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.
npx agentmods add skills/onescience-ai/oneskills/onescience-dataset-buildernpx skills add onescience-ai/OneSkills --skill onescience-dataset-buildergit clone --depth 1 https://github.com/onescience-ai/OneSkillsWrote 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.
[](https://agentmods.dev/skills/onescience-ai/oneskills/onescience-dataset-builder)<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>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.
| Model | Per session | Once 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 |
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.
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:
- 上下文 handoff(默认):从调用方传入的
step_handoff获取任务信息。 - 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:
- 从 orchestrator 接收数据处理代码路径(通过
resource_bindings) - 分析代码中的关键类和接口(数据集类、构建方法等)
- 确定输入数据路径(从
onescience.json或task_context.input_data_hint解析) - 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
- 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:
- 从 orchestrator 接收数据集路径(通过
task_context.dataset_path) - 执行质量检查(完整性、格式、基础统计)
- 生成数据集元数据(dataset_card、statistics、splits)
- 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1step_goal包含 "验证"、"检查"、"validate"、"verify" → 任务2task_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
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.
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.
- 5d ago First seen · 201 lines · 138 tokens per session scan A af88767a9231
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.
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.
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.
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.
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…
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…
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…