一键导入
uv-scripts
Create and run Python helper scripts for Fae using uv — workspace-local, deterministic, auditable utilities for one-off tasks.
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。
菜单
Create and run Python helper scripts for Fae using uv — workspace-local, deterministic, auditable utilities for one-off tasks.
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.
Extract training signals from Fae's memory — SFT examples, DPO correction pairs, engagement scores, and interest-weighted sampling.
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.
| name | uv-scripts |
| description | Create and run Python helper scripts for Fae using uv — workspace-local, deterministic, auditable utilities for one-off tasks. |
| metadata | {"author":"fae","version":"1.0"} |
Use this skill when you need to write small Python helpers to extend Fae's capabilities for one-off tasks — data transforms, repo maintenance, utilities — without modifying Fae itself.
uv run --script for deterministic, reproducible execution..fae/python/..faerc/python/
pyproject.toml # Project metadata + dependencies
uv.lock # Locked dependency versions
scripts/
<name>.py # Individual helper scripts
Set up (first time only):
.fae/python/scripts/ if it doesn't exist..fae/python/pyproject.toml with [project] metadata.uv --directory .fae/python sync to materialise the environment.Write a script at .fae/python/scripts/<name>.py:
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.12"
# dependencies = ["httpx"]
# ///
"""One-line description."""
import json
import sys
def run(params: dict) -> dict:
# TODO: implement
return {"ok": True, "result": "..."}
if __name__ == "__main__":
request = json.loads(sys.stdin.read())
print(json.dumps(run(request.get("params", {}))))
Execute via the bash tool:
uv --directory .fae/python run python scripts/<name>.py -- <args>
Or with a frozen lockfile:
uv --directory .fae/python run --frozen python scripts/<name>.py
Add dependencies:
uv --directory .fae/python add httpx
uv --directory .fae/python lock
uv --directory .fae/python sync --frozen
sys.stdin.read()). Expect {"params": {...}}.print(json.dumps(...))).{"ok": false, "error": "..."} on stdout.input() or other interactive functions.read_write tool mode (Fae can use read and edit tools).full tool mode (needs bash).If uv is not available, ask for explicit user approval first, then:
curl -LsSf -o /tmp/uv-install.sh https://astral.sh/uv/install.sh
sh /tmp/uv-install.sh --install-dir ~/.local/bin
macOS default curl is fine. Always prefer a pre-installed uv over bootstrapping.