SkillAgentSearch skills...

audience-intelligence

Audience research module — builds six-dimension buyer personas (demographic, psychographic, behavioral, need-state, information, decision), Jobs-to-Be-Done maps, RFM/behavioral/lifecycle segmentation models, anti-personas with exclusion criteria, B2B buying-committee maps, and lookalike seed specs.

Install / Use

npx skills add indranilbanerjee/digital-marketing-pro --skill audience-intelligence

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Category

Marketing

Supported Platforms

Universal

Our assessment of audience-intelligence

audience-intelligence scores 85/100 on our quality scale, 384th of 610 Marketing skills we index.

Its SKILL.md is 15 KB long, well organised into 14 sections and no code examples: a thorough specification that gives an agent plenty to work with.

It has 832 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
13/20
Description
15/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 26 days ago, so audience-intelligence is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

audience-intelligence compared with similar skills

All 4 of these similar skills score higher than audience-intelligence; compare them before choosing.

SkillScoreStarsUpdatedFormat
audience-intelligence (this skill)by indranilbanerjee8583226d agoSKILL.md
Agent-Reachby Panniantong10090.1k18d agoCLAUDE.md
algorithmic-artby anthropics100177.9k11d agoSKILL.md
pptxby anthropics100177.9k11d agoSKILL.md
designby nextlevelbuilder100130.2k12d agoSKILL.md

Frequently asked questions

How do I install audience-intelligence?
Run npx skills add indranilbanerjee/digital-marketing-pro --skill audience-intelligence. The install tabs above show the steps for each supported agent.
Which AI agents does audience-intelligence work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is audience-intelligence safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is audience-intelligence still maintained?
The repository was last updated 26 days ago, so audience-intelligence is actively maintained.

name: audience-intelligence description: "Audience research module — builds six-dimension buyer personas (demographic, psychographic, behavioral, need-state, information, decision), Jobs-to-Be-Done maps, RFM/behavioral/lifecycle segmentation models, anti-personas with exclusion criteria, B2B buying-committee maps, and lookalike seed specs. Triggers on "/digital-marketing-pro:audience-intelligence", "who are our customers", "build buyer personas", "segment our audience", "run a JTBD analysis". Reads the brand profile, industry benchmarks, and campaign history, and works from CRM/survey/analytics data when supplied — or labels hypothesis personas explicitly when data is thin. For a single quick persona document, /digital-marketing-pro:audience-profile is the lighter sibling."

Audience Intelligence

When to Use This Skill

Activate this module when the user's request involves any of the following:

  • Buyer Persona Creation: Building detailed profiles of ideal customers for marketing and product decisions
  • Audience Research: Understanding who a brand's customers or prospects are at a demographic, psychographic, and behavioral level
  • Segmentation Strategy: Dividing an audience into meaningful groups for targeted marketing
  • Jobs-to-Be-Done (JTBD) Analysis: Identifying the functional, social, and emotional jobs customers hire a product to do
  • Psychographic Profiling: Understanding audience values, attitudes, interests, lifestyles, and motivations
  • Anti-Persona Definition: Defining who is NOT the target customer to prevent wasted spend
  • Audience Sizing & TAM Estimation: Estimating the size of addressable audience segments

Trigger phrases: "buyer persona," "target audience," "who are our customers," "customer profile," "segmentation," "audience segments," "Jobs-to-Be-Done," "JTBD," "psychographic," "ideal customer profile," "ICP," "anti-persona," "lookalike audience," "audience research," "buying committee," "customer avatar"

Brand Context (Auto-Applied)

Before producing any marketing output from this module:

