← all publishers

shengdabai

@shengdabai source repo

Report this profile Claim this profile

• 300 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Afa · shengdabai bundle

   AFA DTC 全链路独立站操盘系统——系统入口、一级路由器、工作流编排器，统筹品牌基建、付费获客、有机增长、变现留存、运营扩张五大业务线。Use when user mentions: 独立站, DTC, 电商, ecommerce, Shopify, 品牌站, 独立站运营, DTC品牌, 全链路, 操盘, 独立站诊断, 独立站增长, 独立站策略.
   0
   installs
2. ▌
   Aihot · shengdabai bundle

   AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI news today"、"看一下 AI 行业动态"、"今天有什么大模型发布"、"昨天 AI 圈"、"看下精选条目"、"AI HOT 精选"、"最近一周的 AI 论文"、"AI 模型发布"、"AI 产品发布"、"AI 行业动态"、"AI 技巧与观点" 等任何中文 AI 资讯查询时使用。即使用户只说"AI 圈"、"AI 新闻"、"AI 日报"，或者只是问"今天发生了什么"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。
   0
   installs
3. ▌
   Zread · shengdabai bundle

   Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `./.zread/wiki/`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module/package explanations, or "what does this repo do"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread / zread.ai directly. Also use it proactively before diving into a large unknown repo — if `./.zread/wiki/current` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word "zread".
   0
   installs
4. ▌
   Afa Cx · shengdabai bundle

   DTC 客户体验与服务智能引擎——客服优化、售后流程、退货策略、客户旅程设计、NPS/CSAT 管理。Use when user mentions: 客户体验, customer experience, CX, 客服, customer service, 退货, returns, 售后, after-sales, NPS, CSAT, 客户满意度, 投诉, complaints, 客户旅程, customer journey, 自动化客服.
   0
   installs
5. ▌
   Afa Fb · shengdabai bundle

   Meta 广告优化引擎——Facebook/Instagram 广告账户结构、受众策略、出价优化、创意测试、Advantage+ 、CBO/ABO。Use when user mentions: Facebook广告, Meta Ads, Instagram广告, FB广告, CPM, CPA, 受众定向, targeting, Advantage+, CBO, ABO, 广告组, ad set, 像素, pixel, ROAS, Meta投放.
   0
   installs
6. ▌
   Afa Gg · shengdabai bundle

   Google Ads 优化引擎——Shopping 广告、搜索广告、PMax、关键词策略、出价优化、Feed 优化、否定词管理。Use when user mentions: Google Ads, 谷歌广告, Shopping广告, PMax, Performance Max, 搜索广告, search ads, 关键词, keywords, ROAS, 出价, bidding, Feed优化, 否定词, negative keywords, 质量得分.
   0
   installs
7. ▌
   Afa Pr · shengdabai bundle

   DTC 品牌公关与声誉管理引擎——媒体权威建设、UGC 增长循环、声誉监控与危机响应、品牌资产保护、内容原子化。Use when user mentions: 公关, PR, 媒体报道, media coverage, 新闻稿, press release, 危机公关, crisis PR, 声誉管理, reputation, 品牌公关, 媒体关系, media relations, 负面评价, 舆情, 品牌保护, UGC, 买家秀, 用户评价, 媒体套件, media kit.
   0
   installs
8. ▌
   Afa Tt · shengdabai bundle

   TikTok 广告优化引擎——TikTok Ads 账户结构、受众策略、创意方向、TikTok Shop、达人合作。Use when user mentions: TikTok, 抖音广告, TikTok Ads, TikTok Shop, 短视频广告, Spark Ads, 达人广告, creator ads, TikTok投放, TikTok开店, TikTok营销.
   0
   installs
9. ▌
   Afa Aov · shengdabai bundle

