Feishu Doc
openclaw/openclaw
Feishu document read/write workflows. An agent skill from openclaw/openclaw.
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open.
Install Feishu
$ npx skills add nano-muse/nanoMuse --skill feishu -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nano-muse/nanoMuse feishu --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .claude/skills/feishu && rm -rf skills-srcUse ~/.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/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .claude/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishuType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nano-muse/nanoMuse --skill feishu -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nano-muse/nanoMuse feishu --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .agents/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .agents/skills/feishu && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .agents/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nano-muse/nanoMuse --skill feishu -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nano-muse/nanoMuse feishu --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .cursor/skills/feishu && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .cursor/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nano-muse/nanoMuse.git --path nanomuse/skills/builtin/feishu--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nano-muse/nanoMuse --skill feishu -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nano-muse/nanoMuse feishu --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .gemini/skills/feishu && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .gemini/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nano-muse/nanoMuse feishuInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nano-muse/nanoMuse --skill feishu -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .github/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .github/skills/feishu && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .github/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nano-muse/nanoMuse --skill feishu -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nano-muse/nanoMuse feishu --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nano-muse/nanoMuse.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/nanomuse/skills/builtin/feishu .opencode/skills/feishu && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "feishu" agent skill from https://github.com/nano-muse/nanoMuse/tree/main/nanomuse/skills/builtin/feishu into .opencode/skills/feishu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feishu", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
feishu- GitHub stars
- 381
- Token cost
- ~1.1k tokens
- SKILL.md length
- 656 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open.
- The user mentions 飞书
- SKILL.md covers Is it there?, Reading, Writing and With the other hands, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Wants a colleague told something
What it does
Feishu is an agent skill from nano-muse/nanoMuse. The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open. Use when the user mentions 飞书, Lark, a 群, a 日程 or a 飞书文档, or wants a colleague told something.
Its SKILL.md is about 1.1k 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 repository describes itself as: nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers… The licence is GPL-3.0.
When your agent uses it
- The user mentions 飞书
- Wants a colleague told something
Example prompts
- “/feishu”
What it can do on your machine
Read from SKILL.md and the folder at commit 29e7a91. 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
No URLs in SKILL.md.
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
Feishu loads about 1.1k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 656 words of instructions outside code blocks.
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 nano-muse/nanoMuse at commit 29e7a91, republished under its GPL-3.0 licence (© nano-muse). 656 words, ~1,135 tokens.
Download SKILL.mdSave it as
.claude/skills/feishu/SKILL.md (or your agent's skills folder).- name
- feishu
- description
- The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open. Use when the user mentions 飞书, Lark, a 群, a 日程 or a 飞书文档, or wants a colleague told something.
- channel
- cli
- metadata
- author: nanoMuse version: "1"
飞书 (Feishu / Lark) through lark-cli
飞书 has an API, and lark-cli (the official CLI from Larksuite) wraps it; this is done with shell, not on the phone's screen. Every call prints JSON: ok says whether it worked, data holds the result, error.message says what went wrong. Read the JSON, never the user's screen.
Is it there?
shell: lark-cli auth status; identities.user.available must be true for anything done in the user's name (their agenda, their messages). If the command is missing, the answer says not_configured, or the user identity is not logged in, say so in one line and stop; setting it up is the user's job, in two steps they run themselves: lark-cli config init --new once (it prints a link that creates the CLI's own 飞书 app under their account), then lark-cli auth login (a link or a QR code to approve; --domain calendar,im,task narrows what it may touch). Do not try to install it, to run config init or to log in for them. In a sandbox the CLI and its login only exist when the user shared them (sandbox.share_read_only / sandbox.share in config.toml); the error then says "command not found"; tell the user which two lines to add.
Reading
- Today's schedule:
lark-cli calendar +agenda --as user(a date:--date 2026-09-25; a range with--start/--end). - Free time for a meeting:
lark-cli calendar +freebusy --user-ids ou_… --start … --end …. - A person:
lark-cli contact +search-user --query 张三 --as user→ theiropen_id(ou_…). A group:lark-cli im +chat-search --query 项目群 --as user→chat_id(oc_…). Take the one match; with several, ask the user which with oneask_user, do not guess. - What was said:
lark-cli im +chat-messages-list --chat-id oc_… --as user(a DM:--user-id ou_…;--start-time/--end-timefor a window).lark-cli im +messages-search --query 周报 --as useracross chats. - Tasks:
lark-cli task +get-my-tasks --as user. A document:lark-cli docs +fetch --doc <url or token>gives its text. - Add
--jq '<expr>'to keep the output small (--jq '.data[] | {summary, start_time}'), and--format tablewhen you want to show a list to the user as is.
Show full SKILL.md (315 more words)Show less
Writing
Every write is something the user says to other people. Before the call, show the exact text and the recipient and ask with one ask_user; send only what they approved, word for word.
