Latest Agent Skills

飞书幻灯片：创建和编辑幻灯片。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。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 lark-doc）、云文档里的独立画板对象（走 lark-whiteboard）、上传或下载普通文件（走 lark-drive）。

飞书电子表格：创建和操作电子表格。支持创建表格、管理工作表与行列结构（增删/合并/调整尺寸/隐藏/冻结）、读写单元格（值/公式/样式/批注/单元格图片）、查找替换、多操作批量更新，以及图表、透视表、条件格式、筛选器、迷你图、浮动图片等对象的创建与维护。当用户需要创建电子表格、管理工作表、批量读写或编辑数据、统计汇总与可视化、表格美化、公式计算（含 Excel 公式迁移）、金融/财务建模（DCF、三张表、预算、Sensitivity 等）等任务时使用。若用户是想按名称或关键词搜索云空间（云盘/云存储）里的表格文件，请改用 lark-drive 的 drive +search 先定位资源。当用户给出 doubao.com 的 /sheets/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。

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.

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on \"ideate\", \"refine this idea\", or \"stress-test my plan\".

This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.

Use when users do not know which skill fits a task, need to search available skill catalogs, compare candidates, install a matching skill, or route work to the best existing capability.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

User research specialist. Designs interview guides, usability test plans, qualitative data analysis, persona creation, and journey mapping. Complements Echo's UI validation. Use when user research design or analysis is needed.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Audits natural-language programming artifacts such as SKILL.md, AGENTS.md, CLAUDE.md, slash commands, plugin manifests, hooks, rules, and prompt files. Use when reviewing AI-agent repositories, checking manifest-vs-disk consistency, scoring skill or agent quality, adding NL artifact CI gates, or diagnosing vocabulary and version drift across Claude Code, Codex, Cursor, Gemini, and Antigravity-style projects.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, Approval status changes, Task updates, VC meeting started/joined/ended, Minutes generated, Whiteboard updated, 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.

飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。

Use when the user asks Codex to directly generate images with gpt-image-2 using inherited OpenAI/Codex-compatible environment credentials or local GPT_IMAGE2_* overrides, including text-to-image, reference-image guided generation, ratios, resolution, quality, variants, and saved local image files; run the bundled Node CLI and keep URL/sk configuration private.

Provides comprehensive GitHub operations using gh CLI and GitHub API. Activates when working with pull requests, issues, repositories, workflows, or GitHub API operations including creating/viewing/merging PRs, managing issues, querying API endpoints, and handling GitHub workflows in enterprise or public GitHub environments.

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.

飞书知识库：管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。当用户给出 doubao.com 的 /wiki/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：上传文件到知识库节点下（走 lark-drive）、编辑文档/表格/Base 内容（走 lark-doc / lark-sheets / lark-base）。

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。

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.

飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Provisioning infrastructure via cloud IaC (Terraform/OpenTofu/CloudFormation/Pulumi) and local dev environments (Docker Compose, env vars). Use for IaC design or multi-cloud provisioning.

Use when users need to read, search, create, edit, organize, or cross-link notes in an Obsidian vault while preserving markdown structure and knowledge-base context.

Use when users need to operate MCP servers or tools with the mcporter CLI: list servers, configure auth, call HTTP/stdio tools, edit config, or generate CLI/type bindings.

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

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.

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。

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy. Use when PR preparation or commit strategy is needed.

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

飞书视频会议：查询进行中的会议列表（含会议 ID）、读取会中实时内容（发言、聊天、共享等）、发送会中消息，以及搜索历史会议、查询会议纪要（总结/待办/章节/逐字稿）和参会人快照。Agent 真实入会/离会走 lark-vc-agent；查询未来日程走 lark-calendar。

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。

Collecting GitHub PR data and generating work reports. Retrieves PR info via gh commands to auto-generate weekly/monthly reports and release notes. Use when work reporting or PR analysis is needed.

Designing and reviewing APIs: OpenAPI spec generation, versioning strategy, breaking change detection, REST/GraphQL best practices. Use for API design or OpenAPI specs.

Researching competitors and shaping positioning: feature matrices, SWOT, benchmarking, positioning maps, battle cards, win/loss, LLM brand visibility. Research only — use for strategy, not code.

Implementing robust business logic, API integrations, and data models with type safety. Use when business logic or API integration is needed. Offers an interactive pair-programming mode.

Guardian of V.A.I.R.E. quality standards (Value/Agency/Identity/Resilience/Echo). Handles pre-release evaluation, scorecard assessment, and pass/fail determination. Use when UX quality gates are needed. Does not write code.

Responding to incidents: identifies impact scope, formulates recovery procedures, creates postmortems. Use when incident response or disaster recovery is needed. Delegates fixes to Builder.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Generating AI image-generation code using the Gemini API. Handles text-to-image generation, image editing, and prompt optimization. Use when image generation code is needed.

Guiding workflows by decomposing complex tasks (Epics) into Atomic Steps under 15 minutes each, with progress tracking and drift prevention. Use when complex decomposition is needed.

用于只读查询 Sentry issues、events 和服务健康数据，汇总线上错误并辅助生产问题排查。

Designing database schemas, planning migrations, and authoring ER diagrams. Handles normalization, index strategies, and relation definitions. Use when DB schema design is needed.

Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

用于管理 Linear issues、项目、团队和协作状态。

Optimizing FinOps and cloud cost: IaC-based estimation, right-sizing, RI/SP recommendations, anomaly detection, budget alerts, AI/GPU workload economics. Use to forecast or cut cloud spend.

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Generating and auditing personal dev environment configs (zsh/tmux/neovim/ghostty) and automating the macOS desktop via AppleScript/JXA (Finder, Mail, Safari). Use for dotfiles or Apple Events.

Optimizing SEO (meta/OGP/JSON-LD/headings), SMO (social sharing), CRO (CTA/form/exit-intent), and GEO (AI citation optimization). Use for search ranking, conversion, or AI visibility.

Use when automating GitHub issues, pull requests, reviews, CI checks, labels, releases, or engineering collaboration loops through the GitHub CLI.

Regulatory compliance and audit agent. Maps business regulatory requirements (SOC2/PCI-DSS/HIPAA/ISO 27001), checks control implementations, designs audit trails, and implements Policy as Code. Use when compliance auditing is needed.

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

Engineering observability and reliability: SLO/SLI design, distributed tracing, alerting, dashboards, capacity planning, toil automation, reliability review. Use for instrumentation or SLO definition.

Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.