Agent skill

Lark CLI Workflow

by huangruiteng in huangruiteng/CS-Notes

Coordinate Lark/Feishu CLI tasks from Codex. An agent skill from huangruiteng/CS-Notes.

MITAuto-check passedProductivity & Automation

Install Lark CLI Workflow

skills CLI
$ npx skills add huangruiteng/CS-Notes --skill lark-cli-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huangruiteng/CS-Notes lark-cli-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huangruiteng/CS-Notes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/lark-cli-workflow .claude/skills/lark-cli-workflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lark-cli-workflow
GitHub stars
4k
Token cost
~1k tokens
SKILL.md length
526 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Coordinate Lark/Feishu CLI tasks from Codex. An agent skill from huangruiteng/CS-Notes.

  • Works in 3 steps: Classify the object and action. → For any Lark URL or opaque token,… → Pick identity deliberately.
  • A request involves Feishu/Lark docs
  • SKILL.md covers Default Route, Read Pattern, Write Pattern and Repo Safety, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lark CLI Workflow is an agent skill from huangruiteng/CS-Notes. Coordinate Lark/Feishu CLI tasks from Codex. Use when a request involves Feishu/Lark docs, wiki, Drive files, Sheets, Base, Calendar, Minutes, IM, Mail, Tasks, Contacts, Slides, whiteboards, approvals, attendance, or when a Lark URL/token must be read, edited, summarized, routed, or turned into a real work artifact.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Messaging and chat bots. It works with Feishu (Lark). The licence is MIT.

When your agent uses it

  • A request involves Feishu/Lark docs
  • A Lark URL/token must be read
  • Turned into a real work artifact

Example prompts

  • “/lark-cli-workflow”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Classify the object and action.
  2. For any Lark URL or opaque token, inspect or unwrap it before acting.
  3. Pick identity deliberately.

What it can do on your machine

Read from SKILL.md and the folder at commit d01d8f8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lark CLI Workflow loads about 1k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 526 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huangruiteng/CS-Notes at commit d01d8f8, republished under its MIT licence (© huangruiteng). 526 words, ~1,047 tokens.

Download SKILL.mdSave it as .claude/skills/lark-cli-workflow/SKILL.md (or your agent's skills folder).
name
lark-cli-workflow
description
Coordinate Lark/Feishu CLI tasks from Codex. Use when a request involves Feishu/Lark docs, wiki, Drive files, Sheets, Base, Calendar, Minutes, IM, Mail, Tasks, Contacts, Slides, whiteboards, approvals, attendance, or when a Lark URL/token must be read, edited, summarized, routed, or turned into a real work artifact.

Lark CLI Workflow

This is a thin routing skill. Prefer the official lark-* skills and lark-cli shortcuts for domain details; use this skill to choose the right path, identity, safety level, and final artifact shape.

Default Route

  1. Classify the object and action.
    • Docs / Wiki text: lark-doc, with docs +fetch --api-version v2.
    • Wiki hierarchy / members: lark-wiki.
    • Drive files, file permissions, comments, import/export: lark-drive.
    • Sheets: lark-sheets.
    • Base / Bitable: lark-base.
    • Calendar / meeting-room scheduling: lark-calendar.
    • Past meetings and transcripts: lark-vc or lark-minutes.
    • IM messages, groups, files in chats: lark-im.
    • Mail: lark-mail.
    • Contacts / people resolution: lark-contact.
    • Tasks, OKR, approval, attendance, slides, whiteboard: use the matching lark-* skill.
  2. For any Lark URL or opaque token, inspect or unwrap it before acting.
    • Wiki URLs often point to a node wrapper; resolve the real object token before document fetch/update.
    • Do not assume a docx token, sheet token, bitable token, wiki node token, and drive file token are interchangeable.
  3. Pick identity deliberately.
    • Use --as user for personal docs, Drive, calendar, mail, IM history, wiki spaces, and most user-owned resources.
    • Use --as bot only for app-owned resources or when the user explicitly wants an app identity.
    • If a command returns missing scopes, follow the CLI hint and request the minimum needed auth login --scope ....

Read Pattern

  • Start narrow: outline, keyword, section, or metadata before full document fetch.
  • For Docx v2, always pass --api-version v2.
  • Use JSON output when the result will feed another command.
  • If a document contains embedded sheets, bitables, synced blocks, media, or whiteboards, extract the referenced token and switch to the matching skill instead of summarizing the tag itself.
  • Treat internal links, auth URLs, media URLs, access tokens, user IDs, and chat IDs as private unless the user explicitly asks for them in chat.
Show full SKILL.md (236 more words)Show less

Write Pattern

  • Prefer real work artifacts: create or update the Lark doc, Base record, Sheet range, task, calendar event, email draft, or IM message instead of only producing copy-paste text.
  • Before writing, identify the intended object, block/range/record, and command.
  • Prefer block-level or section-level updates over whole-document overwrite.
  • Preserve comments, highlights, citations, permissions, reviewer-visible formatting, and document structure unless the user asks to replace them.
  • High-risk actions need explicit intent or a dry run first: delete, overwrite, permission change, bulk send, group membership change, task closeout, or external sharing.

Repo Safety

  • Do not write internal Lark URLs, temporary media/auth URLs, access tokens, chat IDs, internal people/team details, or non-public implementation details into tracked repository files.
  • If an internal source has reusable public lessons, write only the generalized lesson and cite public/open sources when available, such as the Lark CLI public repository: https://github.com/larksuite/cli
  • Put private source notes, exact internal links, and sensitive judgments under .local/ when a local record is useful.
  • For CS-Notes tasks, update AGENTS.md, .trae/, .codex/skills/, or Notes/ only when the result improves the durable workflow; avoid demo-only files.

