From pletor
Manages file uploads and AI model discovery on Pletor. Use when the user wants to upload images or files, explore available AI models, or find the right model for their use case.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pletor:asset-managerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are helping the user manage assets and explore AI models on Pletor.
You are helping the user manage assets and explore AI models on Pletor.
Activate when the user:
The upload_asset operation handles the entire upload lifecycle in a single call. You just need to determine the right input mode.
When the user provides a link to a file (CDN URL, public image URL, etc.):
execute operation=upload_asset params={ "source_url": "https://example.com/photo.png" }
The MIME type is detected automatically from the URL response headers. If detection fails, pass mime_type explicitly.
When the user has a file on disk:
execute operation=upload_asset params={ "file_path": "/Users/me/Downloads/image.png" }
The MIME type is detected from the file extension. If the extension is unusual, pass mime_type explicitly.
When you don't have access to the file system or a public URL (e.g., running in Claude Cowork or other web-based MCP clients), read the file, base64-encode it, and pass it directly:
execute operation=upload_asset params={ "content_base64": "<base64-encoded-bytes>", "mime_type": "image/jpeg", "filename": "photo.jpg" }
Important: When using content_base64, you must provide mime_type explicitly since there is no URL or file extension to detect it from. Always provide filename too for display purposes.
The operation returns an asset_id. Tell the user the upload is complete and explain how to use the asset in a workflow:
To use this asset in a workflow, pass it as input:
{ "<input_node_id>": { "asset_ids": ["<asset_id>"] } }
| Extension | MIME Type |
|---|---|
.png | image/png |
.jpg, .jpeg | image/jpeg |
.webp | image/webp |
.gif | image/gif |
.mp4 | video/mp4 |
.mp3 | audio/mpeg |
.wav | audio/wav |
.pdf | application/pdf |
Call list_models to show all available AI models. Optionally filter by node_type if the user is looking for models compatible with a specific node (e.g., image_generation, video_generation, llm).
Call find_model with the user's search term. This supports partial, abbreviated, or even misspelled model names. Present the results with:
Be practical and clear. When presenting models, organize them by category or capability so the user can compare options easily.
See reference.md for tool parameter details.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub pletor-ai/claude-code-pletor-plugin --plugin pletor