Content Creation

Create, read, edit, and manage Lark documents with content extraction, summarization, and formatting support. Supports three document types: Docx, Wiki, and Cloud Documents; handles embedded spreadsheets, multidimensional tables, and whiteboards by extracting tokens for downstream skill routing Core operations include fetch (with scoping and detail levels), create (XML or Markdown), update (str_replace, block operations, append, overwrite), and media management (insert, download, preview) All docs +create , docs +fetch , and docs +update commands require --api-version v2 flag; defaults to DocxXML format unless Markdown is explicitly requested Recognizes Feishu document URLs and tokens from both feishu.cn and doubao.com domains; routes based on URL path patterns and token type, not domain alone

Manage files, folders, and documents in Lark Drive with upload, download, import, comments, and permissions. Upload and download files; create folders; copy, move, and delete files; import local Word/Markdown/Excel/CSV/PPTX and Base snapshots as cloud documents Add full-text or block-level comments to docs, sheets, slides, and files; manage comment replies and reactions; subscribe to comment change events Manage document permissions, transfer ownership, and apply for access; update file titles across docx, sheet, bitable, file, folder, and wiki types Auto-unwrap wiki URLs to underlying document types (docx, sheet, bitable, slides, file); inspect document metadata and view access records Sync local directories with Drive folders using hash-based or timestamp-based diffing; version history, export, and secure label management

Manage Lark Wiki spaces, members, nodes, and document organization hierarchies. Create, list, and delete knowledge spaces; retrieve space and node information via token or URL Add, remove, and list space members with support for users, groups, and departments; enforces identity constraints (bot identity cannot manage department members) Create, move, copy, and delete wiki nodes; organize documents and shortcuts within space hierarchies Prioritizes user identity over bot identity for personal knowledge resources; includes safety checks for destructive operations like space deletion requiring explicit user confirmation

Aggregate meeting notes within a time range and generate structured reports. Queries meetings by date range (default: past 7 days), retrieves associated notes and verbatim transcripts, and compiles them into daily or weekly summaries Supports single-day overviews and multi-day/weekly reports with meeting statistics, timestamps, topics, and document links Requires lark-cli with authentication to vc domain (and optionally drive domain for document generation) Handles pagination for searches exceeding 30 results and batch queries for up to 50 meeting notes at a time Can optionally generate and append summaries to Lark cloud documents

Create and edit Lark Office slides with XML protocol, supporting presentation creation, page management, and content modification. Supports three creation workflows: one-step creation for simple slides, two-step creation (empty presentation + page-by-page addition) for complex content, and block-level editing of existing pages without reordering Handles slide operations including create, read, delete, and replace at both presentation and individual page levels; automatically parses /slides/ and /wiki/ URLs to extract presentation tokens Requires planning layer (slide_plan.json) before XML generation for new presentations or major rewrites; includes visual planning (layout_type, visual_focus, text_density) and asset planning with fallback strategies Enforces strict XML validation: text must use <content><p>...</p></content> , images require uploaded file_tokens (no external URLs), and all complex content undergoes post-creation verification against validation checklist Provides template search, summarization, and extraction via template_tool.py to avoid boilerplate; prioritizes user identity ( --as user ) for personal content operations

Markdown file operations for Feishu Drive: create, read, edit, patch, and compare native .md files. Five core commands: create new files, fetch remote content, overwrite existing files, apply local text/regex patches, and diff versions or remote vs. local drafts Patch operation downloads the full file, applies replacements locally, then re-uploads; supports single pattern-content pairs and rejects empty results File names must explicitly include .md suffix; content input accepts strings, local files via @file , or stdin via - Requires lark-cli binary and authentication via shared Feishu credentials; file management tasks like rename, move, delete, and permissions belong in lark-drive skill

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning,…

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Writing, explore: mine raw fragments, no structure yet.

Premium brand-kit image generation for high-end identity systems, logo concepts, and visual-world presentations. Generates intentional, minimal brand-guidelines boards across multiple layout formats (3×3, 2×3, 2×2, custom grids) with strong gutters, restrained typography, and strategic negative space Specializes in 10+ visual modes including dark developer/builder, security/threat intelligence, luxury/editorial, voice/communication, and cultural/experimental aesthetics Creates professional logos through five concept methods: monogram + meaning, product action, metaphor fusion, negative space, and construction geometry; ensures symbols are scalable, ownable, and connected to brand strategy Delivers art-directed panels covering logo systems, digital applications, color palettes, typography specimens, physical mockups, cinematic imagery, and UI component details Enforces premium discipline: no generic startup aesthetics, no copied marks, no cluttered layouts; every board answers why the brand exists and how its visual system scales across touchpoints

Turn a decision you can&#x27;t fully answer into a questionnaire for someone else to fill in.

仅当用户或上游配置显式指定 lark-note 时使用，相关请求统一交由 lark-meeting 技能处理。

Comprehensive SEO auditing framework covering crawlability, indexation, speed, on-page optimization, and content quality. Guides systematic assessment across five priority areas: crawlability and indexation, technical foundations, on-page optimization, content quality, and authority signals Includes detailed checklists for title tags, meta descriptions, heading structure, internal linking, image optimization, and keyword targeting Provides site-type-specific guidance for SaaS, e-commerce, content, and local business sites Emphasizes schema markup validation via browser tools or Google Rich Results Test, not static HTML inspection, to avoid false negatives from JavaScript-injected structured data Delivers findings in prioritized action plans with impact levels and specific remediation steps

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

Marketing copy for homepages, landing pages, pricing pages, and other conversion-focused web pages. Guides you through gathering audience, product, and page-context information before writing, with optional integration of existing product marketing documentation Emphasizes specificity, customer language, and benefit-driven messaging over features, with a quick quality checklist to catch common weaknesses Provides page-type-specific frameworks (homepage, landing page, pricing, feature, about) and detailed CTA formulas to drive action Includes copywriting principles (clarity over cleverness, active voice, honest claims) and voice/tone guidance to maintain brand consistency across sections

Create, read, edit, and manipulate Word documents (.docx files) with full formatting control. Create new .docx files from scratch using JavaScript with support for headings, tables, images, hyperlinks, footnotes, headers/footers, and table of contents Edit existing documents by unpacking XML, making targeted changes (including tracked changes and comments), and repacking with validation Extract text and analyze content using pandoc or raw XML access; convert legacy .doc files to .docx format Handle professional formatting: page sizes (US Letter/A4), margins, multi-column layouts, tab stops, and styled lists without manual unicode characters