General AI Skills

Generate correct MATLAB code using the Symbolic Math Toolbox. Use when the user asks for symbolic computations, analytical solutions, symbolic differentiation/integration, equation solving, or…

美客多变体与尺码表验收。用于颜色、尺码、容量等变体映射及尺码表验证；不为聚合评价而合并不同产品。

用于结合 MPstats 为 OZON 广告选择有需求、供给和贡献基础的商品。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于利用 MPstats 为 OZON 现有店铺筛选相邻品类与扩展规格。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Initialize a new Ruflo project with MCP tools, hooks, and agent configuration. Use when setting up Ruflo in a fresh repo, or when the user says "init ruflo", "set up ruflo", or asks how to bootstrap…

用于借 MPstats 市场走势辅助判断 OZON 推广是否带来新增贡献。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于用 MPstats 建立 OZON 俄语关键词库和商品信息对应关系。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于判断 OZON 细分是否给新商品机会并制定首批试销验证。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于结合 MPstats 竞争环境设计 OZON CPC 测试和亏损诊断。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于结合 MPstats 评估 OZON 按订单付费与 CPC 组合推广是否有净贡献。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Use this skill to reason like Martin Heidegger, 20th-century German philosopher and author of Being and Time. Reach for this skill whenever you encounter discussions about the existential impact of…

用于结合 MPstats 市场趋势与内部真实库存制定 OZON 补货或清仓方案。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于结合 MPstats 评论与内部订单状态诊断 OZON 退货、取消和产品问题。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于结合 MPstats 评论、评分和需求，形成 OZON 可验证产品改进方向。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Keep a durable decision log: what, why, who, and when.

用于用 MPstats 判断 OZON 关键词排名消失、下滑和搜索流量异常。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Prüfung der Anfechtung und Nichtigkeit von GmbH-Gesellschafterbeschlüssen – Beschlussfassung § 47 GmbHG, Stimmverbote § 47 Abs. 4 GmbHG, Einberufung und Ankündigung § 51 GmbHG, Beschlussmängelrecht in…

Prüfung der zivilrechtlichen Geschäftsführerhaftung gegenüber der GmbH (§ 43 GmbHG), der Außenhaftung in der Krise (§ 64 GmbHG / § 15b InsO) und der Insolvenzantragspflicht (§ 15a InsO). Use when ein…

Prüfung der GmbH-Kapitalerhaltung – Verbot der Auszahlung des zur Erhaltung des Stammkapitals erforderlichen Vermögens § 30 GmbHG, Rückgewähranspruch § 31 GmbHG, Unterbilanz und bilanzielle…

Build a RACI matrix to clarify roles on a program.

用于结合 MPstats 价格带与自家成本测算 OZON 单品贡献、保本价和广告上限。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

用于从 MPstats 可比商品和评论问题生成 OZON 主图、图文与富内容测试简报。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Triage and resolve blockers quickly and visibly.

A bottom sheet slides up over a dimmed backdrop, then dismisses. An App-UI micro-interaction (mobile component feedback). Honors prefers-reduced-motion. Keep it short and snappy; only on controls that…

用于用 MPstats 仓库与需求观察辅助 OZON 配仓方案。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

A button that springs down on press and pops back — tactile tap feedback. An App-UI micro-interaction (mobile component feedback). Honors prefers-reduced-motion. Keep it short and snappy; only on…

Applies the existentialist and feminist philosophy of Simone de Beauvoir, French philosopher and author of The Second Sex. Reach for this skill whenever the user is grappling with existential…

用于以 MPstats 市场基线和内部经营数据解释 OZON 周度变化。以 MPstats 的 OZON 数据或可核验导出为必需输入，缺数据先补数；不自动发布、采购或修改广告。

Shopify 获客广告与实验。用于综合广告诊断与预算、素材、归因的联合评审；已有具体单项问题时优先选择对应专题入口。

A Material-style ripple spreads from the point of contact. An App-UI micro-interaction (mobile component feedback). Honors prefers-reduced-motion. Keep it short and snappy; only on controls that…

Build and maintain a program risk register.

A bottom tab bar whose active pill slides between tabs. An App-UI micro-interaction (mobile component feedback). Honors prefers-reduced-motion. Keep it short and snappy; only on controls that actually…

A toast slides up from the bottom, holds, then fades away. An App-UI micro-interaction (mobile component feedback). Honors prefers-reduced-motion. Keep it short and snappy; only on controls that…

Prioritise competing program requests with a transparent, repeatable model.

Define escalation paths and the triggers that activate them.

Map stakeholders by influence, interest, and current stance.

Add a global variable to a Copilot Studio agent. Use when the user needs a variable that persists across topics in the same conversation and can optionally be visible to the AI orchestrator.

Clone a Copilot Studio agent from the cloud. Guides through environment selection, agent selection, and downloads agent YAML files.

Edit an existing action (TaskDialog) in a Copilot Studio agent. Supports connector actions and MCP server actions. Modify inputs, outputs, descriptions, connection mode, and other properties.

Modify topic triggers — trigger phrases and model description. Use when the user asks to add, remove, or change trigger phrases, or edit a topic's model description.

List all available kind discriminator values from the Copilot Studio YAML schema. Use when the user asks what kinds/types are available.

List all topics in the Copilot Studio agent with their trigger types, phrases, and action counts. Use when the user wants to see what topics exist.

Look up Copilot Studio YAML schema definitions. Use when the user asks about schema structure, element properties, or how to use a specific YAML kind.

Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches…

Validate Copilot Studio agent YAML files using the LSP binary's full diagnostics (YAML structure, Power Fx, schema, cross-file references). Use when the user asks to check, validate, or verify YAML…

The AGENT-facing description. This is what the model reads to decide WHEN to invoke the skill, so describe the trigger precisely (e.g. "Use this skill whenever the user asks to … BEFORE calling …").…

Surfaces contradictory evidence - studies moving the same metric in opposite directions - rather than a smoothed answer. Use on "do the studies agree", "any conflicting evidence", after trend-compare.

Refine the user's existing plan, decision, or draft through relentless refinement. Use when the user wants to sharpen or stress-test their thinking.

Queues validation exceptions with reason codes and a recommended correction per exception, deterministically. Use on "route the exceptions", "what needs fixing before entry", after order-validate.

Normalises extracted order lines - whitespace, casing, UOM tokens, qty formats - without changing meaning, preparing them for validation. Use after order-ingest.

Description of what the skill does and when to use it