“code graph”的搜索结果

Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools. Dual-mode: skill-library (agent-loom) or application (any consumer repo). Load when the user asks for a knowledge graph, project map, skill relationships, query the graph, update the graph, or trace how components connect. Auto-runs on memory-handoff and project-setup bootstrap. Also triggers on "build the graph", "what connects to X", "map this project".

中文简介正在准备中。当前显示原文说明。

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

Review web interface code against Vercel's Web Interface Guidelines, covering layout, typography, color, motion, and accessibility. Receive concise findings with file names and line numbers, using a bundled guideline snapshot for a consistent review baseline.

中文简介正在准备中。当前显示英语简介。

• Reviewing product interface code
• Checking accessibility against interface guidelines
• Checking layout, typography, color, and motion

Import Claude Code auto-memory into AgentDB and search past notes by meaning across sessions and projects. The skill checks import status, consolidates near-duplicate entries, and returns search results with their memory sources identified.

中文简介正在准备中。当前显示英语简介。

• Search past notes across projects
• Import all project memories for the first time
• Consolidate near-duplicate memories

Investigate a username, file, code identifier, URL, or concept by exploring connected entities across relevant sources. Produce a dossier with a summary, relationship diagram, source references, and a machine-readable JSON graph.

中文简介正在准备中。当前显示英语简介。

• Mapping connections around a username or concept
• Investigating references to a file or code identifier
• Tracing links to an architecture decision record

Create integration tests for syncable metadata entities in Twenty itself. Cover invalid inputs, validation errors, and successful data operations, using reusable GraphQL request helpers, error snapshots, and cleanup routines to organize the test suite.

中文简介正在准备中。当前显示英语简介。

• Add integration tests for a new syncable entity
• Test required fields, duplicates, and invalid references
• Verify successful creation, updates, and deletion

Review a repository’s architecture using Ontoly Software Graph, a map of code relationships. Explain module boundaries, package structure, dependencies, and architectural risks, with graph evidence and a stated confidence level.

中文简介正在准备中。当前显示英语简介。

• Understanding a repository’s overall architecture
• Reviewing module boundaries and package structure
• Investigating dependency cycles and architectural risks

Design APIs and interfaces between parts of an application with clear input and output types, consistent errors, and predictable names. The guidance helps you extend existing interfaces while preserving compatibility for the code that uses them.

中文简介正在准备中。当前显示英语简介。

• Designing new REST or GraphQL endpoints
• Defining contracts between frontend and backend
• Reviewing changes to a public interface

Find the right GitNexus tools and workflows for exploring code relationships. This reference explains available commands, graph queries, and resources, including how to check which branch an answer describes and whether its index is current.

中文简介正在准备中。当前显示英语简介。

• Find a GitNexus tool for a specific task
• Learn how to query code relationships
• Check index freshness and branch information

Learn how to check Claude Code tool calls against a policy and create digitally signed execution records. This walkthrough covers setup, offline verification, tamper demonstrations, and CI/CD integration before adopting the protect-mcp runtime plugin.

中文简介正在准备中。当前显示英语简介。

• Evaluate signed audit records before adopting runtime hooks
• Demonstrate offline verification and tamper detection
• Verify agent execution records in CI/CD

Create Mermaid diagrams from text to explain software structure, API interactions, workflows, and database relationships. The skill guides diagram selection, syntax, styling, and export, helping keep visual documentation editable and stored alongside code.

中文简介正在准备中。当前显示英语简介。

• Explaining system architecture with diagrams
• Mapping API requests and responses
• Documenting database table relationships

Guides migration of existing codebases to Rust without unsafe code, covering architecture, implementation, testing, and output comparisons. It measures performance before and after optimization and produces an interactive HTML report documenting results and unresolved differences.

中文简介正在准备中。当前显示英语简介。

• Migrating a GitHub or local codebase to Rust
• Comparing original and migrated program outputs
• Measuring and optimizing a Rust port

Audit citations in a LaTeX paper against online sources. Verify that references exist, bibliographic details are accurate, and each cited work supports the surrounding claim, then produce reports with findings and proposed corrections.

