AI Agent Skills

从《医宗金鉴》卷三十五「编辑运气要诀」（清·吴谦等编纂）蒸馏出的运气推算全框架——太极阴阳、五行生克、五运六气、脏腑经络映射、天符岁会、南北政、运气为病。用于"按年干支回查运气格局与病机框架"与"运气推算研读"，非临床处方指南。

从《运气证治歌诀》（清·王旭高/王泰林，辑自陈无择《三因方》司天运气诸方）蒸馏出的运气证治框架——五运十方、六气六方、运气推算歌诀、六淫治例。用于"按年干支回查运气方框架"与"运气治法研读"，非临床处方指南。

刘完素（约1110—1200，金代）的思维框架与表达方式。河间学派创始人，寒凉派代表。 核心心智模型：六气皆从火化、亢则害承乃制（兼化是虚象不可误治）、审机求属。 决策启发式：见火热证先从火化推、兼化假象不误治本气、吐酸为热非寒、不可峻用辛温大热。 用途：作为运气学思维顾问，用刘完素的视角分析病机、审视治法、提供反馈。 触发词：「刘完素…

张介宾（1563—1640，明代，字景岳）的思维框架与表达方式。温补派代表。 核心心智模型：阳气为本（命门真火）、五行互藏、生中有克克中有用、亢则害承乃制（造化不可无制）。 决策启发式：治病温养阳气为先、五行生克辩证看（生非纯生克非纯害）、客主但有胜而无复、天符岁会轻重分级。 用途：作为运气学思维顾问，用张介宾的视角分析病机、审视治法、…

将用户提供的需求资料或参考项目链接转化为面向产品、设计、研发和测试的完整产品设计交付物：产品需求文档（PRD）、设计交付说明、数据库表结构 SQL、研发实现说明和测试验收用例；当用户提供网站、Web 应用、后台系统、移动端 H5 或原型的参考链接时，使用 chrome-devtools-mcp 深入浏览和交互分析，并输出参考项目分析.m…

Search and extract Cypress information from official documentation (docs.cypress.io, cypress.io); prefer LLM markdown under /llm/* and refuse unverified API or behavior…

Analyze code changes and update KNOWLEDGE_BASE.md with architectural and feature changes.

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-fac…

Use this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, relevance, safety) rather than just watching traces. Trigger o…

Use this to make an LLM app resilient to provider failures, rate limits, timeouts, and outages. Trigger on "handle LLM API errors", "add retries/fallbacks", "the app bre…

Use this to add safety and security guardrails to an LLM/agent app - blocking prompt injection, PII leakage, jailbreaks, toxic output, off-topic responses, or invalid st…

Use this to set up human review and annotation of LLM traces, so people (often domain experts) can label outputs, do error analysis, and build a trustworthy golden datas…

Use this to build a good evaluation dataset for an LLM app, the part everyone underestimates. Trigger on "make an eval set", "what should I test my LLM on", "I don't hav…

Use this to capture user feedback on LLM outputs (thumbs up/down, edits, corrections, implicit signals) and feed it back into observability and evals. Trigger on "add th…

Use this to pick or switch the LLM behind a feature, based on evidence instead of hype or the newest release. Trigger on "which model should I use", "is GPT/Claude/Gemin…

Use this to detect when an LLM is making things up, so you can flag or block confident-but-wrong answers before users see them. Trigger on "detect hallucinations", "is t…