# Create Reusable Lark CLI Skills

Building reusable Lark automation requires consistent API research, permissions, and workflow documentation. This skill guides Claude and Codex through focused lark-cli skills for single APIs or multi-step workflows.

## Install

```bash
npx skillstore add larksuite/lark-skill-maker
```

## Metadata

- Status: approved
- Slug: larksuite-lark-skill-maker
- Version: 1.0.0
- Author version: 1.0.0
- Skillstore revision: r2
- Version status: valid
- Tree hash: f6df5c42a80cb546ab3daee2c2869ee844ae1d87f4729feb5a5a02b94893c089
- Author: larksuite
- GitHub username: larksuite
- License: MIT
- Repository: https://github.com/larksuite/cli/tree/main/skills/lark-skill-maker/
- Ref: ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, filesystem
- Quality score: 81
- Quality tier: silver
- Public page: https://skillstore.pages.dev/skills/larksuite-lark-skill-maker
- Manifest: https://skillstore.pages.dev/api/skills/larksuite-lark-skill-maker/manifest

## Capabilities

- Explains registered APIs, shortcuts, raw OpenAPI calls, and schema lookup commands.
- Guides API research through lark-cli help and schema information.
- Provides a reusable SKILL.md structure with metadata and prerequisites.
- Documents permission scopes and authentication requirements for generated skills.
- Shows how to describe data transfer, rollback, and parallel steps in workflows.
- Recommends user confirmation and dry-run previews before write operations.

## Use Cases

- Wrap a Lark API: Create a reusable skill for one documented Lark operation with its parameters, scope, and authentication requirements.
- Design an Admin Workflow: Coordinate several Lark API calls while documenting identifiers, failure handling, confirmations, and possible parallel steps.
- Standardize Team Skills: Give internal AI tools a consistent SKILL.md structure for lark-cli commands, permissions, and trigger descriptions.

## Prompt Templates

### Create a Basic Skill

```
Create a lark-cli skill for [operation]. Include the trigger description, command, required parameters, authentication, and permission scope.
```

### Research and Wrap an API

```
Research lark-cli support for [Lark task]. Prefer a shortcut, then a registered API, and use raw OpenAPI only when necessary.
```

### Build a Multi-Step Workflow

```
Create a skill for [workflow]. Document each API step, transferred identifiers, required scopes, failure rollback, user confirmations, and parallel opportunities.
```

### Review a Production Skill

```
Review my lark-cli skill for trigger clarity, command choice, schema accuracy, scope coverage, authentication, write confirmations, dry-run support, and recovery behavior.
```

## Limitations

- Requires lark-cli, valid Lark credentials, and suitable permission scopes.
- Does not supply complete parameters for every Lark OpenAPI endpoint.
- Does not execute or validate the generated skill automatically.
- Raw API calls still require careful review of methods, paths, and data.

## Best Practices

- Prefer shortcuts before registered APIs, and prefer registered APIs before raw OpenAPI calls.
- Verify command parameters and permission scopes with lark-cli schema or official documentation.
- Require explicit confirmation and offer a dry-run preview before write operations.

## Anti Patterns

- Do not omit authentication or scope requirements from generated skills.
- Do not use raw OpenAPI calls when a stable shortcut or registered API already exists.
- Do not create multi-step workflows without documenting data transfer and failure recovery.

## Security Audit

- Audited at: 2026-07-23T17:06:07.701\+00:00
- Summary: All 19 static findings are false positives caused by Markdown syntax, fixed sibling documentation links, workflow placeholders, or Chinese text entropy. No executable Ruby backticks, arbitrary path traversal, system reconnaissance, obfuscated content, prompt injection, or malicious intent appears in SKILL.md.

## Stats

- Views: 85
- Downloads: 11
- Favorites: 0
- Popularity score: 0