跳到正文
cccskills
免费在 GitHub 公开

demo

Run and explain the RuField deterministic synthetic benchmark and local sensing dashboard. Use for a RuField demo, quickstart, benchmark baseline, or viewer smoke test.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md1.7 KB
  • agents/openai.yaml196 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Run a RuField demo

  1. Locate the user's RuField checkout, then read its Cargo.toml and README.md. Confirm crates/rufield-bench and crates/rufield-viewer exist. The plugin installation directory is not the source checkout. If no checkout exists, ask for its path or clone https://github.com/ruvnet/rufield into a new directory only when requested. Never overwrite an existing checkout.
  2. From that checkout run cargo run --locked -p rufield-bench -- 2026 --json and cargo test --locked -p rufield-bench. Preserve the actual exit status and measured values. These results are SYNTHETIC conformance, not physical sensor accuracy. Timing varies; do not require byte identical timing values across runs.
  3. When a dashboard is requested, run cargo run --locked -p rufield-viewer -- --source synthetic --port 8088 using a managed process. Use another available local port if needed. Verify /health, /api/source, and /api/run at http://127.0.0.1:8088, then inspect the page and confirm the SYNTHETIC banner. Stop only the process you started after a smoke test, or leave it running if the user requested an interactive demo and report how to stop it.
  4. Report the revision, seed, commands, exit codes, measured report, and any unexecuted checks. Keep raw sensor data local. Do not enable live sources, enroll keys, publish a service, or imply hardware validation as a side effect of a demo.

Acceptance: benchmark tests pass, JSON parses, and the requested viewer endpoints respond with synthetic source state.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

audit

免费

Audit RuField tests, trust boundaries, privacy projections, and evidence promotion. Use for conformance review, security regression review, release validation, or checking whether field accuracy claims have support.

中文简介正在准备中。当前显示原文说明。

ruvnet/rufield392026年10月14日 更新

replay

免费

Validate RuField CSI or ultrasonic recording replay and its fusion boundary. Use for captured CSI JSONL, BatVu ultrasonic replay, replay adapter integration, or replay regression diagnosis.

中文简介正在准备中。当前显示原文说明。

ruvnet/rufield392026年10月14日 更新

查看 ruvnet 的全部技能

报告此技能的问题