   DTC 客单价提升与利润优化引擎——捆绑策略、Upsell/Cross-sell、定价心理学、产品组合优化、订单价值分析。Use when user mentions: 客单价, AOV, 提升客单价, average order value, upsell, cross-sell, 捆绑, bundle, 定价, pricing, 利润, profit margin, 订单价值, 折扣策略, discount strategy, 免邮门槛.
   0
   installs
10. ▌
    Afa Geo · shengdabai bundle

    AI 搜索可见度与本地化搜索引擎——AEO/GEO 策略、AI 搜索优化、结构化数据、多语言本地化、hreflang 策略。Use when user mentions: AI搜索, AI search, GEO, AEO, 结构化数据, structured data, 本地化, localization, hreflang, 多语言, multi-language, ChatGPT搜索, Perplexity, AI推荐, AI可见度, 本地SEO, local SEO.
    0
    installs
11. ▌
    Afa Ops · shengdabai bundle

    DTC 运营与供应链优化引擎——仓储物流、库存管理、3PL 选择、发货时效、供应商管理。Use when user mentions: 运营, operations, 供应链, supply chain, 仓储, warehouse, 物流, logistics, 发货, shipping, 库存, inventory, 3PL, 履约, fulfillment, 供应商, supplier, 运营效率.
    0
    installs
12. ▌
    Afa SEO · shengdabai bundle

    DTC SEO 与有机搜索增长引擎——技术SEO、关键词策略、内容规划、产品页优化、结构化数据、链接建设。Use when user mentions: SEO, 搜索引擎优化, 关键词, keywords, 有机流量, organic traffic, 技术SEO, technical SEO, 内容SEO, 反向链接, backlinks, 产品页SEO, 网站速度, 索引, indexing, 搜索排名.
    0
    installs
13. ▌
    Afa Sms · shengdabai bundle

    DTC SMS 营销引擎——短信自动化流、合规建设、列表增长、BFCM 短信策略、短信文案。Use when user mentions: SMS, 短信营销, text message, 短信自动化, SMS flow, TCPA, 短信合规, SMS compliance, 短信列表, 短信文案, SMS copy, MMS, 短信推送, BFCM短信.
    0
    installs
14. ▌
    Lark Vc · shengdabai bundle

    飞书视频会议：搜索历史会议、查询会议纪要产物（总结、待办、章节、逐字稿）、查询会议参会人快照。1. 查询已经结束的会议数量或详情时使用本技能（如历史日期｜昨天｜上周｜今天已经开过的会议等场景），查询未开始的会议日程使用 lark-calendar 技能。2. 支持通过关键词、时间范围、组织者、参与者、会议室等筛选条件搜索会议。3. 获取或整理会议纪要、逐字稿、录制产物时使用本技能。4. 查询“谁参加过某会议”“参会人列表”等参会人快照信息用 vc meeting get --with-participants（任意时点可查，含已结束会议）。注意：**Agent 真实入会/离会、感知正在进行中会议的实时事件**请使用 lark-vc-agent 技能，本技能不覆盖写操作和会中事件流。
    0
    installs
15. ▌
    Afa Paid · shengdabai

    付费获客 Supervisor——统筹 Meta/Google/TikTok 广告与创意生产的跨渠道预算分配、策略协同与路由。Use when user mentions: 付费广告, paid ads, 广告投放, 预算分配, budget allocation, 跨渠道广告, 广告策略, ad strategy, 获客成本, CAC, 广告效果, 投放优化, 多渠道广告.
    0
    installs
16. ▌
    Lark Okr · shengdabai bundle

    飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标（Objective）、关键结果（Key Result）、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。
    0
    installs
17. ▌
    Pr Merge · shengdabai bundle

    This skill should be used when the user asks to "merge a PR", "review and merge pull requests", "integrate external contributions", "handle PR conflicts", "cherry-pick from a PR", or needs to merge GitHub PRs while maximizing contributor attribution.
    0
    installs
18. ▌
    Afa Brand · shengdabai bundle

