Agent skill

Scientific Tool Onboarding

by ZimoLiao in ZimoLiao/scholaraio

A skill your agent uses when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration…

MITAuto-check passedTesting & QA

Install Scientific Tool Onboarding

skills CLI
$ npx skills add ZimoLiao/scholaraio --skill scientific-tool-onboarding -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZimoLiao/scholaraio scientific-tool-onboarding --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZimoLiao/scholaraio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/scientific-tool-onboarding .claude/skills/scientific-tool-onboarding && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
scientific-tool-onboarding
GitHub stars
577
Token cost
~2k tokens
SKILL.md length
647 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration…

  • Works in 9 steps: 先过 2.x integration gate → 再定“官方真源” → 再定“接入粒度” → …
  • Upgrading ScholarAIO support for a scientific computing tool
  • SKILL.md covers Overview, When to Use, Core Workflow and Common Mistakes, plus 3 more sections
  • Calls git

What it does

Scientific Tool Onboarding is an agent skill from ZimoLiao/scholaraio. Use when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration, lightweight skill design, and end-to-end CLI verification.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. It works with Git. The repository describes itself as: Scholar All-In-One: A research infrastructure for AI agents. The licence is MIT.

When your agent uses it

  • Upgrading ScholarAIO support for a scientific computing tool
  • Especially integration-gate review
  • Official docs ingestion
  • Toolref integration

Example prompts

  • “/scientific-tool-onboarding”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. 先过 2.x integration gate
  2. 再定“官方真源”
  3. 再定“接入粒度”
  4. 先做最小 manifest / parser,不要一上来追求全量
  5. TDD 先测 parser 和鲁棒性边角
  6. 实现 fetch/index/show/search 全链路
  7. 必须做“真实使用体验”验证
  8. 再把对应 skill 改成轻量 toolref-first
  9. 最后做发布门槛检查

What it can do on your machine

Read from SKILL.md and the folder at commit 777628b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scientific Tool Onboarding loads about 2k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 647 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZimoLiao/scholaraio at commit 777628b, republished under its MIT licence (© ZimoLiao). 647 words, ~2,013 tokens.

Download SKILL.mdSave it as .claude/skills/scientific-tool-onboarding/SKILL.md (or your agent's skills folder).
name
scientific-tool-onboarding
description
Use when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration, lightweight skill design, and end-to-end CLI verification.

Scientific Tool Onboarding

Overview

先判断一个科学工具是否值得进入 ScholarAIO;只有通过 2.x integration gate 后,接入目标才是形成这三个层次的闭环,而不是“写一份长教程”:

  • toolref 能查官方接口和参数
  • 对应 skill 能指导 agent 何时使用、如何验证
  • CLI 在真实使用中足够稳,不只是测试能过

规范参考:

When to Use

适用于:

  • 新增一个科学计算工具到 scholaraio toolref
  • 升级某个工具的官方文档源或版本策略
  • 发现现有 scientific skill 过重,需要改成 toolref-first

不适用于:

  • 只写一篇一次性笔记
  • 只修一个小 typo

Core Workflow

0. 先过 2.x integration gate

不要因为用户提到一个项目、它很热门,或官方文档可抓取,就默认把它接入 ScholarAIO。先逐项确认:

  • 它解决的是已经出现的核心学术任务,而不是增加一个新的平台类别
  • 当前 agent 原生能力与已有 ScholarAIO 路径不能充分完成这个任务
  • 没有另一套重叠适配器在做同一件事,并且有明确维护责任
  • 依赖、凭据和运行时可以保持可选并与 core install 隔离
  • 可以设计固定语料或端到端 smoke 来证明用户任务确实改善
  • 缺凭据、断网、上游漂移或服务不可用时,能给出可执行错误或 fallback

任何一项不满足时,优先采用外部 recipe、用户自管工具或 sidecar;不要继续下面的内置接入流程。升级既有工具时也要重新过门,不因历史存在而自动保留。

1. 再定“官方真源”

