“systematic”的搜索结果

帮助在PubMed检索医学与生命科学文献，结合规范主题词和筛选条件构建检索式，获取摘要及书目信息，并整理可复现的检索记录，支持通过API持续跟踪文献。

• 查找研究主题相关的医学论文
• 按主题词和时间范围构建检索式
• 通过PMID获取摘要和书目信息

检索学术与技术文献，按预设标准筛选并综合比较。记录检索过程和排除理由，梳理研究分歧与未解问题，区分证据置信度并核查引用，形成可追溯的综述。

• 了解研究主题的整体情况
• 撰写记录检索步骤的文献综述
• 整理研究分歧与未解决问题

按顺序追踪按钮和表单操作引发的状态变化，排查共享状态被意外重置、异步处理竞争等导致界面行为异常的原因，并提出具体修复方案。

• 调查按钮无响应的原因
• 大规模重构后检查共享状态
• 发布前审查关键操作

先准备可重复复现症状的测试或命令，再按原因调查、正常示例对比、假设验证和修复四个阶段，定位根本原因并用回归测试验证结果。

• 调查测试或构建失败
• 排查跨多个系统的异常
• 复现间歇性缺陷

将颜色、间距和字体整理为共用的设计变量，生成CSS变量，定义界面组件在不同状态下的规范，检查代码中直接写入的值，并制作遵循同一品牌规则的HTML演示文稿。

• 统一颜色、间距和字体
• 整理按钮在不同状态下的规范
• 检查代码中直接写入的样式值

按调查、分析、假设、实现四个阶段追查错误和异常行为，确认根本原因后再修复；报告区分证据来源，并明确尚未验证的事项。

• 调查服务器错误的原因
• 根据堆栈跟踪追查原因
• 调查原本正常的功能为何停止

通过多个角度和网络来源研究主题，整理数据、实际案例、专家观点及比较材料。撰写文章或制作资料前，检查信息时效、不同意见与局限，为内容准备依据。

• 写文章前收集论据
• 为演示文稿收集数据与案例
• 比较技术用途及其局限

Breaks long-running goals into small, verifiable steps, tracks progress, and records evidence from actual operation. Checkpoints preserve what has been proven so work can resume after interruptions and continue toward explicit completion criteria.

中文简介正在准备中。当前显示英语简介。

• Managing a long-running development goal
• Resuming work after an interruption
• Recording evidence for completion criteria

Plan A/B tests to compare page changes using clear hypotheses and meaningful measures. The skill helps define sample size, duration, traffic allocation, and result interpretation, and organize a continuing program of prioritized experiments.

中文简介正在准备中。当前显示英语简介。

• Compare headlines or signup buttons
• Estimate test sample size and duration
• Interpret results and possible adverse effects

Plan and write literature reviews using multiple scholarly databases. Document searches, screen papers, synthesize findings, and check citations, then prepare Markdown or PDF reports with transparent selection counts, evidence limitations, and reproducible search records.

中文简介正在准备中。当前显示英语简介。

• Prepare a literature review for a thesis or research paper
• Record reproducible searches across scholarly databases
• Track screening decisions and exclusion reasons

Screen study titles, abstracts, and full texts against confirmed eligibility rules. Two AI reviewers assess records separately, with a third resolving conflicts, while outputs document exclusion reasons, selection counts, and the methods used.

中文简介正在准备中。当前显示英语简介。

• Define eligibility rules from a review protocol
• Screen titles, abstracts, and full texts
• Resolve conflicting screening decisions

Improve an existing AI agent by analyzing execution records, user feedback, and performance metrics. Refine prompts and workflows, compare original and revised versions through tests, and plan staged releases with monitoring and rollback when results worsen.

中文简介正在准备中。当前显示英语简介。

• Investigating recurring agent failures and user corrections
• Refining prompts, examples, and output formats
• Comparing original and revised agents with A/B tests

Explore a web application as a user to find reproducible bugs and usability problems. Produce a structured report with reproduction steps, screenshots, and videos for interactive issues, giving responsible teams concrete evidence to investigate.

中文简介正在准备中。当前显示英语简介。

• Checking a web app's quality before release
• Testing forms and common user workflows
• Finding confusing interfaces and visual problems

Improve existing code structure while preserving its behavior, using Martin Fowler's refactoring approach. Assess tests, identify structural problems, agree on a phased plan, and make small, tested changes with reversible commits and before-and-after comparisons.

中文简介正在准备中。当前显示英语简介。

• Splitting long functions into clearer responsibilities
• Removing duplicate or unused code
• Planning gradual improvements to legacy code

Identify security threats in system designs using STRIDE, a method covering six threat categories. Use structured questions to review components, prioritize threats by impact, and document findings and possible safeguards.

中文简介正在准备中。当前显示英语简介。

• Start a threat modeling session
• Review the security of an existing system design
• Document threats and possible safeguards

Investigate bugs and slow applications through reproducible examples, logs, environment comparisons, and hypothesis testing. The skill structures root cause analysis and performance measurement, helping developers narrow down failures and verify that a fix works.

中文简介正在准备中。当前显示英语简介。

• Investigate bugs that occur only occasionally
• Measure and locate performance bottlenecks
• Collect evidence and reproduce production failures

Review code changes through a structured check of requirements, design, correctness, security, performance, and tests. Produce specific, constructive feedback that separates required fixes from optional suggestions, and build shared review guidelines for a development team.

中文简介正在准备中。当前显示英语简介。

• Review a pull request systematically
• Create a shared code review checklist
• Give actionable feedback to junior developers

Design hands-on workshops with short explanations, immediate exercises, and quick self-checks. Use brief dialogue between a teacher and an assistant to guide practice, then finish with a small project that combines what learners have tried.

中文简介正在准备中。当前显示英语简介。

• Create a workshop built around hands-on practice
• Turn long explanations into short briefs and exercises
• Write guiding dialogue for a teacher and assistant

Find stock investment candidates by combining financial filters with research into investment themes. Produce five to ten long or short ideas, each with a rationale and risks, plus a comparison table and priorities for further research.

中文简介正在准备中。当前显示英语简介。

• Finding stocks that meet value, growth, or quality criteria
• Identifying companies that benefit from an investment theme
• Screening short candidates for business or accounting concerns

Build a competitive analysis presentation covering market context, company performance, strengths, and weaknesses. Compare competitors using consistent metrics, visualize their market positions, and summarize lasting advantages and structural risks for strategic or investment discussions.

中文简介正在准备中。当前显示英语简介。

• Mapping competitors and their market positions
• Comparing peer companies using shared metrics
• Preparing a strategic review presentation

Diagnose slow Power BI reports, data refreshes, and queries through structured measurement and troubleshooting. Get recommendations for data models, DAX calculation formulas, report layouts, and infrastructure, with guidance for validating improvements and ongoing monitoring.

中文简介正在准备中。当前显示英语简介。

• Diagnose slow report pages and visual interactions
• Investigate data refresh delays
• Review slow DAX calculations and queries

Compare project documentation with existing code to identify missing core features. Rank the gaps and create GitHub issues with practical specifications, implementation plans, acceptance criteria, effort estimates, and dependencies.

中文简介正在准备中。当前显示英语简介。

• Find documented features missing from the implementation
• Prioritize gaps in core product functionality
• Turn feature gaps into actionable GitHub issues

Review an AI workflow across five areas: prompts, use of context, tools, system structure, and safety. Receive scores, specific findings, and prioritized actions to address quality and reliability problems.

中文简介正在准备中。当前显示英语简介。

• Check an AI workflow before production use
• Audit an existing agent for quality and reliability
• Prioritize fixes for workflow problems

Check investment research for bias before searching and before writing conclusions. A short checklist broadens coverage beyond large companies and English sources, challenges bullish assumptions, and checks whether important figures are current.

中文简介正在准备中。当前显示英语简介。

• Include smaller companies and suppliers in stock screens
• Expand supply chain research to local language sources
• Test investment theses against opposing evidence