“code graph”的搜索结果

读取记录架构决策及其原因的ADR，创建并更新搜索索引和依赖关系图。支持两种文档格式，并汇总引用与状态的不一致情况。

• 导入其他项目的ADR后建立索引
• 同步文件与关系图
• 为现有代码库开始管理ADR

Audit geographic meta tags on region-specific pages, checking region codes, coordinate formats, and consistency with the intended audience. Use the findings to correct supplementary location signals while keeping language targeting and structured business data as primary approaches.

中文简介正在准备中。当前显示英语简介。

• Auditing geographic tags on regional pages
• Checking region codes and coordinate consistency
• Reviewing supplementary location signals for Bing

Build and revise a design system from brand materials or code. Organize colors, typography, spacing, components, and assets into structured files, with usage guidelines and previews, using the supported Design System artifact format.

中文简介正在准备中。当前显示英语简介。

• Organizing design rules from existing code and brand materials
• Documenting colors, typography, and spacing
• Collecting logos, icons, and component previews

Create charts and dashboards with a consistent approach to chart selection, color validation, labels, and interaction. Includes a palette checker and accessibility rules for readable visualizations in both light and dark modes.

中文简介正在准备中。当前显示英语简介。

• Choose a chart type that fits the data
• Validate chart colors for color vision differences
• Build charts for light and dark modes

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

Build molecular property prediction workflows with DeepChem for solubility, toxicity, and related chemistry tasks. Prepare molecular representations, choose compatible models, handle missing labels, and evaluate predictions using data splits designed for the intended scientific question.

中文简介正在准备中。当前显示英语简介。

• Predicting solubility from molecular structures
• Comparing graph models on MoleculeNet datasets
• Checking data splits for information leakage

Generate, compose, and edit product images, posters, illustrations, and social graphics through the paid Beatra service. The workflow covers reviewing upload files and estimated costs before each paid call, then checking results and actual charges.

中文简介正在准备中。当前显示英语简介。

• Creating product images
• Designing posters and social graphics
• Editing reference images and making photo variations

Create an implementation plan grounded in code relationships and verified source files, with proposed changes, test scenarios, risks, and a structured handoff for an implementation agent. It can also revisit and strengthen an existing plan.

中文简介正在准备中。当前显示英语简介。

• Planning a new feature
• Assessing a shared API change before implementation
• Strengthening and rechecking an existing plan

Create or edit Markdown with each prose paragraph on one source line, letting the viewer wrap the text automatically. Preserve meaningful line breaks in lists, code, and poetry while reducing unnecessary changes in file comparisons.

中文简介正在准备中。当前显示英语简介。

• Writing READMEs without fixed-width line wrapping
• Joining manually wrapped Markdown paragraphs
• Keeping Markdown changes easier to review

Build consistent interface foundations with design tokens, named values for colors, spacing, and typography. Covers light and dark themes, multiple brands, reusable components, and workflows that keep design definitions aligned with application code.

中文简介正在准备中。当前显示英语简介。

• Organizing shared colors, typography, and spacing
• Implementing light and dark theme switching
• Sharing interface components across multiple brands

Work through GitHub pull request feedback by classifying findings, fixing code, running repository checks, and posting replies. With suitable permissions, the skill repeats Copilot reviews until the latest code is reviewed and every thread has an agent response.

中文简介正在准备中。当前显示英语简介。

• Address outstanding Copilot review comments
• Run repeated reviews on a completed pull request
• Explain declined suggestions and hand off design decisions

Define repeatable workflows and their dependencies in JSON, then execute them through a CLI. Combine commands, read-only agent tasks, parallel branches, and human approval steps, with journal records that support recovery after interruption.

中文简介正在准备中。当前显示英语简介。

• Running repeatable build and test workflows
• Resuming a workflow after a crash
• Adding human approval before deployment

Review module relationships and change history to identify structural improvements in a codebase. Receive ranked candidates with file references, suggested changes, and risks, plus a recommendation for where to start, without modifying code.

