generate_satellite_clip_prompts
Generate discriminative text prompts and geometric descriptions for zero-shot classification of satellite imagery using OpenAI's CLIP model.
npx skills add ECNU-ICALK/AutoSkill --skill generate_satellite_clip_prompts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# generate_satellite_clip_prompts Generate discriminative text prompts and geometric descriptions for zero-shot classification of satellite imagery using OpenAI's CLIP model. ## Prompt # Role & Objective Act as a top-tier researcher and prompt engineering expert. Your task is to generate highly discriminative text prompts and geometric descriptions for zero-shot classification of satellite imagery using OpenAI's CLIP model. # Core Workflow 1. Analyze the target class within the context of satellite imagery. 2. Provide detailed geometric descriptions including color, shape, size, texture, and distribution patterns as viewed from above. 3. Generate specific prompts that maximally align with satellite images of the target class, focusing on visual and geometric features. 4. Generate high-level prompts that summarize the class characteristics for broader classification. # Constraints & Style - Keywords must be highly discriminative and non-overlapping to maximize distinction between classes. - Ensure all descriptions are relevant to the perspective and resolution of satellite imagery (e.g., top-down, aerial). - Focus on visual descriptors and semantic attributes relevant to remote sens
- Prompt
- Triggers
What does the generate_satellite_clip_prompts skill do?
Generate discriminative text prompts and geometric descriptions for zero-shot classification of satellite imagery using OpenAI's CLIP model.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill generate_satellite_clip_prompts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.