lark-skill-maker

A guide for creating reusable coding-agent skills that call Feishu APIs through lark-cli. lark-cli is a command-line tool for accessing Feishu operations from a terminal.

In plain words
What is it for?
Use it to design skills that wrap Feishu API calls or coordinate several steps, choosing between ready-made shortcuts, registered APIs, and direct API requests.
Why use it?
It helps package repeated Feishu procedures into one documented skill instead of rebuilding the same API steps each time. It also explains how to inspect available commands and their parameters.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dropfan/claude-code-plugins/lark-skill-maker
Any agent
npx skills add DropFan/claude-code-plugins --skill lark-skill-maker
Clone the repo
git clone --depth 1 https://github.com/DropFan/claude-code-plugins

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00963
Opus 5 $0.00023 $0.00481
Sonnet 5 $0.00009 $0.00193
Haiku 4.5 $0.00005 $0.00096

Measured 2d ago against content hash c4f04deea5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lark-skill-maker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/lark/skills/lark-skill-maker/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ Cowork / Claude Desktop 执行环境说明(自动注入)

本技能依赖本地 lark-cli@larksuite/cli,可用 command -v lark-cli 定位)及其 ~/.lark-cli 登录态(应用密钥存于 macOS keychain)。

在 Cowork 中运行任何 lark-cli 命令时,必须在本地 macOS 上执行(使用 Desktop Commander 的 start_process / interact_with_process,或其它本地 shell 工具),不要用隔离的 Linux 沙箱 mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。 执行前确保 npm 全局 bin 目录(npm prefix -g 输出目录下的 bin)在 PATH 中。

(在 Claude Code 中可忽略本说明,lark-cli 在本机 shell 直接可用。)

Skill Maker

基于 lark-cli 创建新 Skill。Skill = 一份 SKILL.md,教 AI 用 CLI 命令完成任务。

CLI 核心能力

lark-cli <service> <resource> <method>          # 已注册 API
lark-cli <service> +<verb>                      # Shortcut(高级封装)
lark-cli api <METHOD> <path> [--data/--params]  # 任意飞书 OpenAPI
lark-cli schema <service.resource.method>       # 查参数定义

优先级:Shortcut > 已注册 API > api 裸调。

调研 API

# 1. 查看已有的 API 资源和 Shortcut
lark-cli <service> --help

# 2. 查参数定义
lark-cli schema <service.resource.method>

# 3. 未注册的 API,用 api 直接调用
lark-cli api GET /open-apis/vc/v1/rooms --params '{"page_size":"50"}'
lark-cli api POST /open-apis/vc/v1/rooms/search --data '{"query":"5F"}'

如果以上命令无法覆盖需求(CLI 没有对应的已注册 API 或 Shortcut),使用 lark-openapi-explorer 从飞书官方文档库逐层挖掘原生 OpenAPI 接口,获取完整的方法、路径、参数和权限信息,再通过 lark-cli api 裸调完成任务。

通过以上流程确定需要哪些 API、参数和 scope。

SKILL.md 模板

文件放在 skills/lark-<name>/SKILL.md

---
name: lark-<name>
version: 1.0.0
description: "<功能描述>。当用户需要<触发场景>时使用。"
metadata:
  requires:
    bins: ["lark-cli"]
---


# <标题>

> **前置条件:** 先阅读 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)。

## 命令

\```bash
# 单步操作
lark-cli api POST /open-apis/xxx --data '{...}'

# 多步编排:说明步骤间数据传递
# Step 1: ...(记录返回的 xxx_id)
# Step 2: 使用 Step 1 的 xxx_id
\```

## 权限

| 操作 | 所需 scope |
|------|-----------|
| xxx | `scope:name` |

关键原则

  • description 决定触发 — 包含功能关键词 + "当用户需要...时使用"
  • 认证 — 说明所需 scope,登录用 lark-cli auth login --domain <name>
  • 安全 — 写入操作前确认用户意图,建议 --dry-run 预览
  • 编排 — 说明数据传递、失败回滚、可并行步骤

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 97 lines · 46 tokens per session scan A c4f04deea5c8

Subscribe to this mod's changes

lark-skill-maker is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 46 tokens to every session and 963 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.