onescience-trainer SKILL.md skillA
onescience-trainer 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-trainer@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-trainer/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261030.3665286, committed Oct 30, 2026
- First version recorded
- Jul 22, 2026
- Size
- 13,636 bytes
- Repository stars
- 24
- License
- MIT
OneScience 科学模型训练执行技能。用于用户希望基于文本说明、网页说明、本地项目路径、已有 checkpoint 或项目原生训练入口来规划、生成并执行模型训练工作流，覆盖气象/地球系统、生信、材料、流体和通用科研模型等领域，包括训练信息获取、数据与切分规划、训练策略整理、完整训练脚本内容生成、训练执行组织以及结果验证。接收格式与 onescience-orchestrator 调用执行技能时的 step_handoff 保持一致，返回 execution_result。需要时协调交接给 onescience-coder、onescience-runtime 以及数据工作流技能。.
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 Trainer
## 职责
将本技能作为科学模型训练任务的执行工作流。把 orchestrator 交给本技能的当前步骤，例如“根据网页说明生成训练脚本”“基于已有 checkpoint 继续训练”“按文本给定的数据与优化器约束生成微调入口”“整理训练计划并提交训练”，转化为从训练信息获取到结果验证的可追踪闭环。
本技能只消费当前执行步骤，不重新规划完整用户目标。本技能负责训练工作流契约和阶段顺序，负责明确训练策略、数据配置、split 假设、loss、optimizer、scheduler、评测频率、checkpoint 策略、日志与验证要求等完整训练脚本内容；这些内容由 trainer 直接定义并保留在 trainer_workdir 中。训练执行阶段的外层控制、入口确定、预检要求和结果归因也由 trainer 负责。只有当这些已定义内容需要写入仓库、修改现有项目文件或对接项目原生目录结构时，才把当前步骤中的文件落盘子动作交接给 `onescience-coder`。依赖包、硬件和运行环境需求不单独成阶段，而是在训练执行阶段通过 `onescience-runtime` 统一处理。
## 工作流
先继承会话和 handoff 的执行范围、已有连续执行授权、输出目录及禁止事项。用户禁止训练或
`execution_flags.training_allowed=false` 时，只完成所需计划/代码和获准检查，阶段 5 不执行
训练、参数更新、训练 dry-run 或作业提交，阶段 6 只验证实际交付，不生成训练指标。
论文任务以原始用户要求和上游唯一 `reproduction_spec.md` 为科学依据；通用训练建议不能覆盖
该规格或填补其未决项。缺口按目标实验/阶段交回 paper-repro，从官方 GitHub 只读补证后更新
…Read the whole file at its exact version.
How to install
mdr add onescience-ai/oneskills/onescience-trainer@sha256:42d67b88f0a05389The 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_h2hgv32ilmwr6a22)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 22, 2026 and Oct 30, 2026, about one every 33 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261030.3665286 latest | 2026-10-30 | 3665286 | 13,636 B | A | view · diff |
| git:20260814.1419d1c | 2026-08-14 | 1419d1c | 12,016 B | A | view · diff |
| git:20260728.0404723 | 2026-07-28 | 0404723 | 11,411 B | A | view · diff |
| git:20260722.c51b8b7 | 2026-07-22 | c51b8b7 | 10,242 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 (13636 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_h2hgv32ilmwr6a22 GET https://markdownregistry.com/api/v1/resolve?ref=onescience-ai/oneskills/onescience-trainer GET https://markdownregistry.com/api/v1/blob/42d67b88f0a05389874d53a104cc5e0210fd4f8bb560345501c6631ee25b938e
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.