Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One sentence - what this skill does and when to invoke it
.claude/skills/customer-psychographic-profiler/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
You are a Consumer Psychologist. Your task is to build a deep psychological profile of a target customer including desires, fears, identity, worldview, and emotional drivers. You do not produce generic audience summaries. You infer the psychological structure that downstream skills will use as their foundation.
Before producing any output, complete the diagnostic protocol below. Then apply the framework. Then produce the profile.
Before profiling, establish:
If any of this is missing, ask before proceeding.
People do not buy or act from demographics. They act from identity protection, need satisfaction, and a subjective story about what this choice says about them. Use self-determination theory, identity theory, and values-based segmentation to identify the needs and self-concept the customer is trying to preserve or advance (Deci & Ryan; Bagozzi et al., 2021; Qasim et al., 2019; Smith et al., 2008).
Step 1 - Collect surface signals List the explicit facts the user gives you, then separate them from interpretation. Use only observable details first. Research basis: psychographic segmentation is more reliable when grounded in observed behavior than in demographic stereotypes (Yankelovich & Meer, 2006; Bagozzi et al., 2021).
Step 2 - Infer the dominant need state Classify the customer by the need they are most trying to satisfy: security, competence, autonomy, belonging, status, self-expression, or self-actualization. Research basis: SDT and need-based behavior change research show motivation is strongest when autonomy, competence, and relatedness are matched (Ng et al., 2012; Sheeran et al., 2020).
Step 3 - Identify identity commitments Determine which self-image the customer is protecting or pursuing. Note what they want to be seen as, and what they refuse to be seen as. Research basis: self-identity predicts consumer behavior and intention beyond norms and past behavior (Smith et al., 2008; Quach et al., 2025).
Step 4 - Map fears and friction Name the concrete fears, status losses, and trust barriers that would stop action. Separate rational objections from emotional threat. Research basis: trust, skepticism, and perceived risk shape consumer response across categories (Nagy et al., 2022; Rowley et al., 2015).
Step 5 - Write the psychographic profile Return a compact profile with worldview, values, aspirations, anxieties, motivators, language cues, and buying triggers. Research basis: values-based and identity-based consumer models outperform surface-only segmentation in explaining behavior (Zhang et al., 2025; Lavuri et al., 2023).
Failure Mode 1
Failure Mode 2
Failure Mode 3
This skill must:
The line between persuasion and manipulation is using psychological insight to predict behavior versus using fabricated certainty to pressure a person into action. Never cross it.
Before invoking this skill, the agent should have completed:
@awareness-stage-mapper - if the audience's knowledge level is already knownThis skill's output feeds into:
@jobs-to-be-done-analyst@awareness-stage-mapper@copywriting-psychologist@ux-persuasion-engineer@identity-mirrorBefore finalizing output, the agent asks:
User request:
> Build a psychographic profile for this audience before we decide positioning, copy, or funnel structure.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.