← Back to Skills Marketplace
657
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install text-spoken-script
Description
This skill is used to guide the AI in generating short video spoken scripts with high contrast, strong resonance, a sense of story, and personal IP attribute...
Usage Guidance
What to consider before installing or running this skill:
- Inconsistency: The skill declares no required env vars but its instructions require a dLazy API key (DLAZY_API_KEY or ~/.dlazy/config.json). Confirm whether you must provide that key before use.
- Review the CLI: The metadata recommends installing or running the npm package @dlazy/cli (pinned to 1.0.8). Inspect the GitHub repo and the npm package code/release to ensure it behaves as expected before installing or invoking npx.
- Data exfiltration risk: The skill's runtime flow will upload local media files and send prompts to api.dlazy.com/oss.dlazy.com. Do not pass sensitive files or secrets as prompt content or file inputs unless you trust the service and your API key's scope.
- Least privilege: If you proceed, use npx (on-demand) and an API key scoped/rotatable from your dLazy dashboard. Prefer ephemeral/test keys for initial trials.
- If you only want text scripts: you can likely use this skill without installing the CLI or providing a dLazy key — but confirm with the skill author. Ask for the declared required env vars to be updated to match the instructions, or for a variant that does not require CLI invocations.
If you want, I can summarize the exact mismatches to send back to the skill author or draft safer usage instructions (e.g., how to run locally with an isolated test API key and review the npm package).
Capability Analysis
Type: OpenClaw Skill
Name: text-spoken-script
Version: 1.0.5
The skill bundle requires the installation of a global npm package (@dlazy/[email protected]) and provides highly prescriptive 'CRITICAL EXECUTION INSTRUCTIONS' in SKILL.md and SKILL-cn.md that command the AI agent to execute terminal commands (e.g., `dlazy seedream-4.5`). While these actions are aligned with the stated purpose of generating video scripts and media via the dLazy SaaS platform, the use of aggressive prompt-steering language to force shell execution and the requirement for a third-party binary significantly increase the risk of Remote Code Execution (RCE). The skill also manages API keys in `~/.dlazy/config.json` and uploads local media to api.dlazy.com and oss.dlazy.com.
Capability Tags
Capability Assessment
Purpose & Capability
The declared purpose is generating short spoken scripts (text). However metadata and the SKILL.md push use of the dLazy CLI (npm/@dlazy/cli, npx) and image-generation commands. Requiring npm/npx and referencing api.dlazy.com/oss.dlazy.com is disproportionate to a purely text script generator unless you also need image/video generation; the manifest does not declare the dLazy API key as a required env var even though the doc states one is necessary.
Instruction Scope
The SKILL.md contains explicit, stepwise runtime instructions that direct the agent to run terminal commands (e.g., 'dlazy seedream-4.5 --prompt "..."'), upload local media to oss.dlazy.com, and store/use an API key in ~/.dlazy/config.json or DLAZY_API_KEY. Those runtime steps go beyond producing text: they may transmit local files and prompts to an external service. The skill also forbids saving prompts to disk and mandates synchronous single-command execution with user confirmations — all operational constraints the agent must follow.
Install Mechanism
There is no platform install spec (skill is instruction-only), but metadata recommends 'npm install -g @dlazy/[email protected]' or 'npx @dlazy/[email protected]'. Using an npm package/npx is a common pattern and lower risk than arbitrary downloads, but you should review the linked GitHub repo and the exact npm package before installing or running npx.
Credentials
The SKILL.md requires a dLazy API key and references storing it at ~/.dlazy/config.json or passing DLAZY_API_KEY, but the skill's declared 'required env vars' is empty — an inconsistency. The need for an API key (and the ability to upload local files) is reasonable only if you intend to use dLazy's media-generation features; it is not justified for pure text script generation. This mismatch increases the chance of accidental credential use/exposure.
Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skills or system settings. However it explicitly instructs executing CLI commands and uploading files to an external service; combined with the credential/metadata inconsistencies, this elevates operational risk (data transmission to external endpoints) even though no elevated platform privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-spoken-script - After installation, invoke the skill by name or use
/text-spoken-script - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
bump @dlazy/cli to 1.0.8
v1.0.4
Reduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.
v1.0.3
Add provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/[email protected]' install alternative, normalise Chinese auth-error instruction wording.
v1.0.2
- 修正版本号为 1.0.2，确保文档与实际版本一致
- 统一了 en/cn/主文档内容，提升中英文描述一致性
- 无功能或交互变化，仅为文档维护性调整
v1.0.1
- 增加了 dLazy API key 的配置和获取说明，完善身份验证流程。
- 升级依赖的 dlazy CLI 版本至 1.0.6。
- 其他内容和执行流程保持不变，依旧严格遵循 7 步口播文案结构。
v1.0.0
Initial release of text-spoken-script skill.
- Enables AI to generate high-contrast, story-driven, and resonant short video spoken scripts, with a strong personal branding angle.
- Strictly follows a 7-step structure: identity hook, suspense/empathy, vivid storytelling, core insight, personal experience, message elevation, and memorable closing line.
- Designed for oral, emotionally engaging delivery with specific people, stories, or events—no generic preaching.
- Output is optimized for short-video scripts, character stories, and opinion-based personal IP content.
Metadata
Frequently Asked Questions
What is Text Spoken Script?
This skill is used to guide the AI in generating short video spoken scripts with high contrast, strong resonance, a sense of story, and personal IP attribute... It is an AI Agent Skill for Claude Code / OpenClaw, with 657 downloads so far.
How do I install Text Spoken Script?
Run "/install text-spoken-script" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text Spoken Script free?
Yes, Text Spoken Script is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text Spoken Script support?
Text Spoken Script is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text Spoken Script?
It is built and maintained by dlazy (@dlazyai); the current version is v1.0.5.
More Skills