Completion Check

  • Say which Lark object was read or changed, using a safe title or type when links are sensitive.
  • Report identity used (user or bot) when it matters.
  • Mention missing permissions, unread embedded resources, or skipped high-risk actions.
  • If lark-cli suggests an update, finish the current task first, then tell the user the update is available.

© huangruiteng, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/lark-cli-workflow of huangruiteng/CS-Notes.

Open the folder on GitHubat commit d01d8f8

Compare with similar skills

Lark CLI Workflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lark CLI Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lark CLI Workflow this skillhuangruiteng/CS-Notes4k—~1kAutomated safety check: PassMIT
Feishu Docopenclaw/openclaw392k—~516Automated safety check: PassMIT
Feishu Docraucvr/Group-Goki1123 repos~592Automated safety check: PassMIT
Feishu Driveraucvr/Group-Goki1123 repos~587Automated safety check: PassMIT
Tlivey49/tlive2141 repos~1.7kAutomated safety check: NotesMIT
Feishu Permraucvr/Group-Goki1123 repos~630Automated safety check: PassMIT

Similar skills

  • Feishu Doc

    openclaw/openclaw

    Feishu document read/write workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~516 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Feishu Doc

    raucvr/Group-Goki

    Feishu document read/write operations. An agent skill from raucvr/Group-Goki.

    112 GitHub starsUsed in 3 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Feishu Drive

    raucvr/Group-Goki

    Feishu cloud storage file management. An agent skill from raucvr/Group-Goki.

    112 GitHub starsUsed in 3 repos~587 tokens
    Productivity & AutomationAuto-check passed
  • Tlive

    y49/tlive

    tlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex.

    214 GitHub starsUsed in 1 repo~1.7k tokens
    Productivity & AutomationAuto-check: notes
  • Feishu Perm

    raucvr/Group-Goki

    Feishu permission management for documents and files. An agent skill from raucvr/Group-Goki.

    112 GitHub starsUsed in 3 repos~630 tokens
    Productivity & AutomationAuto-check passed
  • Feishu Safety Guide

    SafeAI-Lab-X/ClawKeeper

    One-click deployment Skill for Feishu security governance and message anti-data-leakage guide, responsible for Feishu message security, credential protection, permission auditing, interaction…

    1k GitHub stars~3.6k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

More from huangruiteng/CS-Notes

All 38 skills in this repo
  • CLI Creator

    huangruiteng/CS-Notes

    Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script.

    4k GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Slack

    huangruiteng/CS-Notes

    A skill your agent uses when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.

    4k GitHub starsUsed in 10 repos~578 tokens
    Auto-check passed
  • Codex Thread Heartbeat

    huangruiteng/CS-Notes

    Inspect and manage guarded Codex App-native or launchd heartbeats for Codex main control threads.

    4k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Codex Thread Reader

    huangruiteng/CS-Notes

    Locate and read a Codex thread by a codex thread link, thread id, or rollout path across all local CODEXHOME directories (~/.codex, ~/.codex-gpt, ...).

    4k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Research Material Scout

    huangruiteng/CS-Notes

    A skill your agent uses when the user asks Codex to research, find learning materials, process "素材:" links, "请你读" / "精读" a material, build a material radar, or use SenSight-like broad information…

    4k GitHub stars~8.6k tokensUpdated 2 days ago
    Auto-check passed
  • GitHub

    huangruiteng/CS-Notes

    Interact with GitHub using the gh CLI. An agent skill from huangruiteng/CS-Notes.

    4k GitHub starsUsed in 28 repos~279 tokens
    Auto-check passed

Works with

Questions about Lark CLI Workflow

What does Lark CLI Workflow do?

Coordinate Lark/Feishu CLI tasks from Codex. An agent skill from huangruiteng/CS-Notes. Lark CLI Workflow is an agent skill from huangruiteng/CS-Notes. Coordinate Lark/Feishu CLI tasks from Codex.

When should I use Lark CLI Workflow?

Lark CLI Workflow fits situations like: A request involves Feishu/Lark docs; A Lark URL/token must be read; turned into a real work artifact.

How do I install Lark CLI Workflow in Claude Code?

Run `npx skills add huangruiteng/CS-Notes --skill lark-cli-workflow -a claude-code`. Or copy the skill folder (.codex/skills/lark-cli-workflow in huangruiteng/CS-Notes) into .claude/skills/lark-cli-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Lark CLI Workflow in Codex?

Run `npx skills add huangruiteng/CS-Notes --skill lark-cli-workflow -a codex`. Or copy the skill folder (.codex/skills/lark-cli-workflow in huangruiteng/CS-Notes) into .agents/skills/lark-cli-workflow in your project. Codex loads it when a task matches its description.

Can I use Lark CLI Workflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huangruiteng/CS-Notes --skill lark-cli-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lark-cli-workflow, .gemini/skills/lark-cli-workflow, .github/skills/lark-cli-workflow and .opencode/skills/lark-cli-workflow in your project.

What does Lark CLI Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Lark CLI Workflow is instructions for the agent only.

Does Lark CLI Workflow access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Lark CLI Workflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lark CLI Workflow use?

Lark CLI Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lark CLI Workflow use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lark CLI Workflow?

Skills that share tags, products or a category with Lark CLI Workflow: Feishu Doc (openclaw/openclaw, 392k stars), Feishu Doc (raucvr/Group-Goki, 112 stars), Feishu Drive (raucvr/Group-Goki, 112 stars) and Tlive (y49/tlive, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lark CLI Workflow?

huangruiteng (a GitHub user) maintains it in huangruiteng/CS-Notes, which has 4,000 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 6, 2026.

Source: huangruiteng/CS-Notes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.