Visual Essay Engine
v1.0.5Transform AIGC images into a structured visual essay with narrative sequencing, bilingual captions, artist statements, and Instagram-ready packaging.
⭐ 0· 331·0 current·0 all-time
byMiLab@milab-bit
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (structuring AIGC images into a visual essay) match the provided prompts, examples, and templates. The SKILL.md, PROMPTS.md, EXAMPLES.md, and TEMPLATES.md all focus on producing series titles, narrative arcs, bilingual captions, artist statements, posting order, and hashtag frameworks — exactly what the description promises.
Instruction Scope
All instructions are content-generation prompts and examples for composing captions, narrative architecture, and packaging. There are no instructions to read system files, environment variables, or external configuration, nor to send data to hidden endpoints. The skill expects image inputs (e.g., 9 AIGC images) but provides no guidance that would cause the agent to access unrelated system data.
Install Mechanism
There is no install spec and no code files — this is instruction-only. Nothing will be written to disk or downloaded by the skill itself, so install mechanism risk is minimal.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate to a prompt-based content-structuring utility that does not integrate with third-party APIs or services.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or elevated privileges. Autonomous model invocation remains allowed by platform default, but the skill itself does not request or require 'always: true'.
Assessment
This skill is instruction-only and appears internally consistent with its stated purpose. If you install it, note that: (1) it only provides prompts and templates — it will not itself post images or captions to social platforms unless you (or another enabled skill) instruct the agent to do so; (2) any image data you feed the agent may be processed by whatever LLM or tooling the agent uses — avoid supplying private or sensitive images unless you trust that environment; (3) review and, if needed, adapt the PROMPTS.md to match your tone/brand and to ensure it doesn't accidentally produce copyrighted or sensitive text. No environment credentials or installs are required, so the technical risk is low.Like a lobster shell, security has layers — review code before you run it.
latestvk975xpvxb1nmvnm1kzt81c5mwx827nms
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis