// Add non-text files to a person's artifacts folder. Use when saving images, documents, or other files related to someone. Trigger words: artifact, save image, add photo, attach file, store document.
| name | artifact |
| description | Add non-text files to a person's artifacts folder. Use when saving images, documents, or other files related to someone. Trigger words: artifact, save image, add photo, attach file, store document. |
Add images, documents, or other non-text files to a person's artifacts folder.
Parse the input: Extract person name and file path
/artifact lucy ~/Downloads/chess-game.png → name: "lucy", file: "~/Downloads/chess-game.png"/artifact e ~/Desktop/project-notes.pdf → name: "e", file: "~/Desktop/project-notes.pdf"Verify person exists:
ls ~/.claude-mind/memory/people/{name}/
If not, ask whether to create them first.
Ensure artifacts directory exists:
mkdir -p ~/.claude-mind/memory/people/{name}/artifacts
Copy the file:
cp "{source_path}" ~/.claude-mind/memory/people/{name}/artifacts/
Preserve the original filename unless there's a conflict.
Optionally add context note: Ask if the user wants to add a note about this artifact to the profile
Confirm: Report success and the artifact's new location
Simple storage:
/artifact cal ~/Downloads/system-diagram.png
→ Copies to memory/people/cal/artifacts/system-diagram.png
With context:
/artifact e ~/Pictures/beach-sunset.jpg
→ Copies file, then asks "Want to add a note about this photo?"
Natural trigger:
"Save this screenshot to Dawn's folder"
→ Copies screenshot, prompts for context
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
ASI Agent-O-Rama Skill
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
Personal assistant for daily routines, task management, and productivity
Coordinate Claude Code skills with OpenAI Codex autonomous workflows for end-to-end ATFT-GAT-FAN maintenance.