lark-cli
Automates Feishu/Lark operations via official CLI.
Install
mkdir -p .claude/skills/lark-cli && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16513" && unzip -o skill.zip -d .claude/skills/lark-cli && rm skill.zipInstalls to .claude/skills/lark-cli
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when an agent needs to perform real Feishu/Lark actions through the official larksuite/cli tool, including Docs, Wiki, Calendar, Tasks, Drive, Messenger, and discovery via official agent skills.Key capabilities
- →Create documents with specified titles and markdown content
- →Append or update existing documents
- →Search documents or spreadsheets
- →Manage calendar events and tasks
How it works
The skill uses the official `larksuite/cli` tool to perform actions. It prioritizes shortcuts, then schema inspection, and finally direct method calls. It supports core flows like Docs, Wiki, Calendar, and Tasks.
Inputs & outputs
When to use lark-cli
- →Create or update a Lark document
- →Search wiki nodes
- →Manage calendar agendas
About this skill
Lark CLI
Use this skill when the user wants a real Feishu/Lark action completed through the official larksuite/cli project.
This skill replaces the old local feishu-official-ops and feishu-canvas workflows.
Required Setup
The host must have the official CLI installed:
npm install -g @larksuite/cli
npx skills add larksuite/cli -y -g
Before doing real work, verify the CLI exists:
lark-cli --help
If it is missing, stop and report the blocker instead of falling back to the old local Feishu scripts.
Default Rule
Prefer the official lark-cli command surface over local wrappers:
- Use
lark-cli <service> +<shortcut>first. - If a shortcut is not enough, inspect
lark-cli schema <service>.<resource>.<method>. - Then call
lark-cli <service> <resource> <method>. - Only use
lark-cli api ...as the last resort.
Core Flows
Docs
- Create a document:
lark-cli docs +create --title "Weekly Report" --markdown "# Progress\n- Completed feature X"
- Append or update an existing document:
lark-cli docs +update --doc "<doc_id_or_url>" --mode append --markdown "## Update\n\nNew content"
- Search documents or spreadsheets before deciding which domain skill to use:
lark-cli docs +search --query "项目周报"
Wiki
- Inspect or manage wiki nodes via
lark-cli wiki .... - If a wiki link is provided, first resolve the real object/token instead of assuming the wiki token is the doc token.
Calendar
- View agenda:
lark-cli calendar +agenda
- Recommend time slots before creating a meeting when time is uncertain:
lark-cli calendar +suggestion --start "2026-03-30T09:00:00+08:00" --end "2026-03-30T18:00:00+08:00" --duration-minutes 30
- Create an event after time is confirmed:
lark-cli calendar +create --summary "项目评审" --start "2026-03-30T14:00:00+08:00" --end "2026-03-30T15:00:00+08:00"
Tasks
- Create a task:
lark-cli task +create --summary "整理发布清单"
- List my tasks:
lark-cli task +get-my-tasks
Rules
- Do not use
feishu-canvas; document workspace requests should go throughlark-cli docs +createandlark-cli docs +update. - Do not use the old
feishu-openapi.mjsscript. - When command parameters are unclear, inspect
schemafirst instead of guessing. - Report the real returned IDs, URLs, and metadata after successful writes.
- If auth or config is missing, report the exact missing step.
When not to use it
- →When the official larksuite/cli tool is not installed
- →When the task requires using old local Feishu scripts
- →When command parameters are unclear and schema inspection is not desired
Prerequisites
Limitations
- →Requires the official `larksuite/cli` to be installed
- →Does not support old `feishu-canvas` or `feishu-openapi.mjs` scripts
- →Relies on the `lark-cli` command surface
How it compares
This skill directly interfaces with the official Lark CLI, ensuring real-time and supported actions within the Feishu/Lark ecosystem, unlike using outdated or unofficial local scripts.
Compared to similar skills
lark-cli side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| lark-cli (this skill) | 0 | 4mo | Review | Intermediate |
| linear | 10 | 2mo | No flags | Beginner |
| notion-knowledge-capture | 10 | 9mo | No flags | Intermediate |
| zapier-workflows | 11 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
linear
lobehub
Linear issue management guide. Use when working with Linear issues, creating issues, updating status, or adding comments. Triggers on Linear issue references (LOBE-xxx), issue tracking, or project management tasks. Requires Linear MCP tools to be available.
notion-knowledge-capture
makenotion
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.
zapier-workflows
davila7
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
attio-skill-generator
kesslerio
Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.
automation-brainstorm
MacroMan5
Interactive workflow design advisor for Power Automate, n8n, Make, Zapier and other platforms. Guides users through planning automation workflows with smart questions about triggers, actions, data flow, and error handling. Uses research sub-agent to find best practices and generates detailed implementation plan. Triggers when user mentions "create workflow", "build flow", "design automation", "need ideas for", or describes workflow requirements without having a complete design.
session-handoff
davila7
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.