- A message:
lark-cli im +messages-send --chat-id oc_… --text "…" --as user(a DM:--user-id ou_…; longer or formatted:--markdown "…"). Add--idempotency-key <something unique>so a retried command cannot send twice. - A reply in a thread:
lark-cli im +messages-reply --message-id om_… --text "…" --as user. - An event:
lark-cli calendar +create --summary "…" --start 2026-09-25T14:00:00+08:00 --end 2026-09-25T15:00:00+08:00 --attendee-ids ou_a,ou_b --as user. - A task:
lark-cli task +create --summary "…" --due 2026-09-26 --assignee ou_… --as user. - A document:
lark-cli docs +create --title "…" --markdown @notes.md --as userfrom a file in the workspace.
Commands the CLI marks high-risk-write (deleting an event, removing members, anything with --yes) refuse to run without --yes; add it only after the user has said yes to that very action, and never to a command that was not asked for. Sentinel will show the shell command on an approval card; that is expected.
With the other hands
- 飞书 + 高德: plan the route or check the weather with the
amapskill, then put the result in a message or an event description. - 飞书 + the phone: apps that have no API (12306, 微信, 支付宝) are done with
phone_task; the outcome (the train, the payment made) goes to the colleague through lark-cli. - 飞书 + the workspace: a brief, a comparison, a page you wrote becomes a document with
docs +createor an attachment withim +messages-send --file.
Finish
Reply with what was read or done in a few lines: the messages sent (to whom, first words), the event (title, time, attendees), the task (title, due). Do not paste whole chat histories into the answer; give the gist and offer the rest. remember who the user writes to most and which groups matter, so that next time the search is shorter.
© nano-muse, GPL-3.0. 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 nanomuse/skills/builtin/feishu of nano-muse/nanoMuse.
Open the folder on GitHubat commit 29e7a91
Compare with similar skills
Feishu 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Feishu this skillnano-muse/nanoMuse | 381 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | |
| Feishu Docopenclaw/openclaw | 392k | — | ~516 | Automated safety check: Pass | MIT | |
| Feishu Docraucvr/Group-Goki | 112 | 3 repos | ~592 | Automated safety check: Pass | MIT | |
| Feishu Driveraucvr/Group-Goki | 112 | 3 repos | ~587 | Automated safety check: Pass | MIT | |
| Feishu Permraucvr/Group-Goki | 112 | 3 repos | ~630 | Automated safety check: Pass | MIT | |
| Feishu Safety GuideSafeAI-Lab-X/ClawKeeper | 1k | — | ~3.6k | Automated safety check: Pass | None |
Similar skills
Feishu Doc
raucvr/Group-Goki
Feishu document read/write operations. An agent skill from raucvr/Group-Goki.
Feishu Drive
raucvr/Group-Goki
Feishu cloud storage file management. An agent skill from raucvr/Group-Goki.
Feishu Perm
raucvr/Group-Goki
Feishu permission management for documents and files. An agent skill from raucvr/Group-Goki.
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…
Tlive
y49/tlive
tlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex.
More from nano-muse/nanoMuse
All 11 skills in this repoAmap
nano-muse/nanoMuse
Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.
Kuaidi100
nano-muse/nanoMuse
Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server: any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number.
Train Tickets
nano-muse/nanoMuse
Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment.
Compare Options
nano-muse/nanoMuse
Compare two to five options (products, plans, places, tools, offers) on the criteria that matter to the user, in a table the user can re-weight, with a recommendation.
Inbox Triage
nano-muse/nanoMuse
Go through recent mail and sort it into needs-a-reply, waiting-on-others, to-do and can-ignore, with draft replies ready for review.
Meeting Prep
nano-muse/nanoMuse
Prepare for a meeting (who is in it, what was last said with them, what the user owes them and wants from them) as a one-page brief.
Related
Works with
Categories
Questions about Feishu
What does Feishu do?
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open. Feishu is an agent skill from nano-muse/nanoMuse. The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open.
When should I use Feishu?
Feishu fits situations like: the user mentions 飞书; wants a colleague told something.
How do I install Feishu in Claude Code?
Run `npx skills add nano-muse/nanoMuse --skill feishu -a claude-code`. Or copy the skill folder (nanomuse/skills/builtin/feishu in nano-muse/nanoMuse) into .claude/skills/feishu in your project. Claude Code loads it when a task matches its description.
How do I install Feishu in Codex?
Run `npx skills add nano-muse/nanoMuse --skill feishu -a codex`. Or copy the skill folder (nanomuse/skills/builtin/feishu in nano-muse/nanoMuse) into .agents/skills/feishu in your project. Codex loads it when a task matches its description.
Can I use Feishu 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 nano-muse/nanoMuse --skill feishu -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feishu, .gemini/skills/feishu, .github/skills/feishu and .opencode/skills/feishu in your project.
What does Feishu need to run?
SKILL.md names no scripts, command-line tools or credentials: Feishu is instructions for the agent only.
Does Feishu access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Feishu 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 Feishu use?
Feishu is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Feishu use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Feishu?
Skills that share tags, products or a category with Feishu: Feishu Doc (openclaw/openclaw, 392k stars), Feishu Doc (raucvr/Group-Goki, 112 stars), Feishu Drive (raucvr/Group-Goki, 112 stars) and Feishu Perm (raucvr/Group-Goki, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Feishu?
nano-muse (a GitHub organization) maintains it in nano-muse/nanoMuse, which has 381 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.
Source: nano-muse/nanoMuse on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.