  1. Check session context — The active brand summary was output at session start. Use the brand name, industry, voice settings, channels, goals, compliance, and competitors shown there.
  2. If you need the full profile, read: ~/.claude-marketing/brands/{slug}/profile.json
  3. Apply brand voice — Formality, energy, humor, authority levels must shape all content tone and word choices
  4. Check compliance — Auto-apply rules for brand's target_markets and industry using skills/context-engine/compliance-rules.md
  5. Reference industry benchmarks — Consult skills/context-engine/industry-profiles.md for the brand's industry
  6. Use platform specs — Reference skills/context-engine/platform-specs.md for character limits and format requirements
  7. Check campaign history — Run python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns before planning new work
  8. If no brand exists, say: "No brand profile found. Use /digital-marketing-pro:brand-setup to create one, or I can proceed with general best practices."
  9. Check brand guidelines — If ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json exists, load and enforce: restrictions.md for banned words, restricted claims, and mandatory disclaimers; channel-styles.md for channel-specific tone overrides (may differ from base voice); messaging.md for approved key messages, taglines, and positioning language; voice-and-tone.md for detailed voice rules beyond the 4 numeric scores. If producing content for a specific channel, channel style rules take precedence over base voice settings.

Do not ask the user for information that already exists in their brand profile.

Required Context

Before executing audience intelligence work, gather:

  1. Business Description: What does the company sell, to whom, and what problem does it solve?
  2. Existing Customer Data: Any analytics, CRM data, survey results, or customer interviews available
  3. Product/Service Details: Features, pricing, positioning, and key differentiators
  4. Current Audience Assumptions: Who does the team think their customers are today?
  5. Market Context: Industry, competitive landscape, market maturity
  6. Geographic Scope: Local, regional, national, or global audience
  7. Business Model: B2B, B2C, B2B2C, D2C — this fundamentally shapes persona structure
  8. Sales Process: Self-serve, sales-assisted, enterprise sales — determines decision-maker mapping

If the user has minimal data, build hypothesis-driven personas based on business model, product, and market analysis. Label these clearly as hypotheses to be validated.

Capabilities

  • Multi-Dimensional Persona Building: Personas built across six dimensions:
    • Demographic: Age, gender, location, income, education, job title, company size
    • Psychographic: Values, attitudes, lifestyle, personality traits, motivations
    • Behavioral: Purchase patterns, channel preferences, content consumption, decision-making style
    • Need-State: Current pain points, unmet needs, desired outcomes, urgency level
    • Information: Where they research, who they trust, content format preferences, information journey
    • Decision: Decision criteria, objections, influencers, timeline, risk tolerance
  • JTBD Framework: Mapping functional jobs (what they need done), social jobs (how they want to be perceived), and emotional jobs (how they want to feel) with outcome-driven innovation metrics
  • RFM Segmentation: Recency, Frequency, Monetary value analysis for customer base segmentation
  • Behavioral Segmentation: Grouping by usage patterns, engagement levels, and purchase behavior
  • Value-Based Segmentation: Grouping by customer lifetime value and profitability potential
  • Lifecycle Segmentation: Grouping by customer lifecycle stage (prospect, new, active, at-risk, churned, win-back)
  • Lookalike Audience Guidance: Defining seed audience characteristics for platform-based lookalike targeting
  • Anti-Persona Definition: Explicitly defining who should be excluded from targeting to prevent wasted spend and misaligned messaging
  • Buying Committee Mapping: For B2B, mapping all roles involved in purchase decisions with their individual motivations and objections

Process

Primary Workflow: Persona Development & Segmentation

  1. Discovery & Data Collection

    • Gather all available customer data (analytics, CRM exports, survey results, interview transcripts)
    • Review existing marketing materials, landing pages, and ads for implicit audience assumptions
    • Analyze competitor targeting (who are they going after? what messaging do they use?)
    • If no data exists, conduct a market analysis to build hypothesis personas
    • Document the data quality level: data-rich, data-limited, or hypothesis-only
  2. JTBD Analysis

    • Identify the core job the customer is hiring the product to do
    • Map functional jobs: What task needs to be accomplished?
    • Map social jobs: How does the customer want to be perceived by others?
    • Map emotional jobs: How does the customer want to feel?
    • Identify the "struggling moment" — what triggers the search for a solution?
    • Document competing solutions (including non-consumption and manual workarounds)
    • Define desired outcomes and how customers measure success
  3. Persona Construction