中文简介正在准备中。当前显示英语简介。

• Reviewing architecture after a batch of changes
• Investigating changes that touch too many files
• Prioritizing structural improvements

Helps integrate CopilotKit into an app by consulting current documentation and source code. Covers chat interfaces, agent connections, shared state, and troubleshooting, with guidance on checking configuration and avoiding incompatible API versions.

中文简介正在准备中。当前显示英语简介。

• Adding a CopilotKit chat interface to an app
• Connecting an agent framework
• Diagnosing runtime connection problems

Build and debug sglang tests comparing token probabilities during prompt processing and step-by-step generation. Separate numerical differences from reused-state bugs, choose test thresholds, and locate the first operation that diverges.

中文简介正在准备中。当前显示英语简介。

• Adding probability consistency tests for a model
• Choosing or justifying a kl_div threshold
• Separating numerical differences from cache state bugs

Build a two-tier certificate authority with OpenSSL and Python, separating the offline root from the issuing authority. Covers server and client certificates, revocation checks, and policies that define certificate usage and trust.

中文简介正在准备中。当前显示英语简介。

• Set up an internal certificate authority
• Issue server and client certificates
• Configure certificate revocation checks

Build connections between applications and external APIs, interfaces used to exchange data with other services. The skill guides authentication, data conversion, webhook verification, request limits, retries, and troubleshooting to support reliable API clients.

中文简介正在准备中。当前显示英语简介。

• Connect payment, email, or SMS services to an application
• Implement OAuth and manage API credentials
• Verify webhooks and process incoming events

Research markets, competitors, companies, and technical topics using multiple sources in Google NotebookLM. Produce a structured brief with key findings and recommended actions, with optional slides, podcasts, videos, infographics, reports, or mind maps.

中文简介正在准备中。当前显示英语简介。

• Researching market trends and business opportunities
• Comparing competitors and their positioning
• Researching prospects before a proposal

Add persistent memory to NanoClaw agents using the default Claude provider. With mnemon installed in the container, agents retrieve relevant context before responding and save new insights after each turn, retaining memory across container restarts.

中文简介正在准备中。当前显示英语简介。

• Recalling earlier conversations in a new session
• Keeping agent memory across container restarts
• Checking memory hooks and storage settings

Build working web pages, application interfaces, and components with a clear visual direction. Shape typography, color, layout, and animation around the intended audience and purpose, producing coordinated design and code in HTML, CSS, JavaScript, React, or Vue.

中文简介正在准备中。当前显示英语简介。

• Building a landing page with a clear visual style
• Designing and implementing a dashboard
• Refining typography, colors, and spacing in an existing interface

Convert Markdown files into styled HTML suitable for WeChat and other platforms. Choose themes, colors, and fonts, preserve code and diagrams, and optionally turn external links into numbered references at the end.

中文简介正在准备中。当前显示英语简介。

• Converting Markdown articles into styled HTML
• Formatting articles for WeChat
• Exporting documents containing code and diagrams

Create explainer clips, short videos, and animated overlays with React code. Define scenes and motion by frame number, then render an MP4 that can be regenerated after changes to the content, timing, or visual design.

中文简介正在准备中。当前显示英语简介。

• Turn a process explanation into an animated video
• Create a short video from supplied content
• Build animated overlays for video

Examine writing for familiar AI patterns, statistical features, Pangram detection scores, and hidden character signatures. Compare drafts against known human writing to interpret the evidence, with explanations and limitations rather than a definitive authorship claim.

中文简介正在准备中。当前显示英语简介。

• Check a post for common AI writing patterns
• Compare AI detection scores across drafts
• Compare a revision with known human writing

Build a Three.js 3D model from an object or character reference image using code. The workflow develops shapes and materials in stages, compares rendered views with the reference, and guides corrections through quality checks.

中文简介正在准备中。当前显示英语简介。

• Rebuilding a photographed object as a browser-based 3D prop
• Creating a stylized character from a reference image
• Planning model parts, materials, and animation pivots