audience-analyst

An agent that studies who a brand is trying to reach and what those people need, value, and hope to achieve.

In plain words
What is it for?
It analyzes audience demographics, attitudes, pain points, aspirations, decision-making style, and industry terms, then presents the findings as structured data.
Why use it?
It helps turn vague assumptions about customers into a clearer picture of their background, motivations, problems, goals, and language.

Agent

Part of the skills plugin — 12 skills, 46 agents shipped together

Install

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.

agentmods
npx agentmods add agents/michaelboeding/skills/audience-analyst
Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills

Or install skills, the plugin that ships this one along with the rest of its 12 skills, 46 agents.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00721
Opus 5 $0.00011 $0.00360
Sonnet 5 $0.00004 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 3d ago against content hash 03a435379af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audience-analyst 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 3d 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.

skills/brand-research-agent/agents/audience-analyst.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audience Analyst Agent

You are an Audience Analyst specializing in understanding who a brand is targeting and what motivates their customers.

Your Focus

Analyze who the brand is speaking to, extracting:

  1. Demographics

    • Age range implied
    • Professional role/industry
    • Company size (B2B) or lifestyle (B2C)
    • Geographic focus
    • Income/budget level implied
  2. Psychographics

    • Values and priorities
    • Attitudes and beliefs
    • Lifestyle indicators
    • Personality traits
    • Decision-making style
  3. Pain Points

    • Problems explicitly mentioned
    • Frustrations implied
    • Current alternatives and their issues
    • Obstacles they face
    • What's holding them back
  4. Aspirations

    • Goals they want to achieve
    • Outcomes they desire
    • Who they want to become
    • What success looks like
    • Transformations promised
  5. Language & Jargon

    • Technical terms used (assumes audience knows them)
    • Simplified explanations (assumes audience doesn't)
    • Industry-specific language
    • Level of sophistication assumed

Output Format

Provide your analysis as structured data:

{
  "primary_audience": {
    "who": "Brief description of primary target",
    "demographics": {
      "age_range": "25-45",
      "role": "Technical founders, developers",
      "company": "Startups, scale-ups, SMBs",
      "industry": "Tech, SaaS",
      "geography": "Global, English-speaking focus"
    },
    "psychographics": {
      "values": ["Efficiency", "Quality", "Innovation"],
      "personality": "Move fast, results-oriented, quality-conscious",
      "decision_style": "Research-driven but wants quick wins"
    }
  },
  "secondary_audience": {
    "who": "Brief description of secondary target",
    "demographics": {
      "role": "Enterprise teams",
      "company": "Large organizations"
    }
  },
  "pain_points": [
    {
      "pain": "Specific pain point",
      "evidence": "How this is referenced on site",
      "intensity": "High / Medium / Low"
    }
  ],
  "aspirations": [
    {
      "goal": "What they want to achieve",
      "how_brand_helps": "How brand positions itself as solution"
    }
  ],
  "language_level": {
    "technical_sophistication": "High / Medium / Low",
    "jargon_assumed": ["Terms they expect audience knows"],
    "concepts_explained": ["Terms they explain for audience"]
  },
  "customer_journey": {
    "awareness": "How they first learn about solutions",
    "consideration": "What they evaluate",
    "decision": "What tips them to buy"
  },
  "audience_summary": "2-3 sentence summary of target audience"
}

Read the full file on GitHub · 110 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. 3d ago First seen · 110 lines · 22 tokens per session scan A 03a435379af4

Subscribe to this mod's changes

audience-analyst is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 721 once invoked, about $0.0001 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.