    DTC 品牌定位与识别引擎——品牌定位画布、品牌声音架构、品牌故事、视觉识别系统、品牌健康审计。Use when user mentions: 品牌定位, brand positioning, 品牌声音, brand voice, 品牌故事, brand story, 视觉识别, visual identity, 品牌策略, brand strategy, 品牌画布, 品牌建设, 品牌升级, 品牌规范, brand guidelines.
    0
    installs
19. ▌
    Afa Email · shengdabai bundle

    DTC 品牌全生命周期邮件营销引擎——自动化流设计、Campaign 文案撰写、可交付性诊断、列表健康度管理、BFCM 作战规划。Use when user mentions: 邮件营销, email marketing, 弃单挽回, abandoned cart, 邮件自动化, email flow, 打开率, open rate, 可交付性, deliverability, BFCM邮件, 邮件文案, email copy, 列表清理, list hygiene, welcome flow, 欢迎流.
    0
    installs
20. ▌
    Afa Scale · shengdabai

    运营与扩张 Supervisor——统筹供应链运营与渠道扩张的路由与协同，管辖 afa-ops 与 afa-expand。Use when user mentions: 扩张, scale, 运营优化, operations, 供应链, supply chain, 新市场, 渠道扩张, channel expansion, 规模化, scaling, 多市场运营.
    0
    installs
21. ▌
    Lark Mail · shengdabai bundle

    飞书邮箱 — draft, compose, send, reply, forward, read, and search emails; manage drafts, folders, labels, contacts, attachments, and mail rules. Use when user mentions 起草邮件, 写一封邮件, 拟邮件, 草稿, 发通知邮件, 发送邮件, 发邮件, 回复邮件, 转发邮件, 查看邮件, 看邮件, 读邮件, 搜索邮件, 查邮件, 收件箱, 邮件会话, 编辑草稿, 管理草稿, 下载附件, 邮件文件夹, 邮件标签, 邮件联系人, 监听新邮件, 收信规则, 邮件规则, draft, compose, send email, reply, forward, inbox, mail thread, mail rules.
    0
    installs
22. ▌
    Lark Task · shengdabai bundle

    飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。
    0
    installs
23. ▌
    Afa Expand · shengdabai bundle

    DTC 渠道扩张与多元化引擎——多市场扩张规划、新渠道开拓、亚马逊/沿海双轨策略、国际化合规、本地化运营。Use when user mentions: 扩张, expansion, 新市场, new market, 亚马逊, Amazon, 多渠道, multi-channel, 国际化, internationalization, 欧洲市场, 东南亚, 渠道多元化, 沿海市场, wholesale, 批发, 渠道评估, MEURO.
    0
    installs
24. ▌
    Afa Launch · shengdabai bundle

    DTC 产品上市与冷启动引擎——四阶段启动计划、MVP 广告测试、PMF 判定、新品冷启动策略、市场验证。Use when user mentions: 上市, launch, 冷启动, cold start, 新品, new product, PMF, product-market fit, MVP, 市场验证, validation, 启动计划, go-to-market, 新品上架, 首发.
    0
    installs
25. ▌
    Afa Retain · shengdabai bundle

    DTC 品牌用户留存与 LTV 增长引擎——留存健康体检、RFM+LTV 分层、微诚度计划设计、订阅防流失、召回体系、群组分析。Use when user mentions: 留存, retention, 复购率, repurchase, LTV, 客户生命周期, customer lifetime value, 流失, churn, 微诚度, loyalty, 会员, membership, 订阅, subscription, 召回, win-back, 沉睡客户, 再激活, reactivation, RFM分层.
    0
    installs
26. ▌
    Afa Social · shengdabai bundle

