onescience-data-standardizer SKILL.md skillA
onescience-data-standardizer from onescience-ai/oneskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add onescience-ai/oneskills/onescience-data-standardizer@git:20261030.3665286Pins git:20261030.3665286 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- onescience-ai/oneskills
- Path
skills/onescience-data-standardizer/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261030.3665286, committed Oct 30, 2026
- First version recorded
- Sep 15, 2026
- Size
- 15,468 bytes
- Repository stars
- 24
- License
- MIT
OneScience 数据标准化执行技能（type=executor）。将原始数据集转换为 AI-Ready 数据集，覆盖 cfd / bio / climate(earth) / matchem 四个领域。目标契约从 onescience-primitives 的 dataset spec.md 拉取；数据源支持用户显式路径、本地自动探测与 ModelScope 下载三段式解析；转换采用 Tier1 确定性 adapter 与 Tier2 LLM 合成 converter 双层架构；所有处理在本地文件系统完成；产出统一注册到 ~/.onescience/data_management.json，并在宿主 Agent 提供 dataset_report 工具时自动上报 {name, target_dir, source_dir}。.
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
## 输入获取方式
本技能支持两种输入方式：
1. **上下文 handoff**（默认）：从调用方传入的 `step_handoff` 获取任务信息。
2. **文件 handoff**（autonomous_mode）：从 `.onescience/handoff/step_{step_id}.yaml`
读取任务信息。执行后，将结果写入 `.onescience/handoff/step_{step_id}_result.yaml`。
启动时优先检查 `.onescience/handoff/` 目录是否存在对应的交接文件；若存在则使用文件模式，否则使用上下文模式。
文件交接格式参见 `skills/onescience-orchestrator/references/file_handoff_contract.md`。
# OneScience Data Standardizer
你是 OneScience 的数据标准化执行技能（`type=executor`）。你的唯一职责是：**把原始数据集（raw dataset）在本地转换为 AI-Ready 数据集，并完成注册与上报**。
## 触发场景
当用户或上游提出以下类型请求时，应路由到本技能：
- 把某个原始数据集转换 / 标准化为 AI-Ready 格式，例如“帮我把 ${dataset_name} 数据集（领域 ${domain}）做成 AI-Ready 标准格式”。
- 给定原始数据路径与输出路径，要求产出统一 AI-Ready 目录结构（`data/` + `dataset_card.json` + `README.md`，可选 `static/` / `stats/` / `splits/`）。
- 要求把处理结果注册到数据管理清单（`~/.onescience/data_management.json`），并 / 或上报给宿主 Agent（`dataset_report`）。
- cfd / bio / climate(earth) / matchem 四域的数据集格式转换；本地无数据时先从 ModelScope 下载再转换。
- 为 primitives 未收录的自定义数据集现场合成转换脚本（Tier2 LLM converter）。
不要用本技能处理以下请求（应交对应 executor）：
- 仅生成数据集启动脚本 wrapper、或仅做数据集验证与质量检查 → `onescience-dataset-builder`。
- 训练模型、规划训练流程、生成训练脚本 → `onescience-trainer`。
…Read the whole file at its exact version.
How to install
mdr add onescience-ai/oneskills/onescience-data-standardizer@sha256:7eac2969439d9402The line at the top of this page pins the label git:20261030.3665286, 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_6jpdzsctkvf7dykc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 15, 2026 and Oct 30, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261030.3665286 latest | 2026-10-30 | 3665286 | 15,468 B | A | view · diff |
| git:20260915.3448d36 | 2026-09-15 | 3448d36 | 14,754 B | A | view · diff |
| git:20260915.0d033c1 | 2026-09-15 | 0d033c1 | 13,402 B | A | view |
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 (15468 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
onescience-ai/oneskills · 24 stars · license MIT · pushed 2026-11-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_6jpdzsctkvf7dykc GET https://markdownregistry.com/api/v1/resolve?ref=onescience-ai/oneskills/onescience-data-standardizer GET https://markdownregistry.com/api/v1/blob/7eac2969439d94026e627f1cbc0484b6ddd64d36091afe8885e9f6113947f60c
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.