中文简介正在准备中。当前显示英语简介。

• Checking references before paper submission
• Verifying authors, publication years, and venues
• Checking whether cited papers support manuscript claims

Fetch execution traces, records of an agent’s actions, from LangSmith Studio to debug LangChain and LangGraph agents. Inspect errors, tool calls, memory operations, execution times, and token usage, or export records for further review.

中文简介正在准备中。当前显示英语简介。

• Investigating an agent failure
• Checking tool selection and execution order
• Investigating memory storage and recall

Inspect imports and agent patterns in existing Python code to identify its framework and recommend an Omnigent executor, the component that runs the agent. Explain unsupported frameworks and suggest available next steps.

中文简介正在准备中。当前显示英语简介。

• Identify the framework used by existing Python agent code
• Choose an executor for Claude SDK or OpenAI Agents SDK code
• Check whether a framework has native support

Read frontend source code to document colors, typography, spacing, components, and layout rules in DESIGN.md. Use it to understand an existing interface or prepare design guidance for Stitch without building or running the app.

中文简介正在准备中。当前显示英语简介。

• Document an existing app's design system
• Review styling when the app cannot run
• Prepare an existing visual identity for Stitch

Run Python through the shell when a code sandbox fails to start or connect. Uses a heredoc, a way to pass multiline code, with examples for generating charts, Word documents, and processed JSON files.

中文简介正在准备中。当前显示英语简介。

• Continue Python work when the code sandbox is unavailable
• Create a graph image from Excel data
• Generate a Word document with headings and a table

Turn cryptographic code or specifications into sequence diagrams showing who sends each message, which cryptographic operations occur, and where failures stop the exchange. Outputs include Mermaid source, a plain text diagram, and a protocol summary.

中文简介正在准备中。当前显示英语简介。

• Visualizing handshake and key exchange steps
• Extracting message flows from RFCs and papers
• Diagramming ProVerif or Tamarin models

Generates cryptographic test vectors, inputs with expected outcomes, by deliberately changing implementation code and finding changes existing tests miss. Verifies new vectors across independent implementations and compares detection rates before and after adding them.

中文简介正在准备中。当前显示英语简介。

• Finding coverage gaps in cryptographic test vectors
• Creating invalid inputs that exercise validation checks
• Building test vectors shared across independent implementations

Analyze code structure with Trailmark to identify complex functions, trace input flow, assess impact across connected code, and locate privilege boundaries. The resulting JSON provides detailed evidence for deciding where to focus a code audit.

中文简介正在准备中。当前显示英语简介。

• Prioritizing code audit targets
• Tracing input flow and assessing impact
• Inspecting unresolved calls and type references

Inspects compiled instructions and bytecode to identify timing risks in cryptographic code. Helps trace flagged operations back to secret data, distinguish false positives, and review fixes across compiler settings and target architectures.

中文简介正在准备中。当前显示英语简介。

• Reviewing signing and encryption routines
• Checking division involving secret values
• Inspecting authentication tag comparisons

Build or update a Figma design system from existing code. Organize shared colors, spacing, and typography, create reusable components with states and theme bindings, document their use, and check differences between the implementation and Figma.

中文简介正在准备中。当前显示英语简介。

• Building a Figma component library from existing code
• Organizing shared settings for light and dark themes
• Creating a button with variants and variable bindings

Find API patterns and examples for coding agents with ADK, the Agent Development Kit. Covers tools, state, callbacks, multi-agent coordination, and graph workflows, with Python and Go references plus guidance on studying existing implementations.

中文简介正在准备中。当前显示英语简介。

• Adding tools and callbacks to an ADK agent
• Implementing state management and agent coordination
• Designing branching and parallel graph workflows

Build forms with Formik and yup, a library for defining input validation rules. Apply field errors, submission feedback, edit detection, and step-specific validation to login screens, editing forms, and forms split across multiple steps.

中文简介正在准备中。当前显示英语简介。

• Building login and registration forms
• Adding conditional input validation
• Editing existing records with change detection