优先级:

  • 官方文档站
  • 官方源码仓库中的文档目录
  • 官方维护的 README / man page / PDF

不要优先用:

  • 博客
  • 第三方教程
  • 论坛帖子

要求:

  • 记录文档 URL、版本策略、格式(RST / HTML / man / Markdown / PDF)
  • 判断适合 git 抓取还是 manifest 抓取

经验判断:

  • 如果官方文档天然按源码版本演进、结构稳定、页面很多,优先 git
  • 如果官方文档是独立文档站、页面总数可控、但抓取噪音和网络波动明显,优先 manifest
  • 不要为了“理论更完整”强行选 git;用户在乎的是 agent 能不能顺手查到
  • 如果文档站有“总目录页 / 命令索引页 / 手册页目录”,优先把它作为自动发现种子,而不是手写所有子页面

当前项目里的经验:

  • QE / LAMMPS / GROMACS 更适合 git + parser
  • OpenFOAM / Bioinformatics 更适合 manifest + curated entry pages
2. 再定“接入粒度”

问自己三个问题:

  • 用户会按什么名词来查:求解器、命令、参数、字典、子工具?
  • page_name 应该怎么命名,未来最稳?
  • program / section / title 该怎样存,show/search 才顺手?

经验规则:

  • page_name 要服务 CLI 使用体验,不要只服务抓取方便
  • 一个大页面如果天然包含很多独立参数,应该拆页
  • 如果工具本来就是多子工具工具链,允许一个 top-level tool 下挂多个 program
  • program 要优先贴近用户会说出的名字,而不是内部类名或目录名
  • section 要反映用户排查问题时的思路,例如 solver / dictionary / variant-calling

从现有工具得到的粒度经验:

  • QE:程序名 + namelist + 参数名,这样 show qe pw ecutwfc 才顺
  • LAMMPS:命令家族一定要做 alias 聚合,不然 fix npt 这种自然输入会漂走
  • GROMACS:mdp 参数页必须尽量保留 options,不然会变成只有变量名的空页
  • OpenFOAM:不要一上来想抓完整站点,先抓 solver / dictionary / post-processing 关键页
  • Bioinformatics:要承认它是 toolchain,不是单软件;先解决“路由到哪个子工具”

当目标从“最小可用”升级到“主体尽量全量”时:

  • 不要继续人工堆 manifest
  • 要升级成“seed pages -> automatic discovery -> snapshot manifest -> fetch/index”
  • 对于单页大手册,要优先考虑按 anchor / heading 拆成逻辑页
3. 先做最小 manifest / parser,不要一上来追求全量

先做高价值页面:

  • 最常用求解器或主程序
  • 最关键配置字典或参数页
  • 最关键模型页
  • 1-2 个典型后处理或分析页

先让 list/show/search 真正可用,再扩充覆盖率。

停止条件也要明确:

  • 如果高频真实查询已经稳定命中正确页,就不要为了“全站完整”无限扩张
  • “生产级”不等于“把官网每一页都搬下来”
  • 对 manifest 工具,优先做到“关键入口完整 + 网络失败不回退成残废状态”

如果用户明确要求“主体尽量全量”:

  • 先定义主线边界,再自动扩展
  • 例如:OpenFOAM 主体文档可以包含 fundamentals / tools 主线,但排除插件、挂件、开发者扩展
  • 例如:Bioinformatics 工具链可以扩展官方子命令页、章节页、命令手册锚点,但不要把随机第三方生态也拖进来
4. TDD 先测 parser 和鲁棒性边角

最低应有测试:

  • 解析器能提取 title / synopsis / content
  • 版本或 program 规范化逻辑
  • top-level scholaraio.stores.toolref 入口在内部重构后仍保持兼容
  • manifest 工具的“是否完整”判断
  • 失败后残缺目录不会被误判成已完成
  • 用户自然说法对应的 alias / query expansion
  • 缓存保留和 fallback URL 行为(如果是 manifest 工具)
  • 自动发现规则(如果是 discovery-based manifest)
  • anchor / heading 切片逻辑(如果是单页大手册拆分)
  • meta.json、manifest 快照、SQLite 索引和 toolref list 展示口径一致

