AI Agent Skills

Load before writing PolicyEngine-UK code — UK household calculations, income tax (incl. Scottish and Welsh variations), National Insurance, Universal Credit and other be…

Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default rou…

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, wx.cloud apps). Covers generateText and streamText with callbacks (onText, onEvent, onFinish); str…

When asked to grill, stress-test, or pressure-test an idea, or before a decision map or spec rests on an untested conversation, interview the decision maker in small rou…

For a build brief, implementing a spec or tracked item, or mid-build discoveries tempting scope expansion, build thin verified slices with test-first checks at named bou…

执行多维度代码审查。用于合并任何变更之前；用于审查自己、其他 agent 或人类编写的代码；用于在代码进入主分支前从多个维度评估代码质量。

为清晰度简化代码。用于在不改变行为的前提下重构代码以提升清晰度；用于代码能运行但比应有状态更难阅读、维护或扩展时；用于审查已累积不必要复杂度的代码时。

挖掘用户真正想要的东西，而不是他们觉得自己“应该”要的东西。实现方式是一次一问的访谈，直到对底层意图达到约 95% 的置信度。当一个请求信息不全时（"build me X" 却没说 "for whom" 或 "why now"）、当用户明确发出邀请（"interview me"、"grill me"、"are we sure?"、"st…

Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer set and return a per-case behavioural-equivalence…

Write screenplays and scripts for film, television, YouTube, video essays, documentaries, sketches, and short-form social video. Use for scripted scenes, screenplay form…

Systematic workflow for identifying coverage gaps and writing missing tests. Use when coverage is below target or the user asks to improve coverage.

Optimizes multi-step conversion flows including signup, onboarding, upgrade, and checkout. Maps each step, identifies friction and drop-off risks, then recommends specif…

Deep research producing a fully written, source-validated literature review on an agricultural question, as a senior agricultural scientist of the relevant discipline: s…

General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources…

缺陷修复方法论唯一入口：口喷 bug 定位直修；implement-test-review 循环内的反馈修复也走本 skill（循环内分支，原 impl worker 执行）。触发：修 bug / 有个 bug / 报错了 / 行为不对 / fix / /eo-fix。 NOT FOR: 明确的业务变更（走 /eo-change）。

按 change.md 的 TODO 分批落地代码，批末自验对应 AC。触发：实现 / 写代码 / implement / /eo-implement。 NOT FOR: bug 与反馈修复（口喷 bug 与 test/review/acceptance 循环内反馈一律走 /eo-fix）；变更起草（走 /eo-change）。