← Back to Skills Marketplace
105
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install seedream-ppt-maker
Description
Seedream图片PPT制作器 - 宝玉布局框架 + Seedream 5.0文生图,自动生成图片PPT。支持交互式分步确认流程,减少反复修改节省API配额。
Usage Guidance
What to consider before installing:
- Functionality: This skill sends your content and generated prompts to Volcengine's Seedream API (ark.cn-beijing.volces.com) to create images and then downloads them to assemble a PPT. If your content is sensitive, do not upload it to the API.
- API key: You must add your Volcengine API key into ~/.openclaw/config.json under "volces": {"apiKey": "..."}. The skill metadata did not declare this requirement — make sure you understand and trust the endpoint before providing the key.
- Runtime test: check_install.py will attempt a live API call when run; this will consume quota if the key is valid. Run it locally and inspect outputs first.
- Code quality: interactive.py contains a likely syntax bug (an unquoted identifier 'kpi' used in a literal list), which can raise an exception or break the interactive flow. Expect the interactive pathway to possibly fail; the direct one-shot script (baoyu_seedream_ppt.py) appears runnable.
- Safety/practical steps: review the files locally, back up your ~/.openclaw/config.json before editing, set strict filesystem permissions on that file, and run check_install.py in a controlled environment. If you want to avoid sending sensitive data, use a throwaway API key or redact content before generation.
- If uncertain: prefer to run the one-shot script with a small test document to confirm behavior, or inspect/patch interactive.py to fix the bug before using interactive mode.
Capability Analysis
Type: OpenClaw Skill
Name: seedream-ppt-maker
Version: 1.1.0
The skill bundle is a legitimate tool designed to generate PowerPoint presentations using the Seedream 5.0 image generation API and the Baoyu layout framework. The code in 'baoyu_seedream_ppt.py' and 'interactive.py' aligns with the stated purpose, using standard libraries like 'python-pptx' and 'requests'. It accesses '~/.openclaw/config.json' to retrieve API keys, which is the standard configuration pattern for this platform, and communicates only with the official Volcengine API endpoint (ark.cn-beijing.volces.com). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the implementation: the code calls a Seedream (Volcengine) image API and assembles a PPT using baoyu-infographic templates. However the registry metadata declares no required env/config for credentials, while runtime explicitly requires a Volcengine API key stored in ~/.openclaw/config.json (volces.apiKey). That omission in metadata is an incoherence users should know about.
Instruction Scope
SKILL.md instructs the agent/user to store an API key in ~/.openclaw/config.json and to run check_install.py which itself will perform a live test API call. The code sends user-provided content and generated prompts to an external endpoint (https://ark.cn-beijing.volces.com/api/v3) — expected for image generation but important: user content (potentially sensitive) will be transmitted off-machine. The interactive flow code is intended to solicit confirmations, which limits accidental exfiltration, but that flow contains a coding error (see below) that may break or alter behavior.
Install Mechanism
There is no network install script; the package is instruction/code-only and relies on python3, requests, and python-pptx. No third-party archives or obscure download URLs are used by the skill itself. It does instruct use of clawhub to install baoyu-infographic which is expected.
Credentials
The skill requires a Volcengine (火山方舟) API key at runtime, but the skill registry metadata does not declare any required env vars — a mismatch. Aside from the API key, no unrelated credentials or paths are requested. The check_install script prints the first 20 chars of the API key to console, which may be an information leak in shared environments.
Persistence & Privilege
The skill does not request elevated or permanent privileges (always:false). It reads/writes under its own output directory and ~/.openclaw/config.json for the API key; it does not modify other skills or global agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install seedream-ppt-maker - After installation, invoke the skill by name or use
/seedream-ppt-maker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
**Major update: Adds interactive step-by-step confirmation process for generating image-based PPTs, reducing repeated edits and saving API quota.**
- New interactive generation workflow: analyzes content, recommends layout/style, previews prompts, and confirms at each step.
- Supports quick one-click generation for simple needs or predefined styles.
- Documentation expanded with detailed usage instructions, trigger phrases, and configuration steps.
- Provides style recommendations for different presentation scenarios.
- Dependencies and API key setup instructions clarified.
Metadata
Frequently Asked Questions
What is Seedream Ppt Maker?
Seedream图片PPT制作器 - 宝玉布局框架 + Seedream 5.0文生图,自动生成图片PPT。支持交互式分步确认流程,减少反复修改节省API配额。 It is an AI Agent Skill for Claude Code / OpenClaw, with 105 downloads so far.
How do I install Seedream Ppt Maker?
Run "/install seedream-ppt-maker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Seedream Ppt Maker free?
Yes, Seedream Ppt Maker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Seedream Ppt Maker support?
Seedream Ppt Maker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Seedream Ppt Maker?
It is built and maintained by Cindypapa (@cindypapa); the current version is v1.1.0.
More Skills