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 skills add onescience-ai/OneSkills --skill onescience-primitive-distillergit 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-primitive-distiller)<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-primitive-distiller"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-primitive-distiller/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-primitive-distiller"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-primitive-distiller.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.03288 |
| Opus 5 | $0.00038 | $0.01644 |
| Sonnet 5 | $0.00015 | $0.00658 |
| Haiku 4.5 | $0.00008 | $0.00329 |
Grade A, and why
onescience-primitive-distiller 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 3d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneScience Primitive Distiller
你是 OneScience 的原语蒸馏执行技能(type=executor)。你的职责是把外部科研 agent skill 或第三方科研能力材料,标准化为 onescience-primitives 可以检索、绑定、规划和交接的 primitive 资产包。
本技能解决的是体系整合,不是目录合并。默认产物是 resource 级 primitive;只有当执行边界、输入输出、环境和验证方式都足够稳定时,才建议提升为 executor;只有当需要复杂取舍、领域决策和 fallback 时,才建议提升为 expert。
触发场景
使用本技能处理以下请求:
- 将
scientific-agent-skills/skills/<name>蒸馏到skills/onescience-primitives/assets/。 - 把第三方科研包、CLI、SDK、数据库、服务、数据集、输出格式或工作流经验注册为 OneScience primitive。
- 评估一个外部 agent skill 应落地为 primitive、expert、executor,还是拆成多个对象。
- 为已有 primitive 补齐
primitive_id、provider、provenance、requirements、contracts 或依赖关系。
不要用本技能执行真实科研分析、训练、推理、HPC 提交、报告生成或代码重构。这些任务应交给对应的 executor。
输入格式
primitive_distillation_request:
source:
kind: agent_skill | upstream_docs | third_party_tool | database | service | dataset | output_format | workflow
location: <source path, repo locator, URL, or supplied text>
name: <source capability name>
target:
domain: <bio | cfd | climate | matchem | general>
category: <tools | databases | datasets | services | output-format | workflow-planning | application | models | components | datapipes | contracts | visualization>
primitive_name: <lower_snake_case or existing primitive directory name>
options:
distillation_status: resource_only | resource_with_execution_assets | propose_expert | propose_executor | split
copy_knowledge_references: true
copy_execution_assets: false
update_consumers: true
缺少 target 时,先根据来源内容给出保守分类建议;能稳定判断时直接创建 resource 级 primitive 草案,不能稳定判断时返回需要用户确认的候选分类。
工作流程
-
Inventory
- 读取来源
SKILL.md、frontmatter、When to use、workflow、examples、references manifest、scripts manifest 和 assets manifest。 - 只在确实需要蒸馏执行资产时检查脚本和模板内容;默认不复制脚本。
- 读取来源
-
Classify
- 第三方包、CLI、SDK、HPC 软件、实验室工具 ->
tools。 - 数据库、知识库、API 数据源 ->
databases。 - 数据集、benchmark、标准样本集 ->
datasets。 - 云平台、远程计算、实验接口 ->
services。 - docx、pdf、pptx、表格、图件等交付形态 ->
output-format。 - 可复用路线、决策树、fallback ->
workflow-planning。 - 面向任务的工具组合和模板集合 ->
application。 - 输入输出 schema、handoff、验证规则 ->
contracts。
- 第三方包、CLI、SDK、HPC 软件、实验室工具 ->
What ships with it
15 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.
- assets/materialize_plan.example.json 494 B
- assets/next_batch_2026-09-07.json 2.3 KB
- assets/next_batch_2026-09-07b.json 2.4 KB
- assets/next_batch_2026-09-07c.json 2.2 KB
- assets/next_batch_2026-09-07d.json 2.1 KB
- assets/next_batch_2026-09-08a.json 2.2 KB
- assets/next_batch_2026-09-08b.json 2.1 KB
- assets/next_batch_2026-09-08c.json 2.4 KB
- assets/next_batch_2026-09-08d.json 2.5 KB
- assets/next_batch_2026-09-08e.json 1.8 KB
- assets/next_batch_2026-09-08f.json 1.9 KB
- references/primitive_bundle_and_flow.md 3.7 KB
- scripts/build_skill_migration_manifest.py 22 KB runs code
- scripts/distill_skill_batch.py 4.1 KB runs code
- scripts/materialize_skill_primitives.py 33 KB runs code
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.
- 3d ago First seen · 238 lines · 76 tokens per session scan A 1ea8bcacae69
onescience-primitive-distiller is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 3,288 once invoked, about $0.0004 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 2026-09-07.
Other skills, from other repositories
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
paper-select-journal
A workflow for choosing suitable SCI journals for a scientific manuscript. It reviews the paper, filters possible journals using impact-factor data, and checks journal scope and recent publications.
nsfc-budget
A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.
research-literature-radar
A research workflow for finding, judging, classifying, tracking, and archiving important research papers. It treats bioRxiv and similar sources as places where researchers share papers, and combines database searches with other discovery signals.
paper-search
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.