如果没有先看到失败场景,就不知道这个工具接入点真正脆不脆。

如果这次工作包含 toolref 内部重构或拆包,必须额外补这类兼容测试:

  • import scholaraio.stores.toolref 后旧调用路径仍可用
  • 顶层兼容 patch 点仍能影响真实行为
  • CLI 不需要知道内部模块名变化
  • 旧缓存数据库在新 schema / trigger 下不会损坏或重复触发
5. 实现 fetch/index/show/search 全链路

最低要求:

  • fetch 能拉取并落盘
  • list 能看到版本和页数
  • show 能按用户自然输入命中
  • search 能搜到高价值页面

重点防御:

  • 网络失败后的残缺目录
  • manifest 页面部分失败
  • program 名规范化不一致
  • 页面命名和用户输入不一致
  • 同一概念的不同人话表达
  • 主入口页失效后没有降级路径
  • 包拆分后顶层兼容 facade 失效
  • fetch、index、list 的计数口径漂移

manifest 工具的额外要求:

  • 对高价值但不稳定的页面,允许配置 fallback_urls
  • force refresh 不能把旧缓存中仍然可用的页面冲掉
  • meta.json 要能说清楚:预期页数、失败页数、恢复自缓存的页数
  • 自动发现得到的 manifest 必须落盘成快照,不能每次都重新“猜”一遍
  • 发现阶段已经拿到的 HTML,正式抓取时应直接复用,避免二次下载
  • 当外站超时但本地已有种子页缓存时,应该允许“用缓存继续做结构发现”
  • 如果逻辑页来自单页手册的 anchor,正式抓取时要允许 #anchor 页面复用其基础 URL 的种子 HTML
  • 预置高价值页名不一定等于真实 heading id;发现阶段要把真实 anchor 元数据回填到这些规范化 page_name
  • toolref list 不能盲信过期 meta.json;必要时要与快照和实际索引自校准
  • fetch 返回的索引数量要和最终库里的真实可查询条目数一致,而不是解析中间态数量
6. 必须做“真实使用体验”验证

不能只跑测试。必须像用户一样手动执行:

bash
scholaraio toolref fetch <tool>
scholaraio toolref list <tool>
scholaraio toolref show <tool> <natural query>
scholaraio toolref search <tool> "<real query>"

检查:

  • show 命中的是不是用户想看的页面
  • 正文前是不是被导航噪音淹没
  • synopsis 有没有信息量
  • 首次失败后,第二次 fetch 是否会卡在脏目录
  • 搜索是不是只“有结果”,还是首条结果就是对的
  • 结果标题是不是能让用户一眼知道为什么它是对的
  • 如果是工具链型工具,用户的描述能不能先路由到对的 program
  • fetch 报的页数/条目数,和 list 看到的最终数值是否一致
  • manifest 工具在旧缓存存在时,list 会不会出现自相矛盾的显示
  • 对外入口是否仍然只需要 scholaraio toolref ...,而不是内部模块命令

如果手感不好,就继续打磨 CLI;不要因为测试是绿的就停。

至少要抽查这三类真实查询:

  • 参数名式:如 ecutwfc
  • 自然语言式:如 drag coefficient、v-rescale thermostat
  • 任务导向式:如 read mapping nanopore、variant calling vcf

如果做了“主体尽量全量”的扩展,还要加两类检查:

  • 扩展后的总页数是否显著增加,而不是只换了实现没换覆盖面
  • 扩展后 show/search 的核心路径是否仍然稳定,没有被噪音页挤掉
Show full SKILL.md (261 more words)Show less
7. 再把对应 skill 改成轻量 toolref-first

对应 scientific SKILL.md 应只保留:

