“agent-skill”的搜索结果

记录软件设计决策的理由及比较过的方案，整理README、API文档和变更日志，帮助后来加入的成员与AI智能体理解实现背景。

• 记录设计决策和未采用方案
• 记录公开API的变更
• 完善README的启动步骤

检查Web应用的输入处理、身份验证和外部集成，梳理漏洞应对措施，并涵盖依赖包、个人信息及LLM输出的处理方式。

• 检查登录流程和访问权限
• 检查文件上传与外部API集成
• 发布前审计依赖包

在生产发布前检查质量、安全、性能、无障碍和基础设施，准备监控与回滚方案，并根据发布后的检查结果、运行指标和可靠性目标逐步扩大开放范围。

• 检查首次生产发布的准备情况
• 规划重大功能的分阶段发布
• 整理监控项目与发布后检查步骤

将项目质量标准及其数值、理由和检查方法写入文档，并从差异中检查跳过测试、抑制警告或降低门槛的改动，维持智能体开发质量。

• 制定智能体开发的质量标准
• 选择覆盖率与性能目标
• 发现跳过测试或抑制警告

将跨多个文件的功能开发和改造拆成可验证的小步骤，反复进行实现、测试、验证与提交，让系统在每个阶段都保持可运行状态。

• 实现跨多个文件的功能
• 开始计划中的下一项任务
• 通过功能开关隐藏未完成功能后集成

在保持行为不变的前提下，整理深层条件分支、长函数、重复逻辑和含糊命名。先检查现有规范与测试，再以可读性为标准逐步修改。

• 改善已正常运行功能的代码可读性
• 处理代码审查指出的复杂逻辑
• 整理深层条件分支和长函数

将设计或实现中的重要决策交给不继承工作过程的独立审查者验证，找出隐藏前提和失败条件，再据此修正问题或重新评估决策。

• 验证设计方案的前提
• 检查陌生代码中的决策
• 审查认证与敏感处理逻辑

通过对话深入梳理模糊的想法，比较多个方案，形成可付诸行动的构想，并明确目标人群、成功标准、待验证假设、最小范围和不做的事项。

• 把模糊的服务或功能想法具体化
• 确定方向前比较其他方案
• 制定计划前验证假设

检查项目所用框架和库的版本，依据对应的官方文档实现代码，为设计决策提供来源链接，并标明已弃用的 API、未验证的方法及与现有代码的冲突。

• 依据所用版本的官方文档核对实现
• 创建附有来源的代码模板
• 检查代码是否使用已弃用的 API

将混杂的代码改动按目的拆成提交，协助管理分支和准备拉取请求，并根据兼容性变化整理版本号、标签和变更日志，同时检查提交内容。

• 将混杂改动拆成独立提交
• 准备供审查的分支和拉取请求
• 用 git worktree 分离并行工作

Fit probabilistic models to single-cell measurements for integration across experiments, cell annotation, combined RNA and protein or ATAC analysis, and gene expression comparisons. The skill covers input requirements, training checks, reference mapping, and interpretation of model uncertainty.

中文简介正在准备中。当前显示英语简介。

• Integrating single-cell RNA data across experimental batches
• Assigning cell labels using partial annotations or a reference
• Analyzing RNA with protein or ATAC measurements

Prepare papers, research posters, and grant documents for a specific journal, conference, or funder. The skill guides official template selection, checks current submission requirements, adapts writing, and inspects PDF page counts and embedded fonts.

中文简介正在准备中。当前显示英语简介。

• Preparing a paper for a journal or conference
• Checking page limits and anonymous review requirements
• Drafting grant proposal components

Build graph neural networks, models that learn from connected nodes, with PyTorch Geometric. Supports node and graph classification, link prediction, custom datasets, and training approaches for large graphs or graphs containing multiple types of nodes and connections.

中文简介正在准备中。当前显示英语简介。

• Build node and graph classification models
• Predict links between nodes
• Train models on graphs with multiple node and connection types

Retrieve U.S. federal financial data from the Treasury’s public API, including debt, revenue, spending, interest rates, and exchange rates. Filter dates and fields, retrieve multiple pages, and organize results into tables for analysis.

中文简介正在准备中。当前显示英语简介。

• Tracking U.S. national debt over time
• Comparing monthly federal revenue and spending
• Retrieving Treasury reporting exchange rates

Fit regression and time series models in Python, interpret coefficients, compare alternatives, and check model assumptions. Supports statistical diagnostics and forecasting, with confidence intervals and validation steps to assess uncertainty and predictive performance.

中文简介正在准备中。当前显示英语简介。

• Fit regression models and interpret coefficients
• Compare models for binary outcomes or counts
• Forecast time series with prediction intervals

Work with Waypoint models to analyze microbiome samples, the communities of microbes in a sample. Convert taxonomic abundance tables, generate numerical sample representations, configure further training for prediction tasks, and evaluate models on the Compass benchmark.

中文简介正在准备中。当前显示英语简介。

• Convert microbiome abundance tables into Waypoint inputs
• Generate sample vectors for clustering and visualization
• Configure further training with sample labels

Stress-test research plans by comparing possible scenarios, such as sample losses, unavailable materials, or methods failing to transfer. Record assumptions and evidence, compare response options, and define contingency plans and observable triggers for changing course.

中文简介正在准备中。当前显示英语简介。

• Plan responses to higher-than-expected sample losses
• Prepare backups for unavailable reagents or datasets
• Compare research options under resource constraints

Forecast sales and other time series with Google’s TimesFM without task-specific training. Prepare regularly spaced CSV data, export predicted values and uncertainty ranges, add explanatory variables, and evaluate forecasts against held-out observations.

中文简介正在准备中。当前显示英语简介。

• Forecast monthly sales or revenue from CSV data
• Export predicted values with uncertainty ranges
• Forecast with additional explanatory variables

Simulate concentration changes over time from biochemical models in SBML or Antimony, and compare fixed parameter conditions. Checks model units and exports CSV results plus COMBINE archives containing models and experiment settings, then replays them to compare results.

中文简介正在准备中。当前显示英语简介。

• Calculate concentration changes in reaction networks
• Compare baseline and altered kinetic parameters
• Inspect model units and consistency warnings

Estimate RNA velocity, the modeled direction of gene expression change, from single-cell spliced and unspliced counts. Fit models, inspect gene-level plots, visualize trajectories, and explore relative timing and associated genes while checking model limitations.

中文简介正在准备中。当前显示英语简介。

• Explore hypotheses about directions of cell-state change
• Inspect gene-level RNA velocity model fits
• Estimate relative cell ordering with a dynamical model

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.

中文简介正在准备中。当前显示英语简介。

• Training and evaluating molecular property prediction models
• Building molecule generation workflows
• Learning representations of protein sequences and structures

Analyze large scientific tables with Vaex, including datasets that exceed available memory. Build calculated columns, filter rows, compute statistics, visualize aggregated data, and convert files while identifying operations that may still require substantial RAM.

中文简介正在准备中。当前显示英语简介。

• Computing statistics on tables larger than available memory
• Creating calculated features without storing full columns
• Visualizing large datasets with aggregated grids

Organize treatment decisions already supplied and verified by authorized licensed professionals into local JSON documents. Check document structure, source references, declared review status, and supplied dates to support documentation handoffs without making clinical decisions.

中文简介正在准备中。当前显示英语简介。

• Organize verified clinician-authored treatment records
• Check source references and missing documentation fields
• List checkpoint dates already supplied by clinicians

Store genomic variant records in TileDB-VCF, add samples over time, and retrieve selected samples or genomic regions. Supports batch reading, allele statistics, quality checks, and VCF/BCF export, with workflows for local storage and TileDB Cloud.

中文简介正在准备中。当前显示英语简介。

• Build a variant dataset and add samples incrementally
• Extract variants for selected samples and genomic regions
• Review allele statistics and sample quality