    • Build 3-5 primary personas (avoid persona proliferation)
    • For each persona, complete all six dimensions:
      • Demographic profile: Concrete characteristics with ranges, not single points
      • Psychographic profile: Values, beliefs, lifestyle factors that influence purchase decisions
      • Behavioral profile: How they buy, where they spend time, what content they consume
      • Need-state profile: Specific pain points, urgency drivers, and desired outcomes
      • Information profile: Research behavior, trusted sources, content preferences
      • Decision profile: Criteria, objections, influencers, and timeline
    • Give each persona a memorable name and narrative (but avoid stereotyping)
    • Assign estimated segment size and revenue potential
    • Prioritize personas by business impact
  4. Anti-Persona Development

    • Define 1-3 anti-personas: people who may seem like targets but are poor fits
    • Common anti-persona types: price-sensitive bargain hunters (for premium brands), feature-seekers who will never buy (tire kickers), wrong company size or industry
    • Document specific signals that identify anti-personas in your data
    • Create exclusion criteria for ad targeting and lead qualification
  5. Segmentation Strategy

    • Select the segmentation approach based on available data and business needs:
      • RFM: When transaction data is available — score by recency, frequency, monetary value
      • Behavioral: When usage/engagement data exists — group by behavior patterns
      • Value-based: When LTV data is available — prioritize high-value segments
      • Lifecycle: When customer journey stage data exists — customize by stage
      • Needs-based: When qualitative research is available — group by pain point
    • Define segment boundaries and naming conventions
    • Map segments to personas (segments are data-driven groups; personas are the human stories within them)
    • Assign channel and messaging strategies per segment
  6. Activation Planning

    • For each persona/segment, define:
      • Priority channels for reaching them
      • Messaging themes and value propositions that resonate
      • Content types and formats they prefer
      • Lookalike audience seed criteria for paid platforms
      • Lead scoring rules based on persona fit
    • Create a persona-to-campaign mapping guide
    • Build a validation plan to test persona hypotheses with real campaign data

Reference Files

  • persona-builder.md — Six-dimension persona template, persona interview guide, data-to-persona methodology, and persona validation framework
  • jtbd-framework.md — Jobs-to-Be-Done analysis methodology, job mapping canvas, outcome-driven innovation scoring, and competing solutions analysis
  • segmentation.md — RFM scoring model, behavioral segmentation framework, lifecycle segmentation definitions, and segment-to-action mapping
  • psychographic-profiling.md — Values and attitudes framework, lifestyle analysis, motivation mapping, and psychographic data collection methods
  • customer-research-methods.md — Quantitative and qualitative research methods: survey design, interview techniques, voice-of-customer programs, and synthesis methods with budget guidance

Output Formats

| Deliverable | Format | Description | |---|---|---| | Buyer Persona Document | Document (per persona) | Complete six-dimension persona with narrative, data points, and activation guidance | | Persona Summary Card | One-page visual | Quick-reference persona card for team alignment | | JTBD Analysis | Document | Job map, struggling moments, desired outcomes, and competing solutions | | Segmentation Model | Spreadsheet + document | Segment definitions, criteria, sizes, and strategy per segment | | Anti-Persona Profiles | Document | Who to exclude, why, and identification signals | | Buying Committee Map | Visual diagram + document | B2B decision-maker map with roles, motivations, and influence paths | | Audience Activation Guide | Document | Channel, messaging, and content recommendations per persona/segment | | Lookalike Audience Spec | Document | Seed audience criteria and platform-specific setup instructions |

Edge Cases

B2B Buying Committees (Multiple Personas per Deal)

  • Situation: Enterprise B2B purchases involve 6-10 decision-makers with different roles, motivations, and objections
  • Approach: Build individual personas for

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars832
CategoryMarketing
Updated26d ago
Forks136

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions