Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

consort-check配偶检查

Agent Skill

consort-check 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

524

周安装

21

GitHub Stars

76

下载量

170
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:consort-check(配偶检查)
来源仓库:https://github.com/htlin222/dotfiles
仓库路径:skills/consort-check
安装命令:
npx skills add https://github.com/htlin222/dotfiles --skill consort-check
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/htlin222/dotfiles --skill consort-check

简介

CONSORT 2025 合规检查器审计随机对照试验手稿是否符合最新临床试验报告标准。

  • 适用于医学研究、临床数据分析及学术出版准备等专业场景,确保符合国际规范。
  • 通过 GitHub 安装并使用 npx skills add 命令添加,依据 30 项清单逐条核验内容完整性。
  • 输出为结构化评分与缺失项列表,不能替代同行评审或期刊具体要求。
  • consort-check 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

CONSORT 2025 Compliance Checker

Audit randomized controlled trial manuscripts against the CONSORT 2025 (Consolidated Standards of Reporting Trials) 30-item checklist. Published April 2025, supersedes CONSORT 2010.

What Changed from CONSORT 2010

  • 7 new items added (data sharing, conflicts of interest, PPI, site eligibility, harms assessment, analysis population, intervention delivery)
  • 3 items revised (protocol access, post-commencement changes, missing data)
  • 1 item deleted (generalisability — now incorporated into Limitations, item 30)
  • New Open Science section (items 2-5)
  • Renumbered throughout (do NOT use CONSORT 2010 numbering)

Workflow

  1. Read the full manuscript
  2. Confirm the study is a randomized trial; identify design (parallel, factorial, crossover, cluster)
  3. Walk through each item below
  4. For each item, assign: Reported / Partial / Missing / N/A
  5. Quote the relevant manuscript text as evidence
  6. Output a compliance summary + actionable fixes
  7. Check for CONSORT flow diagram (strongly recommended)

CONSORT 2025 Checklist (30 Items)

Title and Abstract

#TopicRequirement
1aTitleIdentification as a randomised trial in the title
1bAbstractStructured summary of trial design, methods, results, and conclusions

Open Science (NEW section)

#TopicRequirement
2Trial registrationRegistry name, identifying number with URL, and registration date
3Protocol and SAP accessWhere the trial protocol and statistical analysis plan can be accessed
4Data sharingNEW. Where and how de-identified participant data (including data dictionary), statistical code, and other materials can be accessed
5aFundingSources of funding and other support; role of funders in design, conduct, analysis, reporting
5bConflicts of interestNEW. Financial and other conflicts of interest of the manuscript authors

Introduction

#TopicRequirement
6Background/rationaleScientific background and rationale based on existing evidence
7ObjectivesSpecific objectives related to benefits and harms, using PICO framework

Methods

#TopicRequirement
8Patient/public involvementNEW. Details of patient or public involvement in the design, conduct, and reporting of the trial
9Trial designType of design (parallel, crossover, factorial, etc.), allocation ratio, framework (superiority, non-inferiority, equivalence)
10Protocol changesREVISED. Important changes to the trial after commencement, with reasons and timing
11Trial settingSettings and geographical locations where the trial was conducted
12aParticipant eligibilityEligibility criteria for participants
12bSite/provider eligibilityNEW. Eligibility criteria for sites and individuals delivering interventions
13InterventionsSufficient details to allow replication; how and when administered; access to intervention manuals/materials
14OutcomesPre-specified primary and secondary outcomes: measurement variables, analysis metrics, aggregation methods, timepoints
15Harms assessmentNEW. How harms were defined and assessed (systematically vs non-systematically)
16aSample sizeHow sample size was determined, with all supporting assumptions
16bInterim analysesExplanation of interim analyses and stopping guidelines
17aRandomisation — sequenceWho generated sequence; method used
17bRandomisation — typeType of randomisation; details of restriction (stratification, blocking)
18Allocation concealmentMechanism to implement allocation sequence; steps taken to conceal until assignment
19ImplementationWhether personnel accessing the allocation sequence could foresee assignment
20aBlinding — whoWho was blinded after assignment (participants, care providers, outcome assessors)
20bBlinding — howHow blinding was achieved; description of similarity of interventions
21aStatistical methodsMethods for comparing groups for primary/secondary outcomes and harms
21bAnalysis populationNEW. Definition of who is included in each analysis and how group assignment was handled
21cMissing dataREVISED. How missing data were handled in the analysis
21dAdditional analysesMethods for subgroup and sensitivity analyses, distinguishing pre-specified from post hoc

Results

#TopicRequirement
22aParticipant flowFor each group: numbers randomised, received intervention, analysed. Flow diagram strongly recommended
22bLosses/exclusionsLosses and exclusions after randomisation, with reasons
23aRecruitment datesPeriods of recruitment and follow-up for outcomes of benefits and harms
23bTrial terminationWhy the trial ended or was stopped
24aIntervention deliveryNEW. Intervention and comparator as actually administered, including fidelity
24bConcomitant careCare received during the trial for each group
25Baseline characteristicsTable of baseline demographic and clinical characteristics for each group
26OutcomesNumbers analysed, available data, results per group, effect sizes with confidence intervals
27HarmsAll harms or unintended events in each group
28Ancillary analysesOther analyses performed, distinguishing pre-specified from post hoc

Discussion

#TopicRequirement
29InterpretationInterpretation consistent with results, balancing benefits and harms, considering other evidence
30LimitationsREVISED. Trial limitations: bias, imprecision, generalisability, and multiplicity of analyses (generalisability now incorporated here; was a separate item in 2010)

Critical CONSORT 2025 Elements

Must-HaveWhy
Flow diagram (22a)Journals typically will not review without one
Trial registration (2)Mandatory for ICMJE journals; prospective registration expected
Randomisation details (17-19)Core of trial integrity reporting
Sample size (16a)Reviewers check this immediately
Analysis population / ITT (21b)Must define who is included and how; state ITT or per-protocol
Harms (15, 27)Both assessment method AND results now required
Data sharing (4)New open science requirement; increasingly mandated

Common CONSORT 2025 Gaps

Frequently MissingFix
Item 4 (Data sharing)State data availability policy; provide repository URL or explain restrictions
Item 5b (Conflicts)Add explicit COI disclosure for each author
Item 8 (PPI)Describe patient involvement or state "No patient or public involvement"
Item 12b (Site eligibility)State criteria for site and provider selection
Item 15 (Harms assessment)Describe how AEs were defined, collected, and classified
Item 21b (Analysis population)State ITT/mITT/per-protocol explicitly; define who was included
Item 21c (Missing data)Describe imputation or complete-case approach
Item 24a (Intervention delivery)Report fidelity and actual administration vs protocol

Output Format

CONSORT 2025 Compliance Report
Trial design: [Parallel / Factorial / Crossover / Cluster]
Manuscript: [filename]

Summary: X/30 Reported | Y Partial | Z Missing | W N/A

CRITICAL MISSING (journal will likely reject):
  [Item #] [Topic] — [What's needed]

NEW ITEMS IN 2025 (check carefully):
  [Item #] [Topic] — [Status]

OTHER MISSING:
  [Item #] [Topic] — [What's needed]

PARTIAL ITEMS:
  [Item #] [Topic] — [What's present] → [What's missing]

Flow diagram: [Present / Missing]
Trial registration: [Registered (ID) / Not registered / Not stated]
Data sharing statement: [Present / Missing]

Related Skills

  • /manuscript — Overall manuscript writing and anti-pattern scanning

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.04%
按下载量换算56

Claude

29.13%
按下载量换算50

Cursor

19.14%
按下载量换算33

Gemini CLI

9.64%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills