experiment-track SKILL.md skillA
experiment-track from kendrick-stein/mcislab_deepread is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kendrick-stein/mcislab_deepread/experiment-track@git:20260428.bf023ecPins git:20260428.bf023ec in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kendrick-stein/mcislab_deepread
- Path
skills/3-experiment/experiment-track/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260428.bf023ec, committed Apr 28, 2026
- Size
- 6,722 bytes
- Repository stars
- 12
- License
- none declared
当 Supervisor 说"记录一下实验结果""实验跑完了"， 或 Researcher 完成一轮实验需要记录时， 在 Experiment 笔记中追加 Run Entry 并更新状态.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Purpose experiment-track 是 MindFlow 实验执行循环的记录层。每当一轮实验（training run、ablation、baseline 对比等）产出结果，该 skill 负责以 **append-only** 的方式将 Run Entry 写入目标 Experiment 笔记，并根据当前进展同步更新 frontmatter `status`。 核心设计原则：**只追加，不修改**。已有 Run Entry 和 Variables/Baseline/Metrics 等设计字段一律保持不变，确保实验记录的完整性和可追溯性。 ## Steps ### Step 1：读取目标 Experiment 笔记 用 Read 打开 `experiment` 参数指向的 `Experiments/xxx.md` 文件。重点提取以下字段： - `status`：当前实验状态（`planning` / `running` / `completed` / `failed`） - `variables`：实验变量（用于核对 Run Entry 中的 config 是否合理） - `metrics`：评估指标（用于核对 result 中上报的指标是否对齐） - 正文中已有的 `### Run [N]` 标题列表（用于计算新 Run 编号） - `## Analysis` 节是否存在（用于确定追加位置） 若文件不存在，停止执行并告知 Supervisor，不继续后续步骤。 ### Step 2：计算新 Run 编号 扫描已有的 `### Run [N]` 标题（N 为正整数）： - 若存在已有 Run Entry，新 Run 编号 = max(N) + 1 - 若尚无任何 Run Entry，新 Run 编号 = 1 记录新编号供下一步使用。 ### Step 3：追加 Run Entry 用 Edit 将 Run Entry 插入 Experiment 笔记，位置规则： - 若存在 `## Analysis` 节，将 Run Entry 追加在 `## Analysis` **之前** - 若不存在 `## Analysis` 节，追加到文件末尾 Run Entry 格式如下： ```markdown ### Run [N] — YYYY-MM-DD - **config**: <本次运行的关键超参数或配置差异，对照 variables 字段逐项说明> - **result**: <量化结果，务必包含 metrics 中定义的指标；可附路径指向日志或结果文件> - **observation**: <对结果的直接观察：是否符合预期？异常现象？与 baseline 的差距？> …
Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/experiment-track@sha256:621c2acae9753118The line at the top of this page pins the label git:20260428.bf023ec, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uxqowhsu4bi5gban)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Apr 28, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6722 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kendrick-stein/mcislab_deepread · 12 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uxqowhsu4bi5gban GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/experiment-track GET https://markdownregistry.com/api/v1/blob/621c2acae97531183ee337ad0c9e7525432ab6a5586d295668e63871ac50419d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.