← Back to Skills Marketplace
128
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install story-to-prompts
Description
Convert story synopses or single-scene descriptions into high-quality text-to-image prompts. Two modes: (1) multi-scene - a story outline is split into multi...
Usage Guidance
This skill is instruction-only and internally consistent with its purpose: it generates multi- or single-scene text-to-image prompts and includes local reference files. It asks for no credentials or installs. Things to consider before installing: (1) the skill will output final prompts directly without asking follow-up questions — if you need clarification first, ask the skill to pause or provide explicit instructions in your prompt; (2) do not paste secrets or private data into text you plan to convert into prompts (those words will appear verbatim in outputs); (3) generated prompts may include style keywords that implicitly reference artists or copyrighted aesthetics — check licensing/usage policies of downstream image-generation services you plan to use.
Capability Assessment
Purpose & Capability
Name/description (story -> text-to-image prompts) matches the instructions and included reference files. No unrelated binaries, env vars, or credentials are requested.
Instruction Scope
SKILL.md confines runtime behavior to parsing user text, splitting scenes, and producing bilingual prompts scored/optimized per its spec. It does not instruct reading system files, environment variables, or contacting external endpoints. The references are local files bundled with the skill.
Install Mechanism
No install spec and no code files beyond markdown references — nothing is written to disk or downloaded during install. Lowest-risk install footprint.
Credentials
The skill requests no environment variables, credentials, or config paths. All declared requirements are minimal and proportionate to converting story text into prompts.
Persistence & Privilege
always is false and disable-model-invocation is default (agent may invoke autonomously, which is normal). The skill does not request permanent system presence or to modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install story-to-prompts - After installation, invoke the skill by name or use
/story-to-prompts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
SKILL.md fully rewritten in English for better LLM comprehension. Output language still auto-detected from user input.
v1.1.0
1. description 改为英文便于国际发现\n2. 新增输出语言自动判断\n3. 双语输出标记主语言/附带语言
v1.0.0
Initial release: 故事梗概/单场景→文生图prompt，支持多场景拆分、评分优化、中英文双语输出
Metadata
Frequently Asked Questions
What is Story to Prompts?
Convert story synopses or single-scene descriptions into high-quality text-to-image prompts. Two modes: (1) multi-scene - a story outline is split into multi... It is an AI Agent Skill for Claude Code / OpenClaw, with 128 downloads so far.
How do I install Story to Prompts?
Run "/install story-to-prompts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Story to Prompts free?
Yes, Story to Prompts is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Story to Prompts support?
Story to Prompts is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Story to Prompts?
It is built and maintained by ggKe (@ggke); the current version is v1.2.0.
More Skills