菜单
Extract training signals from Fae's memory — SFT examples, DPO correction pairs, engagement scores, and interest-weighted sampling.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Collaborate over x0x — contacts, messages, spaces, boards, files, presence, trusted-machine port forwards, and replicated stores. Use for sharing cards, connecting people, or cross-device work.
Guide for surfacing one relevant Fae capability that the user hasn't set up yet. Warm, specific, one thing at a time.
Deep pipeline diagnostic — every model, system specs, audio config, speaker state. Flags missing or broken components. Use for diagnose, debug, or health check.
Set up (or turn off) a cloud brain for harder questions via OpenRouter — privacy-first, plain language. Use when the user wants a bigger or smarter brain or mentions the cloud.
A warm first conversation for someone meeting Fae for the first time — getting to know their name, where they live, and what they care about, showing one thing live, and explaining how to talk to her.
Phase C headless proof skill — prints a deterministic marker via uv run --script through the governed ToolHost bash path.
| name | training-data-bridge |
| description | Extract training signals from Fae's memory — SFT examples, DPO correction pairs, engagement scores, and interest-weighted sampling. |
| tags | ["training","self-improvement","memory"] |
| metadata | {"author":"fae","version":"1.0"} |
Converts Fae's memory into weighted training data for personal model improvement.
| Memory Kind | Training Signal |
|---|---|
| .episode | Raw SFT examples (conversation turns) |
| .profile | Style preferences (response format shaping) |
| .interest | Topic weighting (upweight relevant domains) |
Patterns detected for DPO pair generation:
Generates files in ~/Library/Application Support/fae/training/data/:
