Summary
If you're building anything with Apple's on-device 3B parameter LLM that shipped at WWDC 2025, this is your complete API reference in skill form. It covers the entire Foundation Models framework with all the code examples from the sessions. The real value is having the specs and limitations right there while you work: 4096 token context window, 2-bit quantized, good for summarization and classification but explicitly not for math or world knowledge. Saves you from constantly switching to documentation tabs when you're trying to figure out what this thing can actually handle on an iPhone.
Install to Claude Code
npx -y skills add charleswiltgen/axiom --skill axiom-foundation-models-ref --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