    DTC 社交内容与 UGC 引擎——内容日历规划、平台策略、UGC 征集与管理、社区运营、品牌叙事。Use when user mentions: 社交媒体, social media, Instagram, TikTok内容, 内容日历, content calendar, UGC, 用户生成内容, 社区, community, 帖子, posts, Reels, 短视频, 品牌内容, 内容策略, content strategy.
    0
    installs
27. ▌
    Lark Event · shengdabai bundle

    Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM message receive, reactions, chat member changes, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.
    0
    installs
28. ▌
    Afa Compete · shengdabai bundle

    DTC 竞争情报引擎——竞品逆向工程、流量拆解、广告策略分析、定价对标、差异化机会识别。Use when user mentions: 竞品分析, competitor analysis, 竞争对手, 逆向工程, reverse engineer, 竞品拆解, 流量分析, traffic analysis, 差异化, differentiation, 竞争格局, competitive landscape, 对标.
    0
    installs
29. ▌
    Afa Convert · shengdabai bundle

    DTC 全链路转化率优化引擎——转化漏斗分析、结账流程优化、弃单挽回、落地页优化、A/B测试、信任元素。Use when user mentions: 转化率, conversion rate, CRO, 加购率, add to cart, 结账, checkout, 弃单, abandoned cart, 落地页, landing page, A/B测试, 信任度, trust, 购买流程, 转化漏斗, funnel.
    0
    installs
30. ▌
    Afa Explore · shengdabai bundle

    DTC 用户洞察与市场探索引擎——VOC 深度挖掘、市场规模评估、用户画像、赛道分析、竞争格局映射。Use when user mentions: 市场调研, market research, 用户洞察, user insight, VOC, 用户画像, persona, 市场规模, TAM SAM SOM, 赛道分析, 品类分析, category analysis, 需求挖掘, 空白市场, 用户研究.
    0
    installs
31. ▌
    Afa Organic · shengdabai

    有机增长 Supervisor——统筹 SEO、社交内容、网红合作、公关传播、AI 搜索优化的跨渠道有机流量策略与路由。Use when user mentions: 有机增长, organic growth, 免费流量, free traffic, SEO+社交, 内容营销, content marketing, 降低广告依赖, 自然流量, organic traffic, 有机策略.
    0
    installs
32. ▌
    Afa Product · shengdabai bundle

    DTC 产品策略引擎——产品发现与验证、溢价阶梯构建、COGS 与定价建模、供应链管理、产品组合规划。Use when user mentions: 产品策略, product strategy, 定价, pricing, COGS, 产品组合, product mix, SKU, 产品线, product line, 溢价, premium, 产品验证, 产品开发, 选品, product selection.
    0
    installs
33. ▌
    Kairos Lite · shengdabai bundle

    Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.
    0
    installs
34. ▌
    Lark Slides · shengdabai bundle

    飞书幻灯片：创建和编辑幻灯片，接口通过 XML 协议通信。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。
    0
    installs
35. ▌
    Afa Creative · shengdabai bundle

    DTC 创意生产与测试引擎——广告创意策略、创意角度矩阵、Hook 变体、A/B测试、创意疲劳刷新。Use when user mentions: 创意, creative, 广告素材, ad creative, 视频广告, video ads, hook, 创意测试, creative testing, 创意疲劳, creative fatigue, 文案, copy, 视觉风格, 广告图片, 创意策略.
    0
    installs
36. ▌
    Afa Diagnose · shengdabai bundle

    DTC 全链路诊断与归因引擎——全链路归因分析、关键指标异常检测、跨业务线问题定位、根因分析、优先级排序。Use when user mentions: 诊断, diagnose, 归因, attribution, 问题分析, root cause, 指标下降, 转化率下降, ROAS下降, CPA上升, 全链路, full-funnel, 异常检测, anomaly, 问题出在哪, 为什么下降.
    0
    installs
37. ▌
    Afa Monetize · shengdabai

