autoskill
适合希望自动化日常研究流程并快速产出技能模板的研发人员。
需本地运行 screenpipe 并访问屏幕内容，存在隐私与安全风险。
通过本地 screenpipe 监控屏幕，检测重复流程并草拟或生成新技能。
监听本地的 screenpipe 屏幕流，自动识别你反复做的科研流程，并把这些模式和已有技能比对，草拟或生成新的技能或组合脚本。当你想让工具根据自己最近的实际操作提建议或把重复工作自动化时用。必须在本机运行 screenpipe（默认 http://localhost:3030），检测过程在本地完成，只有脱敏摘要会被上报，隐私友好。
▸ 展开 SKILL.md 英文原文
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
帮我安装这个 skill：https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/main/skills/autoskill/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/main/skills/autoskill/SKILL.md"# autoskill > **Requires a running [screenpipe](https://github.com/screenpipe/screenpipe) daemon.** This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http://localhost:3030`). If the daemon isn't running, `run()` raises `ScreenpipeUnreachable` with install instructions. > **Network access & environment variables.** This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http://localhost:1234/v1` (LM Studio, default), `https://api.anthropic.com` (opt-in Claude), or a user-supplied BYOK Foundry gateway. The skill reads three environment variab