that never gets used. Start with what decision the research needs to inform.
What are we trying to learn?
- What language does my audience use to describe their problem? (for copywriting)
- Why do people buy — and why do they hesitate? (for conversion optimization)
- What does my audience actually want vs. what I think they want? (for offer development)
- Who is my real audience vs. who I think it is? (for targeting and positioning)
- What content topics does my audience care about? (for content strategy)
- How does my audience make buying decisions? (for sales and marketing process)
The research question: Reduce the goal to one specific question. Everything else is secondary.
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.
- 12d ago First seen · 654 lines · 33 tokens per session scan A e3c78078eb11
audience-research is a skill published in the GitHub repository Davidhevesi/marketing-skills-repo (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 5,691 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 2026-08-31.
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…