Use when you need to deliver sensitive political counsel to a new or distrustful leader. Builds trust gradually through demonstrated competence, acknowledged risk, and escalating from safe topics to dangerous internal politics.

Use when extracting a VIP from hostile territory under surveillance. Covers disguise preparation, cover stories, timing extraction with legitimate travel, and the facilitator's willingness to accept consequences.

Use when entrusted with dangerous levels of military or political power by a suspicious ruler. Based on Wang Jian's (王翦) strategy — repeatedly requesting personal land, houses, and gardens to signal you seek wealth, not power, thereby reducing the ruler's fear of betrayal.

Use when negotiating for survival under threat of execution or hostage situations. Restructures hostage transactions by demonstrating a living captive's leverage value, sequencing agreements to protect all parties, and buying time for allied intervention.

Use when responding to internal rebellion, coup attempts, or revolts against legitimate authority. Covers initial assessment of rebel forces and loyalist strength, response options (negotiation, military action, external intervention), and post-rebellion protocols for punishment, pardon, and institutional reform.

Use when organizing a multi-party coalition against a dominant threat. Covers envoy dispatch, resource gifting, securing key partners first, establishing coordination structures, and cementing alliances through marriage or exchange in Warring States diplomatic tradition.

Use when evaluating officials for noble titles or ranking meritorious service. Applies the five-tier classification (勋劳功伐阅) to determine title rank, land grants, and hereditary privileges based on contribution type.

Use when cross-referencing conflicting historical accounts or assessing source reliability. Applies Sima Qian's doubt-transmission principle (疑则传疑) to compare 谍记, 历谱谍, and other documentary evidence.

Use when reforming harsh punishments or transitioning a legal system to humane alternatives. Guides abolishing corporal punishment (废除肉刑) using Tiying's (缇萦) petition model under Emperor Wen.

Use when navigating a hostile banquet, diplomatic ambush, or dangerous political gathering. Guides escape from the Hongmen Banquet (鸿门宴) scenario using alliances, deference, and covert withdrawal.

Use when creating a new imperial title or establishing governance terminology for a unified empire. Guides council deliberation, historical precedent review, title composition (皇帝), imperial terminology (制/诏/朕), and succession numbering from 始皇帝 onward.

Use when recovering from a major military defeat or rebuilding forces after a loss. Based on Duke Mu's response to the Xiao defeat, covers personal accountability, commander restoration, public acknowledgment, and rebuilding strategy.

Use when neutralizing a capable enemy advisor or creating distrust between a rival ruler and their counselor. Deploys distraction tactics, manufactured suspicion, and defection incentives. Based on Qin's handling of You Yu and the Rong king.

Use when selecting or vetting a successor for leadership. Applies a multi-phase evaluation combining character tests, progressive responsibility assignment, regency trials, and public acceptance before formalizing succession.

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior. Do not use for test-first/TDD feature work, test-report packaging, review-feedback handling, or final completion evidence.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.

Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.

Design experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or estimating effects on existing data, use performing-causal-analysis instead.