  • 何时使用
  • 高层工作流
  • 科学规范
  • toolref 查询入口
  • agent 行为准则
  • 覆盖缺口时如何退化处理

不要把 skill 写成第二份 API 手册。

分工应始终是:

  • skill = 路由 + 方法论 + 验证规范
  • toolref = 官方接口与参数
  • scientific-runtime = 运行时退化与用户体验协议

不要把内部包结构泄漏到 skill:

  • skill 和用户文档应该引用 scholaraio toolref ...
  • 如果确实需要提 Python API,引用顶层 scholaraio.stores.toolref
  • 不要把 fetch.py / manifest.py / storage.py 之类内部模块写成公开入口
8. 最后做发布门槛检查

一个新工具只有同时满足下面几条,才算真正接入完成:

  • 官方文档已入 toolref
  • fetch/list/show/search 都能真实使用
  • 至少有基础 parser 测试
  • 对应 skill 已改成轻量 toolref-first
  • 至少手动体验过一次端到端 CLI
  • 如果做过内部重构,顶层兼容入口也已验证

如果你要判断“是否已经够生产,不要再打磨了”,就看这几条:

  • 高频 show 查询能直接命中
  • 高频 search 查询 rank 1 基本正确
  • 本地重抓后不会把覆盖率越抓越差
  • agent 不需要再让用户帮它维护文档
  • 即使覆盖有缺口,runtime fallback 也能继续完成任务
  • fetch/list 的统计口径不会把用户带沟里

满足这些,就应该把精力转回 demo 和真实科研任务,而不是继续无止境磨 toolref

Common Mistakes

  • 没过 integration gate 就因为热度或用户随口提及而新增内置支持
  • 把 agent 已有的原生能力在 ScholarAIO 里重复实现一遍
  • 让可选集成进入 core install,或在不可用时拖垮核心工作流
  • 只看测试,不自己用 CLI
  • 第一次抓取失败后没处理脏目录
  • page_name 为抓取方便而设计,导致 show 很难用
  • 内部拆包后忘了保护 scholaraio.stores.toolref 顶层兼容面
  • 把 scientific skill 写成超长命令手册
  • 新 skill 没有写清楚覆盖缺口时 agent 应如何继续服务用户
  • 用第三方教程代替官方文档
  • 把“能跑起来”误当成“生产级”
  • 把“manifest 页数 100%”误当成“用户体验 100%”
  • 忘记给易失联页面准备 fallback
  • 工具链型工具没有先做路由,直接把所有子工具混在一起搜
  • fetch、数据库真实条目数、和 list 展示数字彼此不一致

What The Current Five Tools Taught Us

QE
  • 机器可解析的结构化文档价值极高
  • program + section + variable 粒度一旦对了,show 体验会非常稳
LAMMPS
  • alias 是生产级体验的核心,不是装饰
  • 用户说 fix npt,show 必须能稳稳落到 fix_nh,search 至少要把 fix_nh 放进最前排结果
GROMACS
  • 参数页不能只有变量名,必须保住 options 和代表性说明
  • 排名正确不够,页面内容也要足够回答问题
OpenFOAM
  • 不要妄图第一次就镜像整站
  • 先抓高价值入口页,配合好的 search alias,就能把体验快速拉起来
  • 自动发现不应该把 curated 高价值入口覆盖掉;应该是扩充或升级它们
  • 当用户真的要求“主体尽量全量”时,正确升级路径是:
    • 从官方主线文档页自动发现
    • 只保留主体路径
    • 把发现结果快照化
    • 用快照驱动后续抓取和页数判断
Bioinformatics
  • 首先要解决“这是哪一个子工具的问题”
  • manifest 工具一旦跨多个站点,fallback 和缓存保留机制就不是可选项
  • 单页大手册常常比“单独 man page 仓库”更有结构价值
  • 对 samtools / bcftools / iqtree 这类工具,应该利用官方总目录页、命令索引、章节 anchor 自动扩页
  • 网络不稳时,已有缓存不只是兜底数据,也应该成为 discovery 的输入
  • 高价值规范名和真实 anchor id 可能不一致,例如用户会更自然地说 ultrafast-bootstrap,但上游文档的实际锚点可能是 ultrafast-bootstrap-parameters

