Claude Skills by seaworld008

Configure and troubleshoot Honcho memory for Hermes.

Implement or audit UI internationalization: translation keys, locale files, pluralization, formatting, hard-coded strings, and parity checks.

Explore alternatives and stress-test assumptions when refining a vague idea into a concrete concept or evaluating an early plan.

Generate or edit images with OpenAI image tools or the bundled API CLI, including inpainting, background changes, transparent assets, and variants.

Coordinate active incidents through severity assessment, roles, mitigation, communications, recovery verification, and postmortem handoff.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you''re about to write a large amount of code at once, or when a task feels too big to land in one step.

Design or audit ISO 27001 ISMS controls, security risk treatment, and compliance evidence, including healthcare and medical-device contexts.

Inspect untrusted external content for prompt injection when suspicious instructions or data-boundary risks need explicit analysis.

Interview the user when they request guided discovery or when unresolved goals, audience, or constraints materially affect a proposed solution.

Design hiring interviews, competency matrices, question banks, scoring rubrics, and interviewer calibration for a specified role.

Use when turning research notes into an investment memo, writing a buy or sell thesis, or structuring catalysts, risks, and monitoring items for an IC-style document.

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Use when managing Kubernetes clusters, debugging Pods and workloads, designing Helm charts, reviewing manifests, or improving deployment, scaling, and observability practices.

Build React/Next.js landing pages with Tailwind, focused copy, accessible sections, calls to action, metadata, and performance validation.

飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

Use when querying Lark attendance records, checking missing clock-ins, and preparing traceable explanations for attendance exceptions.

操作飞书 Base 多维表格、字段、记录、视图、公式、仪表盘、BaseApp 页面和角色权限。处理 /base/、/app/ 链接；导入导出转 lark-drive，认证转 lark-shared。

飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-meeting）、待办任务（走 lark-task）。

飞书 / Lark 通讯录:按姓名 / 邮箱解析成 open_id,或按 open_id 反查姓名 / 部门 / 邮箱 / 联系方式 / 个人状态 / 签名,以及按关键词搜索当前用户可见的机器人 / 智能体(agent)。当用户提到一个名字要下一步发消息 / 排日程,或拿到 open_id 想查具体信息时使用。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。

飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

管理飞书 Drive 云空间文件、目录、元数据、权限和版本，以及 Word/Markdown/Excel/CSV/PPTX 导入导出。搜索文件或解析资源链接时使用；文档正文编辑转对应文档技能。

Consume Lark/Feishu events as NDJSON with lark-cli for messaging, approvals, tasks, meetings, and drive changes; use for event subscriptions, not historical queries.

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

飞书邮箱：Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等；use for mail/email intent only. Do not use for docs/sheets/calendar/auth setup/pure contact lookup/IM chat tasks.

操作飞书云空间中的 Markdown 文件：读取、创建、上传、局部编辑和比较。用于飞书 Markdown 资源操作；本地 Markdown 编辑无需此技能，导入在线文档和云盘管理转对应技能。

Use Lark CLI to locate meetings, manage Minutes and AI notes, inspect transcripts, and run authorized live-meeting interactions.

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、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。不负责：待办任务管理（lark-task）、日程/会议安排（lark-calendar）、绩效评估

飞书/Lark 原生 OpenAPI 探索：从官方文档库中挖掘未经 CLI 封装的原生 OpenAPI 接口。当用户的需求无法被现有 lark-* skill 或 lark-cli 已注册命令满足，需要查找并调用原生飞书 OpenAPI 时使用。

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling _notice JSON.

创建、读取和编辑飞书电子表格，处理单元格、公式、工作表、图表、透视表和财务模型；搜索云空间文件转 lark-drive，Base 多维表格转 lark-base。

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。

创建、读取和编辑飞书幻灯片与页面；支持飞书或 doubao.com 的 /slides/ 链接和 token。文件导入导出转 lark-drive，独立画板转 lark-whiteboard。

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。

Use when querying, exporting, or editing Lark whiteboards, including preview images, raw node structures, and structured canvas updates.

管理飞书知识空间、成员和文档节点，查询或调整节点层级。支持飞书或 doubao.com 的 /wiki/ 链接和 token；文件上传转 lark-drive，正文编辑转 lark-doc。

会议纪要整理工作流：汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。

Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use for workflow automation or quality gates via hooks.

云成本、预算告警、资源规格和人工智能工作负载成本优化。

代码库理解、功能发现、数据流追踪和上下文调查。

Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.

用于管理 Linear issues、项目、团队和协作状态。

Use when checking URL availability, dead links, redirect chains, suspicious domains, documentation link health, or link-risk evidence before publishing.

Manage LinkedIn lead qualification and follow-up workflows through linkedin-cli and local lead records; outreach requires existing user authorization.

General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.

Karpathy''s LLM Wiki: build/query interlinked markdown KB.

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

Use when tracking macro regime shifts, summarizing inflation, growth, spreads, and liquidity signals, or creating a house view before updating sector or asset-allocation calls.

Convert PDF, DOCX, PPTX, and other documents to Markdown, preserving tables, images, and structure with the appropriate extraction tool.

Multi-channel demand generation, paid media optimization, SEO strategy, and partnership programs for Series A+ startups