yao-gametheory-skill

Yao Game Theory Skill

Use This Skill For

• convert CEO-facing strategic interactions into game theory reports
• choose and combine game theory frameworks from references/framework-catalog.md
• answer "对手可能怎么反应" and "我们的承诺动作是否可信"
• use historical behavior and reference-class experience to adjust rationality and commitment probabilities
• update prior reports when a player makes a new move
• export synchronized Markdown, HTML, Word/DOCX, and PDF reports

Do Not Route Here

• game theory homework, theorem proofs, or textbook explanation with no strategic report
• generic strategy brainstorming where no player can react strategically
• final legal, financial, investment, antitrust, or regulatory advice
• manipulative, deceptive, coercive, or unlawful competitive tactics

Default Workflow

1. Convert the request with references/intake-contract.md; use references/dynamic-iteration-loop.md for incomplete input or later player moves.
2. Route through references/framework-catalog.md: select one primary framework and 2-4 secondary lenses.
3. Instantiate the combination with references/game-model-playbook.md: players, strategies, payoffs, timing, beliefs, and equilibrium logic.
4. Calibrate player rationality with real historical behavior and experience references before trusting payoff-matrix inference.
5. Test commitments and signals with references/commitment-signal-checklist.md.
6. Run references/strategic-hygiene-checklist.md, references/strategy-readiness-loop.md, and references/sensitivity-and-safety.md.
7. Build framework selection, opponent reactions, payoff matrix, historical behavior calibration, readiness, sensitivity, next information, and update triggers.
8. Run scripts/generate_report_bundle.py; finalize with references/strategic-report-contract.md and references/report-export-pipeline.md.

Output Contract

• Produce an executive strategy report, not a theory lecture.
• Put the recommendation, opponent reaction forecast, and credible-commitment call before technical sections.
• Mark payoffs, probabilities, and assumptions as observed, estimated, or assumed.
• Include frameworks, payoff matrix, reactions, equilibria, historical rationality calibration, commitment/signal checks, readiness, sensitivity, next information, update log, triggers, and caveats.
• Default language is Simplified Chinese; generate PDF automatically when possible, otherwise keep HTML print-ready.

Reference Map

• references/intake-contract.md: request-to-game-brief conversion
• references/framework-catalog.md: game theory framework library and AI application router
• references/game-model-playbook.md: players, strategies, payoffs, timing, equilibrium reasoning
• references/commitment-signal-checklist.md: credibility and signal-quality checks
• references/dynamic-iteration-loop.md: multi-turn and opponent-update loop
• references/strategy-readiness-loop.md: readiness score and remaining-gap loop
• references/strategic-hygiene-checklist.md: strategic assumption hygiene checks
• references/sensitivity-and-safety.md: stress tests and safety boundaries
• references/strategic-report-contract.md: required report sections and schema alignment
• references/report-export-pipeline.md: artifact generation and print/PDF rules
• scripts/generate_report_bundle.py: report builder and exporter
• templates/report.schema.json: structured report schema
• evals/trigger_cases.json: route positives, negatives, and near-neighbor cases