onescience-dataset-builder

onescience-dataset-builder is a skill for Claude Code, Codex from onescience-ai/OneSkills. It costs 138 tokens per session (1,809 once invoked), scanned A, original, MIT.

A workflow tool for building and checking scientific datasets. It can create a small startup script around existing data-processing code, then check the finished dataset and produce metadata.

In plain words
What is it for?
Use it to generate a script that loads dataset code and calls its build method, or to check a dataset’s completeness, format, and basic statistics. It can also create a dataset card, statistics, and information about dataset splits.
Why use it?
It removes the need to manually connect existing dataset code to a runnable script or perform basic checks by hand. It also separates dataset creation from dataset validation.

Skill for Claude CodeCodex

Part of the oneskills plugin — 18 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/onescience-ai/oneskills/onescience-dataset-builder
Any agent
npx skills add onescience-ai/OneSkills --skill onescience-dataset-builder
Clone the repo
git clone --depth 1 https://github.com/onescience-ai/OneSkills

Made for: Claude Code, Codex.

Or install oneskills, the plugin that ships this one along with the rest of its 18 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for onescience-dataset-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-dataset-builder.svg)](https://agentmods.dev/skills/onescience-ai/oneskills/onescience-dataset-builder)
Your own site
<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-dataset-builder"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-dataset-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00138 $0.01809
Opus 5 $0.00069 $0.00905
Sonnet 5 $0.00028 $0.00362
Haiku 4.5 $0.00014 $0.00181

Measured 5d ago against content hash af88767a9231, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onescience-dataset-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/onescience-dataset-builder/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 Dataset Builder

你是 OneScience 的数据集构建执行技能(type=executor)。你负责两个独立的任务,由 orchestrator 分别调用。

两个独立任务

任务1:生成数据集构建启动脚本

输入:orchestrator 传递的数据处理代码路径(核心处理逻辑已实现)

执行步骤:

  1. 从 orchestrator 接收数据处理代码路径(通过 resource_bindings
  2. 分析代码中的关键类和接口(数据集类、构建方法等)
  3. 确定输入数据路径(从 onescience.jsontask_context.input_data_hint 解析)
  4. 生成启动脚本(如 build_datasets.py),该脚本仅包含
    • sys.path.append 加载核心代码模块
    • import 导入数据集类
    • 创建数据集对象并传入参数
    • 调用构建接口
  5. 返回启动脚本路径给 orchestrator

任务2:验证构建好的数据集

执行步骤:

  1. 从 orchestrator 接收数据集路径(通过 task_context.dataset_path
  2. 执行质量检查(完整性、格式、基础统计)
  3. 生成数据集元数据(dataset_card、statistics、splits)
  4. 返回验证结果和元数据路径给 orchestrator

任务识别

根据 step_handoff.step_goal 判断执行哪个任务:

  • step_goal 包含 "生成"、"脚本"、"generate"、"script" → 任务1
  • step_goal 包含 "验证"、"检查"、"validate"、"verify" → 任务2
  • task_context 中存在 dataset_path 字段 → 任务2(已有数据集路径表示验证阶段)
  • 其他情况:根据 inputs 内容判断

工作流程

[任务1:生成脚本]
orchestrator 调用 dataset-builder (step_goal: 生成数据集构建脚本)
-> 解析输入数据路径(data_path_resolution.md)
-> 分析数据处理代码接口
-> 生成调用接口的脚本
-> 返回脚本路径

↓

orchestrator 调用 onescience-runtime 执行脚本
-> 生成数据集文件

↓

[任务2:验证数据集]
orchestrator 调用 dataset-builder (step_goal: 验证数据集)
-> 读取生成的数据集
-> 执行质量检查
-> 生成元数据
-> 返回验证结果

技能交接

输入契约(来自 orchestrator)

任务1:生成脚本

step_handoff:
  step_id: generate_dataset_script
  execution_skill: onescience-dataset-builder
  step_goal: 生成数据集构建脚本  # 关键字:生成/脚本
  task_context:
    user_goal: <用户最终目标>
    input_data_hint: <用户指定的输入数据路径,可选>
    output_path: <输出数据集路径>
  resource_bindings:
    - path: <data-profile 规划结果路径>
      type: processing_plan
    - path: <数据处理代码路径>
      type: code
  inputs:
    processing_plan: <来自 data-profile 的规划>
  required_outputs:
    - 数据处理脚本

Read the full file on GitHub · 201 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 201 lines · 138 tokens per session scan A af88767a9231

Subscribe to this mod's changes

onescience-dataset-builder is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 22d ago), licensed MIT. It adds 138 tokens to every session and 1,809 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

admet_genetic

ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.

PKU-YuanGroup/OpenAI4S · 63 tokens

bioprobench

Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.

PKU-YuanGroup/OpenAI4S · 46 tokens

sweep

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

Borda/AI-Rig · 45 tokens

analysis-workflow

Organize multi-step scientific analyses into reproducible, self-contained modules. Use for workflows such as QC→PCA→DEG→GSEA that produce scripts, inputs, figures, tables, and methods. Creates a stable module layout, records exact inputs/parameters/package and database versions in each module README, keeps large data…

xuzhougeng/wisp-science · 81 tokens

public-data-access

Plan, configure, validate, and document portable public-bioinformatics data acquisition. Use for GEO/GSE/GDS, SRA/ENA, TCGA/GDC, GTEx, DepMap, public expression matrices, raw reads, release files, manifests, resumable downloads, and reusable local caches. Keep the workflow provider-neutral: DepMap is one optional…

xuzhougeng/wisp-science · 83 tokens

bioinformatics-scientist

Use when a task needs the judgment of a Bioinformatics Scientist — designing a differential-expression or GWAS analysis with correct multiple-testing correction, calling and triaging variants from NGS data using genotype-likelihood confidence rather than raw allele counts, interpreting a BLAST/DIAMOND homology search…

wonsukchoi/domain-experts · 168 tokens