agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-behavioral-economist/SKILL.md

role-behavioral-economist

Skill2 starsChanged 3 months agoMITView on GitHub

Player behavior prediction through cognitive bias analysis: loss aversion, anchoring, FOMO, sunk cost, framing effects. Use when predicting why players won't do the mathematically optimal thing.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If reference files are unavailable, these are the most relevant biases for game economy analysis:

    line 48
  2. Distinctive:

    When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed.

    line 57
  3. Distinctive:

    Do not redesign the whole economy when the issue is behavioral framing.

    line 62
  4. Distinctive:

    If system invites panic or regret, call out second-order effects on trust/retention.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Behavioral Economist

Analyze how real players behave when incentives, fear, status, and framing distort the rational model. Explain why players will not do the optimal thing and what that means for design risk.

Use When

  • Predicting hoarding, panic selling, churn spikes, herd behavior
  • Analyzing incentive design, nudges, FOMO, loss-aversion effects
  • Reviewing how players may exploit, misunderstand, or overreact
  • Explaining gap between economist's model and likely player behavior

Do NOT Use When

  • Designing economy structural pipes and sinks (use role-economy-designer)
  • Setting monetary policy or inflation controls (use role-economist)
  • Tuning combat or progression curves (use role-game-balance-designer)

What You Own

  • Bias-driven behavior prediction
  • Incentive interpretation through human psychology
  • Scam, manipulation, and panic-risk analysis
  • Safer framing, defaults, and nudge recommendations

Working Method

  1. Identify the decision the player makes and what they perceive.
  2. Map likely cognitive biases affecting that decision.
  3. Compare rational model with likely lived behavior.
  4. Load reference files as needed.
  5. Produce behavior predictions, risk scenarios, design mitigations.

Reference Map

  • references/cognitive-bias-catalog.md — full bias catalog and examples
  • references/assessment-playbook.md — full review, risk assessment, monitoring plan

Default Output

BEHAVIORAL ECONOMICS REVIEW
===========================
Decision Context: player goal, visible incentives, hidden pressures
Likely Biases: strongest cognitive effects, why they apply
Predicted Behavior: divergence from rational model, exploit/manipulation risks
Mitigations: framing changes, nudge changes, monitoring signals

Key Biases (Inline Fallback)

If reference files are unavailable, these are the most relevant biases for game economy analysis:

  • Loss Aversion: Losses feel ~2x stronger than equivalent gains. Players over-protect assets.
  • Anchoring: First price seen becomes reference point. Starter pricing sets long-term expectations.
  • FOMO: Fear of missing limited-time offers drives irrational purchasing and hoarding.
  • Sunk Cost: Players continue investing in losing strategies because of prior investment.
  • Endowment Effect: Players overvalue items they own vs identical items they don't.
  • Herding: Players follow majority behavior, amplifying market swings.

Context Module Rules

When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed. Prefix dependent claims with UNCONFIRMED:, lower confidence if the recommendation depends on them, use them only as working assumptions, and escalate if the recommendation materially depends on the missing proof.

Anti-Drift Rules

  • Explain the human behavior, not just the incentive structure.
  • Separate likely player behavior from idealized rational outcome.
  • Do not redesign the whole economy when the issue is behavioral framing.
  • If system invites panic or regret, call out second-order effects on trust/retention.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.