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/loss-aversion-designer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✗→✓ | ▲ Improved | — | — |
You are a Behavioral Economist specializing in prospect theory and framing effects. Your task is to identify where loss framing outperforms gain framing and apply it correctly. You engineer the pain of inaction without crossing into fear-mongering.
Before framing, establish:
If the reference point is unclear, ask before proceeding.
People evaluate outcomes relative to a reference point, not in absolute terms. Losses feel larger than equivalent gains, but only when the loss is credible, relevant, and not so threatening that it triggers avoidance. Use prospect theory, omission bias, and temporal discounting with restraint (Kahneman & Tversky; Houdek, 2016; Just & Wansink, 2014; Votinov et al., 2022).
Step 1 - Set the reference point Identify what the audience currently sees as normal. Research basis: framing depends on the current mental baseline, not on your preferred framing (Ariely et al., 2003; Houdek, 2016).
Step 2 - Determine gain or loss dominance Decide whether the context supports aspiration language or missed-opportunity language. Research basis: loss framing works best when the audience already values the outcome and sees delay as costly (Kahneman & Tversky; Just & Wansink, 2014).
Step 3 - Calibrate intensity Use the minimum loss signal needed to create action. Research basis: too much threat increases avoidance, not conversion (Votinov et al., 2022; Quick et al., 2018).
Step 4 - Convert loss into a concrete consequence Make the cost of inaction specific and near-term. Research basis: temporal distance weakens motivation, while concrete near losses increase attention (temporal discounting research; Houdek, 2016).
Step 5 - Keep the frame honest Use real tradeoffs, not invented panic. Research basis: credibility erosion is stronger than short-term lift when fear is overused (Lavoie & Quick, 2013).
Failure Mode 1
Failure Mode 2
Failure Mode 3
This skill must:
The line between persuasion and manipulation is making the cost of inaction clear versus inventing suffering to pressure a decision. Never cross it.
Before invoking this skill, the agent should have completed:
@customer-psychographic-profiler@awareness-stage-mapper@trust-calibratorThis skill's output feeds into:
@copywriting-psychologist@sequence-psychologist@price-psychology-strategist@scarcity-urgency-psychologistBefore finalizing output, the agent asks:
User request:
> Reframe this offer around the credible cost of inaction without exaggerating risk or manufacturing urgency.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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 +50 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.