← Back to Skills Marketplace
Tpt Generate Cover
by
kakazhang50
· GitHub ↗
· v1.0.0
604
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tpt-generate-cover
Description
Generate a TPT cover using the AI Studio DinoCover tool and save it locally with the book title as filename.
Usage Guidance
This skill will launch a browser profile named 'geminibuild' that must already be logged into Google, and it will read/write files in specific local folders (E:\AI\openclaw-tpt\...). The registry metadata does not declare those config paths or the need for a logged-in profile — that's an inconsistency. Before installing or running: (1) verify the geminibuild profile is dedicated and contains no sensitive personal or organizational data (use a throwaway or limited account if possible); (2) confirm the input/output paths are correct and contain only intended files; (3) run the skill in an isolated VM or dedicated workspace if you worry about exposing Google session cookies or Drive access; (4) ask the skill author to update metadata to list required config paths and to document precisely what the agent will access; and (5) if you cannot verify those things, treat the skill as untrusted and avoid exposing high-value accounts or data to it.
Capability Analysis
Type: OpenClaw Skill
Name: tpt-generate-cover
Version: 1.0.0
This skill involves significant capabilities, including browser automation to interact with a Google AI Studio tool, uploading local files, and downloading generated content. It also performs local file system operations (reading input TXT/PNGs from `E:\AI\openclaw-tpt\input\` and writing output PNGs to `E:\AI\openclaw-tpt\output\COVER\`). While `SKILL.MD` includes explicit safety boundaries, the use of user-provided input (TITLE from the TXT file) for filename generation without explicit sanitization presents a path traversal vulnerability. The combination of browser control and file system access, coupled with the prompt-driven nature of the AI agent, creates a substantial attack surface for potential prompt injection to override safety instructions or exploit file system vulnerabilities, classifying it as suspicious.
Capability Assessment
Purpose & Capability
The declared purpose (use AI Studio DinoCover to create a cover) aligns with the runtime steps (open DinoCover URL, upload reference images, read local TXT, fill fields, download output). However the skill requires use of a persisted browser profile ('geminibuild') with an active Google login and specific local paths (E:\AI\openclaw-tpt\...), yet the registry metadata lists no required config paths, env vars, or credentials — this mismatch is unexpected and should be declared.
Instruction Scope
SKILL.md instructs the agent to launch a browser with profile 'geminibuild', open a Google AI Studio URL, upload images from a local input folder, read the latest TXT file to extract title and content, and save a generated PNG to a specified output folder. Those file reads/writes and use of a logged-in browser session are within the feature's functional scope, but they involve access to local files and to a Google-authenticated browser profile (cookies/session tokens). The instructions explicitly forbid logging in or handling MFA, but they still rely on a pre-authenticated profile — this is sensitive and should be explicitly declared in the metadata and documentation.
Install Mechanism
No install spec or code is present; the skill is instruction-only. This minimizes supply-chain risk because no external binaries or archives are fetched by the skill itself.
Credentials
The skill requires access to a persisted Google login via a browser profile and to specific local filesystem paths, but the registry metadata lists no required environment variables, credentials, or config paths. Requesting access to an authenticated browser profile effectively grants access to Google account session tokens and possibly Drive data; such sensitive access should be explicitly declared and justified. Also the hard-coded Windows paths (E:\...) reduce portability and imply the agent will access those exact locations.
Persistence & Privilege
The skill is not marked always:true and does not request persistent installation or modify other skills. It operates per-invocation and requires human hand-off conditions for login/MFA/captchas, which reduces autonomous risk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tpt-generate-cover - After installation, invoke the skill by name or use
/tpt-generate-cover - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of tpt-generate-cover skill.
- Automates TPT cover creation using the AI Studio DinoCover tool with local file inputs and outputs.
- Uses an existing logged-in Google account via the "geminibuild" browser profile.
- Uploads reference PNG images and parses TXT files for title and story context.
- Downloads and saves generated covers to a specified output folder, naming them after the book title.
- Includes clear stop conditions for handling authentication or tool errors.
Metadata
Frequently Asked Questions
What is Tpt Generate Cover?
Generate a TPT cover using the AI Studio DinoCover tool and save it locally with the book title as filename. It is an AI Agent Skill for Claude Code / OpenClaw, with 604 downloads so far.
How do I install Tpt Generate Cover?
Run "/install tpt-generate-cover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Tpt Generate Cover free?
Yes, Tpt Generate Cover is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Tpt Generate Cover support?
Tpt Generate Cover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Tpt Generate Cover?
It is built and maintained by kakazhang50 (@kakazhang50); the current version is v1.0.0.
More Skills