    变现与留存 Supervisor——统筹转化优化、客户体验、用户留存、客单价提升、邮件营销、SMS 营销的全流程路由与协同。Use when user mentions: 变现, monetization, 留存, retention, 转化+留存, 提升收入, revenue growth, 客户价值, customer value, LTV提升, 复购+转化, 变现策略.
    0
    installs
38. ▌
    Dream Memory · shengdabai bundle

    Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
    0
    installs
39. ▌
    Harness Eval · shengdabai bundle

    This skill should be used when the user asks to "test the harness", "run integration tests", "validate features with real API", "test with real model calls", "run agent loop tests", "verify end-to-end", or needs to verify OpenHarness features on a real codebase with actual LLM calls.
    0
    installs
40. ▌
    Lark Contact · shengdabai bundle

    飞书 / Lark 通讯录,用于按姓名 / 邮箱把员工解析成 open_id,以及按 open_id 反查员工的姓名 / 部门 / 邮箱 / 联系方式。当用户说出某人姓名而下一步需要发消息 / 加群 / 排日程时,先用本 skill 把姓名换成 ID;当输出里出现 open_id 需要展示成姓名给用户看,或用户直接询问某人的部门 / 邮箱 / 联系方式时,用本 skill 查。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生 OpenAPI。
    0
    installs
41. ▌
    Lark Minutes · shengdabai bundle

    飞书妙记：妙记相关基本功能。1.查询妙记列表（按关键词/所有者/参与者/时间范围）；2.获取妙记基础信息（标题、封面、时长 等）；3.下载妙记音视频文件；4.获取妙记相关 AI 产物（总结、待办、章节）；5.上传音视频生成妙记，也支持将本地音视频文件转成纪要、逐字稿、文字稿、撰写文字等产物。遇到这类请求时，应优先使用本 skill，而不是尝试 `ffmpeg`、`whisper` 等本地转写命令。飞书妙记 URL 格式: http(s)://<host>/minutes/<minute-token>
    0
    installs
42. ▌
    Afa Dashboard · shengdabai bundle

    DTC 数据仪表盘与体检引擎——全链路数据分析、KPI 追踪、行业基准对标、数据健康度评估、市场趋势监控。Use when user mentions: 数据体检, data audit, KPI, 仪表盘, dashboard, 指标追踪, metrics, 基准线, benchmark, 数据分析, data analysis, 营收报表, revenue report, 渠道数据, 广告数据, ROAS跟踪.
    0
    installs
43. ▌
    Huashu Design · shengdabai bundle

    花叔Design——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审。根据任务embody对应专家（UX/动画师/幻灯片设计师/原型师），避免web design tropes。触发词：做原型、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、做个HTML页面、做个可视化、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、设计方向、配色方案、推荐风格、选个风格、做个好看的、评审、好不好看、review this design、带解说的动画、解说视频、长视频科普、voiceover、narration、5分钟讲清楚什么是XX。需求模糊时进设计方向顾问（三套逻辑并行出3版真实视觉，HTML原生40种风格库网页20+PPT20为弹药）；另含品牌资产协议、反AI slop、Junior工作流、Tweaks变体、动画→MP4/GIF导出、带解说长视频pipeline、5维评审。
    0
    installs
44. ▌
    Lark Approval · shengdabai

    飞书审批 API：审批实例、审批任务管理。
    0
    installs
45. ▌
    Lark Calendar · shengdabai bundle

    飞书日历（calendar）：提供日历与日程（会议）的全面管理能力。核心场景包括：查看/搜索日程、创建/更新日程、管理参会人、查询忙闲状态及推荐空闲时段、查询/搜索与预定会议室。注意：涉及【预约日程/会议】或【查询/预定会议室】时，必须先读取 references/lark-calendar-schedule-meeting.md 工作流！高频操作请优先使用 Shortcuts：+agenda（快速概览今日/近期行程）、+create（创建日程并按需邀请参会人及预定会议室）、+update（更新既有日程字段，或独立增删参会人/会议室）、+freebusy（查询用户主日历的忙闲信息和rsvp的状态）、+rsvp（回复日程邀请）
    0
    installs
46. ▌
    Lark Markdown · shengdabai bundle

    飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。
    0
    installs
47. ▌
    Lark Vc Agent · shengdabai bundle

    飞书视频会议：让机器人代当前用户加入/离开正在进行的会议，并读取会议期间的实时事件（参会人加入与离开、发言、聊天、屏幕共享等）。1. 用户提供 9 位会议号、要求代为入会或离会时使用 +meeting-join / +meeting-leave——会真实产生入会/离会记录。2. 会议进行中用户想知道“谁加入了”“谁离开了”“谁在发言”“有人共享屏幕吗”等会中动态时，机器人入会后用 +meeting-events 读取事件时间线。3. 典型场景：参会机器人、会中助手、代为旁听、代为参会。前提：机器人只能读到它自己参会过且仍在进行中的会议的事件；查询已结束会议的参会名单、纪要或逐字稿请使用 lark-vc 技能。
    0
    installs
48. ▌
    Omc Reference · shengdabai

    OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestrating teams, making commits, or invoking skills.
    0
    installs
49. ▌
    Afa Foundation · shengdabai

    品牌与产品基建 Supervisor——统筹市场探索、竞争情报、品牌定位、产品策略、产品上市的全流程路由与协同。Use when user mentions: 品牌建设, brand building, 产品规划, product planning, 从零开始, from scratch, 品牌基建, foundation, 市场调研, market research, 品牌定位, brand positioning, 产品上市, product launch.
    0
    installs
50. ▌
    Afa Influencer · shengdabai bundle

    DTC 网红与联盟营销引擎——网红筛选与合作、品牌大使计划、联盟营销、KOL/KOC 策略、合作模式设计。Use when user mentions: 网红, influencer, KOL, KOC, 达人, creator, 品牌大使, brand ambassador, 联盟, affiliate, 微型网红, micro-influencer, 合作推广, 种草, seeding, 网红营销.
    0
    installs
51. ▌
    Follow Builders · shengdabai

    AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai. No API keys or dependencies required — all content is fetched from a central feed.
    0
    installs
52. ▌
    Lark Whiteboard · shengdabai bundle

    飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用 DSL（转成 OpenAPI 格式）、PlantUML/Mermaid 格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板，或是需要可视化表达架构、流程、组织关系、时间线、因果、对比等结构化信息时使用此 skill，无论是否提及"画板"。 ⚠️ 原 `lark-whiteboard-cli` skill 已合并至本 skill，若 skill 列表中同时存在 `lark-whiteboard-cli`，请忽略它，统一使用本 skill（`lark-whiteboard`），并提示用户运行 `npx skills remove lark-whiteboard-cli -g` 删除旧 skill。
    0
    installs
53. ▌
    Memory Extractor · shengdabai bundle

    Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
    0
    installs
54. ▌
    Teach Impeccable · shengdabai

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
    0
    installs
55. ▌
    Swarm Coordinator · shengdabai bundle

    Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.
    0
    installs
56. ▌
    Verification Gate · shengdabai bundle

    Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
    0
    installs
57. ▌
    Daily Task Prep · shengdabai

    Morning preparation. Calendar lookahead, meeting context loading, open threads from yesterday, active task review. Extends briefing with actionable prep.
    0
    installs
58. ▌
    Structured Context Compressor · shengdabai bundle

    Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.
    0
    installs
59. ▌
    Careful · shengdabai

    Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
    0
    installs
60. ▌
    Stock Analyzer · shengdabai bundle

    Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.
    0
    installs
61. ▌
    Skillify 2 · shengdabai bundle

