feishu-aily-skills

文档创作年度报告：主要借助 `aily-doc` 获取用户年度文档信息（数量、点赞、评论、PV、UV 等），并基于这些指标与代表性文档产出年度总结型飞书云文档。

商业计划书：强调市场机会、产品与商业模式、竞争、团队、财务与风险，形成可评审BP。

季度/年度业务汇报：围绕指标达成、业务进展、问题与对策输出结构化业务汇报。

公司调研：基于官方与公开信息输出公司概况、业务结构、竞争位置、经营与风险的结构化研究。

竞品分析：通过统一维度对比产品与市场信息，形成结构化对比结论与机会点。

概念解释：由浅入深讲清概念的定义、原理与本质，面向不同知识背景的读者。

基于飞书群聊的**智能摘要与洞察**生成能力。从指定群聊/时间范围的消息中提取关键信息，识别决策、行动项、风险，生成**飞书云文档结构化摘要**。

面向特定行业/赛道的**系统性深度研究**能力。从行业定义、市场规模、竞争格局、技术趋势、政策环境、投融资动态等多维度进行**广覆盖、深挖掘**的全面调研，输出结构化的行业研究报告。

活动营销方案：明确目标人群、核心卖点、传播节奏、渠道矩阵、预算与风险，形成可执行方案。

面向学术论文的**原文级调研（Deep Research）**能力模块。适用于：用户指定某篇论文要求"读透 + 追踪背景 + 扩展最新相关工作"，或用户给出某个学术 topic 要求系统性深度调研与写作综述。

会前材料准备：围绕会议议题、决策点与材料清单，结合历史会议纪要与当前任务进展，生成可讨论、可决策的会前材料。

产品发布会材料：聚焦卖点、发布流程、演示与FAQ，适用于对外宣讲与发布会材料。

项目启动报告：统一目标、范围、里程碑、分工与风险，形成可落地的启动材料。

技术方案：围绕业务目标与约束，输出架构设计、关键模块、技术选型、风险与实施计划的完整技术方案。

根据用户指定的**主题**和**时间范围**，自动检索权威动态，生成一份**飞书云文档动态报告**，按类别聚类，每条新闻含 intro / description / 索引链接。强调**时间筛选 + 权威优先 + 去重**。

基于飞书生态的**每周周报**自动生成 Skill：从当周**日程、任务、妙记、云文档**中提取工作内容，使用 `knowledge_answer` 兜底补全遗漏信息，最终调用 `doc_agent (writer)` 生成结构化的飞书云文档周报。

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) An operation or tool fails unexpectedly, (2) User corrects the agent, (3) User requests a capability that doesn't exist, (4) A better approach or knowledge gap is discovered. Also review learnings before major tasks.

帮助用户创建和更新技能，扩展 aily 工作助手的功能。

Use this skill for analytics tracking implementation and measurement setup: GA4, Google Tag Manager, Mixpanel, Segment, event tracking, conversion tracking, UTM parameters, data layer configuration, and debugging analytics that aren't firing. Use when users want to measure marketing results, track user behavior, create tracking plans, or implement attribution. This skill covers the technical setup of analytics infrastructure — NOT conversion rate optimization tactics, workflow automation, SEO, content creation, or general marketing strategy. For A/B test measurement, see ab-test-setup.

Support SOX 404 compliance with control testing methodology, sample selection (random, systematic, targeted), sample size determination by frequency (annual, quarterly, monthly, weekly, daily), and documentation standards. Use when generating testing workpapers, selecting audit samples, determining sample sizes for controls of different frequencies, classifying control deficiencies, or preparing for internal or external audits.

Write comprehensive backend tests including unit tests, integration tests, and API tests. Use when testing REST APIs, database operations, authentication flows, business logic, or setting up automated testing in CI/CD pipelines. Handles Jest, Pytest, Mocha, testing strategies, mocking, test coverage, and test automation workflows.

Interact with Bilibili (B站/哔哩哔哩) via CLI — fetch video info, subtitles, comments, download audio, search users/videos, browse trending rankings, manage favorites, and perform interactions like likes and triple-clicks

Use this skill when the user wants to discuss, plan, or design something BEFORE implementation. Triggers for: exploring ideas, gathering requirements, creating design specs, comparing architectural approaches, or reviewing design decisions. Does NOT trigger for direct implementation requests like 'write code', 'generate a component', 'create a document', 'fix a bug', or 'deploy this' - those skip straight to implementation. The key signal is the user wants to THINK THROUGH and DESIGN something together, not receive immediate output.

在内容中应用和维护品牌语调、风格指南和核心信息。适用于审查内容一致性、记录品牌调性、适配不同受众语气或检查术语和风格合规。

为销售电话准备客户背景、与会者调研和议程建议。独立使用 Web 搜索即可工作，接入 CRM、邮件、聊天或会议记录后效果更佳。触发词：「帮我准备和 [公司] 的电话」「电话准备 [公司]」。

使用 OAMC 框架（目标、受众、信息、渠道、衡量）规划营销活动，涵盖受众分群、渠道策略、内容日历和 KPI 设定。适用于活动上线、产品发布、内容排期或预算分配。

为常见法律咨询生成模板化回复，同时识别需要个案处理的情形。适用于数据主体请求、供应商咨询、NDA 请求、诉讼保全通知等日常法律问题的回复管理。

Benchmark compensation against market data. Trigger with "what should we pay", "comp benchmark", "market rate for", "salary range for", "is this offer competitive", or when the user needs help evaluating or setting compensation levels.

深度调研竞品并生成交互式 HTML 竞争卡片，包含产品对比矩阵和销售话术。触发词：「竞争情报」「调研竞品」「我们和 [竞品] 怎么比」「[竞品] 的战卡」。

Use this skill when the user wants to create competitor comparison or alternative pages for websites, landing pages, or SEO content. Trigger on requests mentioning 'alternative page,' 'vs page,' 'competitor comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'battle card,' or 'competitor teardown' when the output is for web content. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Not for PPTs, presentations, or general sales documents—use sales-enablement for those.

导航隐私法规（GDPR、CCPA），审查数据保护协议，处理数据主体请求。适用于审查数据处理协议、响应数据主体访问/删除请求、评估跨境数据传输要求或隐私合规评估。

撰写多渠道营销内容——博客、社交媒体、邮件、落地页、新闻稿和案例研究。适用于任何营销内容写作，支持渠道专属格式、SEO 优化、标题选项和行动号召。

依据组织谈判手册审查合同，标记偏差并生成修改建议。适用于审查供应商合同、客户协议或任何需要逐条对比标准条款的商业协议。

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' or 'sharpen the messaging.' Use this when the user already has copy and wants it improved rather than rewritten from scratch. For writing new copy, see copywriting.

Use this skill to research customer-specific questions and investigate account contexts. Search across internal documentation, knowledge bases, CRM records, and connected sources to answer questions about specific customer accounts, their history, product usage, support tickets, or inquiries. Synthesize findings with confidence scores. Trigger when users need to investigate a particular customer's situation, verify information for a specific account, or gather background on customer interactions. Do not use for general competitive analysis, skill evaluation, or tasks unrelated to specific customer accounts.

提供每日优先级排序的销售简报。独立使用时需手动输入会议和优先事项，接入日历、CRM 和邮件后效果更佳。触发词：「晨间简报」「今日安排」「帮我准备今天的工作」。

通过提取分析师的领域知识，生成或改进公司级数据分析技能。 BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want aily to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.

数据集画像和探索，理解数据的结构、质量和分布模式。适用于接触新数据集、评估数据质量、发现列分布、识别空值和异常值，或决定分析维度。

在分享给干系人前对分析进行 QA 检查——方法论验证、准确性核实和偏差检测。适用于审查分析错误、检查幸存者偏差、验证聚合逻辑或准备可复现性文档。

使用 Python（matplotlib、seaborn、plotly）创建数据可视化。适用于构建图表、选择图表类型、创建出版级图形或应用无障碍和色彩理论等设计原则。