Creates research posters in LaTeX using beamerposter, tikzposter, or baposter. Use for conference posters, academic presentations, multi-column scientific layouts, figure integration, typography, compilation, and PDF preflight.
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow invokes a Python script (`scripts/generate_schematic.py`) that executes AI-driven image generation and review calls via OpenRouter API based on user-supplied prompts.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
An operational dependency on OpenRouter (`openrouter.ai`) is evidenced in the skill documentation and scripts, but OpenRouter is a commercial AI model gateway/transporter rather than the first-party publisher of the underlying models (`google/gemini-3.1-flash-image`, `google/gemini-3.7-flash`), making it a common/reputable unofficial operational dependency.
K-Dense-AI/scientific-agent-skills
a25cf9e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.