Production-Ready Mindset

面向 ScholarAIO 用户时,要始终记住:

  • 用户不是来帮我们修 toolref 的
  • 新工具接入的目标是让 agent 更自主,而不是把复杂性重新转嫁给用户
  • 最终标准不是“代码优雅”或“页数很多”,而是 agent 是否真的更顺手、更可靠地完成科学任务
  • 但如果用户明确要求更完整覆盖,就应该把“自动发现 + 快照 + 缓存复用 + 锚点拆页”做成正式能力,而不是继续靠人工列清单

Quick Checklist

  • 已逐项通过 2.x integration gate
  • 已确认没有 agent 原生能力或现有适配器能够充分替代
  • 依赖与凭据保持可选、隔离,失败时有 actionable fallback
  • 官方文档源已确认
  • 版本策略已确认
  • 解析粒度已确认
  • parser 测试已写
  • 顶层兼容入口已验证
  • fetch/list/show/search 已手动体验
  • 残缺目录问题已验证
  • 高价值自然语言查询已验证
  • fetch/list 计数口径已核对
  • 如果有网络脆弱页面,fallback 已验证
  • 如果是 discovery 型 manifest,快照写入与复用已验证
  • 如果是单页大手册拆分,anchor 页面 show/search 已验证
  • 对应 skill 已改成轻量结构
  • 新 skill 与 scientific-runtime 协议兼容
  • 最终再跑一次相关测试与 CLI smoke

© ZimoLiao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/scientific-tool-onboarding of ZimoLiao/scholaraio.

Open the folder on GitHubat commit 777628b

Compare with similar skills

Scientific Tool Onboarding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Scientific Tool Onboarding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scientific Tool Onboarding this skillZimoLiao/scholaraio577—~2kAutomated safety check: PassMIT
OpenHarness End-to-End EvalsHKUDS/OpenHarness16k1 repos~2.1kAutomated safety check: NotesMIT
Evaluate PR Testsdotnet/maui23k—~2.9kAutomated safety check: PassMIT
TiDB Test Diff Triagepingcap/tidb41k—~498Automated safety check: PassApache-2.0
SimpleITK Binary Data UploadSimpleITK/SimpleITK1.1k—~1.9kAutomated safety check: PassApache-2.0
Nemoclaw Maintainer Fix E2E FailuresNVIDIA/NemoClaw23k—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

    16k GitHub starsUsed in 1 repo~2.1k tokens
    Testing & QAAuto-check: notes
  • Official

    Reviews the tests added in a pull request for fix coverage, quality, edge cases and test type, and recommends lighter test types where they would do.

    23k GitHub stars~2.9k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Investigates TiDB plan or test-result diffs that the change does not explain, ruling out failpoint setup and merge effects before expected outputs are updated.

    41k GitHub stars~498 tokensUpdated today
    Testing & QAAuto-check passed
  • SimpleITK Binary Data Upload

    SimpleITK/SimpleITK

    Uploads a binary test file to the SimpleITK ExternalData repository by hashing it with SHA-512, staging it in the object store, writing a content-link file and opening a draft PR.

    1.1k GitHub stars~1.9k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Official

    Continuously maintain automatic NemoClaw main E2E results through coordinated repairs.

    23k GitHub stars~2.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Playwright Component Testing

    mellowagain/gitarena

    Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime.

    115 GitHub starsUsed in 1 repo~2.6k tokens
    Testing & QAAuto-check passed

More from ZimoLiao/scholaraio

All 43 skills in this repo
  • Document

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to create or inspect DOCX, PPTX, or XLSX files, generate a downloadable Office deliverable, or verify its structure and layout warnings with scholaraio…

    577 GitHub stars~674 tokensUpdated 15 days ago
    Auto-check passed
  • Academic Writing

    ZimoLiao/scholaraio

    A skill your agent uses when the user needs help choosing or organizing an academic-writing workflow by deliverable, stage, or format, including review articles, guided reading, paper sections, PPT…

    577 GitHub stars~827 tokensUpdated 15 days ago
    Auto-check passed
  • Arxiv

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to browse arXiv preprints, search arXiv directly, fetch a PDF by arXiv ID or URL, or send a preprint into the ScholarAIO ingest pipeline.

    577 GitHub stars~799 tokensUpdated 15 days ago
    Auto-check passed
  • Bioinformatics

    ZimoLiao/scholaraio

    A skill your agent uses when working on bioinformatics workflows such as alignment, variant calling, phylogenetics, or protein-structure analysis, especially across BLAST, minimap2, samtools…

    577 GitHub stars~1.4k tokensUpdated 15 days ago
    Auto-check passed
  • Citation Check

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to verify citations in AI-generated or human-written text against the local knowledge base and catch hallucinated, wrong, or missing references.

    577 GitHub stars~454 tokensUpdated 15 days ago
    Auto-check passed
  • Draw

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants diagrams, flowcharts, architecture visuals, data relationships, timelines, concept maps, Mermaid, Graphviz, drawio, or polished paper figures generated…

    577 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check: notes

Works with

Categories

Questions about Scientific Tool Onboarding

What does Scientific Tool Onboarding do?

A skill your agent uses when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration…. Scientific Tool Onboarding is an agent skill from ZimoLiao/scholaraio. Use when evaluating, adding, or upgrading ScholarAIO support for a scientific computing tool, especially integration-gate review, official docs ingestion, toolref integration, lightweight skill design, and end-to-end CLI verification.

When should I use Scientific Tool Onboarding?

Scientific Tool Onboarding fits situations like: upgrading ScholarAIO support for a scientific computing tool; especially integration-gate review; official docs ingestion; toolref integration.

How do I install Scientific Tool Onboarding in Claude Code?

Run `npx skills add ZimoLiao/scholaraio --skill scientific-tool-onboarding -a claude-code`. Or copy the skill folder (.claude/skills/scientific-tool-onboarding in ZimoLiao/scholaraio) into .claude/skills/scientific-tool-onboarding in your project. Claude Code loads it when a task matches its description.

How do I install Scientific Tool Onboarding in Codex?

Run `npx skills add ZimoLiao/scholaraio --skill scientific-tool-onboarding -a codex`. Or copy the skill folder (.claude/skills/scientific-tool-onboarding in ZimoLiao/scholaraio) into .agents/skills/scientific-tool-onboarding in your project. Codex loads it when a task matches its description.

Can I use Scientific Tool Onboarding in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZimoLiao/scholaraio --skill scientific-tool-onboarding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scientific-tool-onboarding, .gemini/skills/scientific-tool-onboarding, .github/skills/scientific-tool-onboarding and .opencode/skills/scientific-tool-onboarding in your project.

What does Scientific Tool Onboarding need to run?

Going by SKILL.md and its folder, Scientific Tool Onboarding needs the command-line tools its instructions call (git). Our summary lists: Python 3.

Does Scientific Tool Onboarding access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scientific Tool Onboarding safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Scientific Tool Onboarding use?

Scientific Tool Onboarding is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scientific Tool Onboarding use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Scientific Tool Onboarding?

Skills that share tags, products or a category with Scientific Tool Onboarding: OpenHarness End-to-End Evals (HKUDS/OpenHarness, 16k stars), Evaluate PR Tests (dotnet/maui, 23k stars), TiDB Test Diff Triage (pingcap/tidb, 41k stars) and SimpleITK Binary Data Upload (SimpleITK/SimpleITK, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scientific Tool Onboarding?

ZimoLiao (a GitHub user) maintains it in ZimoLiao/scholaraio, which has 577 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on September 25, 2026.

Source: ZimoLiao/scholaraio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.