    Codify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the same intent run the codified script in ~200ms instead of re-driving the page. Walks back through the conversation, synthesizes script.ts + script.test.ts + fixture, runs the test in a temp dir, and asks before committing. Use when asked to "skillify", "codify", "save this scrape", or "make this permanent". (gstack)
    0
    installs
62. ▌
    Real Engineer Tdd · shengdabai bundle

    Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
    0
    installs
63. ▌
    Real Engineer To Prd · shengdabai

    Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
    0
    installs
64. ▌
    Real Engineer Triage · shengdabai bundle

    Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
    0
    installs
65. ▌
    Gstack 2 · shengdabai bundle

    Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots.
    0
    installs
66. ▌
    Real Engineer Caveman · shengdabai

    Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
    0
    installs
67. ▌
    Real Engineer Handoff · shengdabai

    Compact the current conversation into a handoff document for another agent to pick up.
    0
    installs
68. ▌
    Gstack 3 · shengdabai

    Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots.
    0
    installs
69. ▌
    Real Engineer Diagnose · shengdabai bundle

    Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
    0
    installs
70. ▌
    Real Engineer Grill Me · shengdabai

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
    0
    installs
71. ▌
    Real Engineer Prototype · shengdabai bundle

    Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
    0
    installs
72. ▌
    Real Engineer To Issues · shengdabai

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
    0
    installs
73. ▌
    QA 2 · shengdabai bundle

    Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
    0
    installs
74. ▌
    Cso 2 · shengdabai bundle

    Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".
    0
    installs
75. ▌
    QA 3 · shengdabai

    Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
    0
    installs
76. ▌
    Cso 3 · shengdabai

    Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".
    0
    installs
77. ▌
    Learn 2 · shengdabai bundle

    Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"
    0
    installs
78. ▌
    Retro 2 · shengdabai bundle

    Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.
    0
    installs
79. ▌
    Real Engineer Write A Skill · shengdabai

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
    0
    installs
80. ▌
    Browse 2 · shengdabai bundle

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
    0
    installs
81. ▌
    Canary 2 · shengdabai bundle

    Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".
    0
    installs
82. ▌
    Review 2 · shengdabai bundle

    Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes.
    0
    installs
83. ▌
    Learn 3 · shengdabai

    Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "what have we learned", "show learnings", "prune stale learnings", or "export learnings". Proactively suggest when the user asks about past patterns or wonders "didn't we fix this before?"
    0
    installs
84. ▌
    Retro 3 · shengdabai

    Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.
    0
    installs
85. ▌
    QA Only 2 · shengdabai bundle

    Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes.
    0
    installs
86. ▌
    Browse 3 · shengdabai

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
    0
    installs
87. ▌
    Canary 3 · shengdabai

    Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".
    0
    installs
88. ▌
    Review 3 · shengdabai

    Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes.
    0
    installs
89. ▌
    Real Engineer Grill With Docs · shengdabai bundle

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
    0
    installs
90. ▌
    Autoplan 2 · shengdabai bundle

    Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions.
    0
    installs
91. ▌
    QA Only 3 · shengdabai

    Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes.
    0
    installs
92. ▌
    Benchmark 2 · shengdabai bundle

    Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".
    0
    installs
93. ▌
    Autoplan 3 · shengdabai

    Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions.
    0
    installs
94. ▌
    Benchmark 3 · shengdabai

    Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".
    0
    installs
95. ▌
    Testing 2 · shengdabai

    Use when writing test specs for NL artifacts, running /nlpm:test, or setting up TDD workflows for skills, agents, commands, rules, hooks, and prompts.
    0
    installs
96. ▌
    Investigate 2 · shengdabai bundle

    Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.
    0
    installs
97. ▌
    Setup Deploy 2 · shengdabai bundle

    Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".
    0
    installs
98. ▌
    Investigate 3 · shengdabai

    Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.
    0
    installs
99. ▌
    Design Review 2 · shengdabai bundle

    Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site.
    0
    installs
100. ▌
     Office Hours 2 · shengdabai

     YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written. Use before /plan-ceo-review or /plan-eng-review.
     0
     installs