Навыки nature-literature-pipeline
📦

nature-literature-pipeline

Ревизия содержимого r1 Безопасно 🌐 Доступ к сети⚙️ Внешние команды

Automate Your Research Literature Pipeline

Keeping current with research requires repeated searching, filtering, reading, and organizing. This skill defines a configurable workflow for recurring discovery, delivery, and archival.

Поддерживает: Claude Codex Code(CC)
🥉 78 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента
Review the Skillstore skill "nature-literature-pipeline" from https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline.md and its manifest at https://skillstore.io/api/skills/yuan1z0825-nature-literature-pipeline/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Протестировать

Использование «nature-literature-pipeline». Track machine learning methods for marine concrete durability during the last seven days.

Ожидаемый результат:

A ranked digest lists five deduplicated papers with scores, reading depth, methods, specific results, limitations, and stable source links.

Использование «nature-literature-pipeline». Check whether a four-component material system has been studied and document the search.

Ожидаемый результат:

  • A concise conclusion distinguishes a confirmed gap from partial overlap.
  • A subsystem table classifies direct, adjacent, and unrelated evidence.
  • A reproducibility section records search terms, sources, hit counts, and follow-up work.

Использование «nature-literature-pipeline». Prepare a reusable daily literature push for a research group.

Ожидаемый результат:

A configurable profile defines topics, exclusions, source priority, scoring weights, delivery target, archive settings, and a verification checklist.

Аудит безопасности

Безопасно

All 28 static detections are false positives caused by Markdown formatting, benign examples, ordinary prose, or UTF-8 Chinese text. No prompt injection, malicious execution instructions, credential exposure, or covert data transfer was found in the reviewed files.

12
Просканировано файлов
934
Проанализировано строк
0
Пункты проверки
0
Ложные срабатывания проигнорированы
Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.
Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет
Оценка безопасности

Копировать ссылку на отчёт

https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/yuan1z0825-nature-literature-pipeline/security.svg)](https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/yuan1z0825-nature-literature-pipeline/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/yuan1z0825-nature-literature-pipeline.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Академические ссылки (APA · BibTeX · CFF)

Цитата APA

yuan1z0825. (2026). nature-literature-pipeline security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline/audits/2

Цитата BibTeX

@techreport{yuan1z0825-yuan1z0825-nature-literature-pipeline-2026, author = {yuan1z0825}, title = {nature-literature-pipeline security audit report (audit version 2)}, institution = {Skillstore}, year = {2026}, number = {2}, url = {https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline/audits/2}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "nature-literature-pipeline security audit report (audit version 2)" version: "unspecified" type: report authors: - name: "yuan1z0825" date-released: "2026-08-18" url: "https://skillstore.io/skills/yuan1z0825-nature-literature-pipeline/audits/2" identifiers: - type: other value: "skillstore:yuan1z0825-nature-literature-pipeline:audit:2" description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний
59
Архитектура
85
Сопровождаемость
87
Контент
65
Сообщество
83
Соответствие спецификации

Что вы можете построить

Monitor a Research Topic

Create a daily or weekly digest of new papers for a defined topic, keyword set, and exclusion list.

Build a Team Reading Queue

Rank recent candidates and deliver focused summaries that help a research group select papers for deeper reading.

Map a Literature Gap

Search related systems, classify direct and adjacent evidence, and prepare a reproducible gap report for a new project.

Попробуйте эти промпты

Create a Basic Weekly Digest
Create a weekly literature pipeline for [topic]. Search [sources], review the last [days] days, and return the top [count] papers.
Configure Scoring and Delivery
Monitor [topic] using these keywords: [keywords]. Exclude [terms]. Score [candidate count] papers and deliver the top [final count] to [target].
Create a Verified Archive Workflow
Build a recurring pipeline for [topic]. Deduplicate by stable identifiers, label reading depth, archive raw notes under [path], and verify delivery separately.
Produce a Research Gap Report
Investigate whether [research question] is a documented gap. Search exact and adjacent terms across three sources. Record queries, evidence tiers, limitations, and next steps.

Лучшие практики

  • Review keywords and score distributions after several runs, then adjust weights with the user.
  • Label every paper as full text, abstract only, metadata only, or project page reviewed.
  • Verify scheduling, delivery, archival, deduplication, and failure alerts as separate stages.

Избегать

  • Do not treat a high score as proof of paper quality or relevance.
  • Do not claim full-text findings when only metadata or an abstract was available.
  • Do not place private chat identifiers, API keys, or machine-specific paths in shared templates.

Часто задаваемые вопросы

Which literature sources does this skill support?
It describes searches across arXiv, OpenAlex, Crossref, and optionally Semantic Scholar, with graceful degradation when a source is unavailable.
Does the skill create scheduled jobs by itself?
It provides scheduling prompts and verification guidance. Actual scheduling requires a compatible local scheduler and user configuration.
Can it send digests to messaging platforms?
Yes, when the agent has a configured messaging integration and an authorized destination such as Feishu or Telegram.
How does it prevent duplicate papers?
It compares DOI, arXiv ID, OpenAlex ID, and normalized titles before selecting and archiving papers.
What happens when full text is unavailable?
The workflow uses available abstracts or metadata and labels the reading depth so users can judge evidence quality.
Does the scoring system replace expert judgment?
No. The rubric prioritizes candidates, while researchers must verify relevance, methods, results, and citations.

Сведения для разработчиков

Автор

yuan1z0825

Лицензия

MIT

Ревизия Skillstore

r1

Примечание о версии

Автор не указал версию.

Ссылка

e22f0e5c175a84e01097fa734ec2a74420c14771

Актуальность поддержки

19.08.2026

Использование

0 загрузок · 0 просмотров