productivity by openakita
飞书 CLI (lark-cli) openakita/skills@feishu-cli
Feishu/Lark CLI - official open-source CLI tool from Feishu for AI Agents. Provides 200+ commands across 12 business domains: IM, Docs, Sheets, Base (Bitable), Calendar, Video Meeting, Mail, Tasks, Wiki, Drive, Contacts, Search. Supports both user identity and bot identity authentication.
What it changes View full report → Passed 22 of 22 test cases with the skill, and 11 of 22 without it.
Without skill 52%
With skill 100%
Checks it passed that the model alone missed and 13 more in the full report
11 fixed12 passed either way0 still failing0 broke
Pass-rate lift +48 pp
Tokens +35%
Agent turns 0%
Response time -39% Model gemini-3.6-flashMeasured 8/13/2026 v1 23 of 23 cases passed with skill · 22 comparable
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/openakita-skills-feishu-cli/SKILL.md https://app.decimal.ai/s/openakita-skills-feishu-cli/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add openakita-skills-feishu-cli, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/openakita-skills-feishu-cli/ and pins it in .decimal/skills.lock
$ decimalai skills add openakita-skills-feishu-cliCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/openakita-skills-feishu-cli/SKILL.md https://app.decimal.ai/s/openakita-skills-feishu-cli/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt I need to quickly create a task with the summary "Review Q3 Report" via the Feishu CLI quick script. What is the exact script invocation?
What was checked, without and with the skill Checked Without skill With skill Recommends running python3 scripts/feishu_quick.py create-task. Includes --summary parameter in the command.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 128 lines 3 files includes scripts
飞书 CLI (lark-cli)
飞书官方开源的命令行工具，为 AI Agent 提供连接飞书业务系统的标准化执行入口。安装后 Agent 可以直接读消息、查日历、写文档、建多维表格、发邮件，把任务真正落到飞书里完成。
官方 GitHub: https://github.com/larksuite/cli （7.3k+ Stars）
官方介绍: https://www.feishu.cn/content/article/7623291503305083853
npm: https://www.npmjs.com/package/@larksuite/cli
安装
# 第一步：安装 lark-cli
npm install -g @larksuite/cli
# 第二步：安装相关 Skills
npx skills add https://github.com/larksuite/cli -y -g
# 第三步：初始化应用配置（默认创建新应用，也可选已有应用）
lark-cli config init --new
安装完成后需重启 AI Agent 工具，确保 skills 完整加载。
认证
飞书 CLI 支持两种工作模式：
应用身份（Bot）
不需要用户授权即可使用。AI 可执行发消息、创建文档等操作，但无法访问用户个人数据（如日程、私信、收件箱）。只需在飞书开发者后台开通对应 scope。
用户身份（User）
AI 可以访问用户的个人日历、消息、文档，并以用户名义执行操作。需要完成一次用户授权：
lark-cli auth login
执行后打开链接在飞书中确认即可。后续 AI 在需要访问个人数据时也会自动发起授权提示。
身份选择原则
Track record Benchmark 22 / 22
test cases passed, vs 11 / 22 without
Adoption
Users 3
Times used 62 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/3/2026Version v1Bundled 2 files · scripts