“codebase”的搜索结果

检查采用领域驱动设计的 TypeScript 代码，查找跨业务领域的不当引用、数据一致性、事件及仓储位置问题，并汇总问题位置和改进建议。

• 审计业务领域间的依赖
• 合并前检查跨领域改动
• 在持续集成中检查设计边界

Add support for a programming language to codegraph, from connecting its parser and implementing code extraction to writing tests. Evaluate extraction quality and compare agent effort with and without codegraph across three real codebases.

中文简介正在准备中。当前显示英语简介。

• Adding a new programming language to codegraph
• Testing extraction of functions, imports, and calls
• Comparing agent effort across three real codebases

Benchmark how CodeGraph affects an agent investigating a real codebase. Choose a version, language, repository, and execution mode, then compare cost, tool calls, file reads, and answer correctness with and without CodeGraph.

中文简介正在准备中。当前显示英语简介。

• Evaluating a local development build
• Auditing a published CodeGraph version
• Comparing investigation cost and file reads

Learn the OpenSpec workflow by completing a small task in a real codebase. The skill explains each stage, creates planning documents, implements agreed tasks, and archives the change to preserve its decision history.

中文简介正在准备中。当前显示英语简介。

• Learn OpenSpec through a real code change
• Find a small improvement for a first practice task
• Understand the roles of proposals, specs, design, and tasks

Turn a broad coding request into a concrete work plan grounded in the codebase. After user approval, it documents affected files, decisions, dependencies, and verification steps so a separate worker can carry out the implementation.

中文简介正在准备中。当前显示英语简介。

• Planning a large feature before coding
• Turning a vague request into defined tasks
• Preparing an implementation handoff

Audit a codebase with three vulnerability hunters and two engineers who build small demonstrations of suspected flaws. Verify attack paths, assess severity from demonstrated impact, and report evidence, targeted fixes, and checks to prevent recurrence.

中文简介正在准备中。当前显示英语简介。

• Review security before a release
• Audit security risks in a pull request
• Verify whether a suspected flaw is exploitable

Inspect a codebase and create concise project instructions for Claude Code. Review existing guidance, separate team rules from personal preferences, and propose reusable skills or hooks that run commands automatically.

中文简介正在准备中。当前显示英语简介。

• Set up project instructions for Claude Code
• Review and improve an existing CLAUDE.md
• Separate personal preferences from team rules

Understand a codebase before searching for bugs or vulnerabilities. This skill examines functions line by line, documents assumptions and state changes, and traces calls across modules to build an evidence-based picture of system behavior.

中文简介正在准备中。当前显示英语简介。

• Understanding a codebase before a security audit
• Tracing data and state changes across function calls
• Documenting assumptions for an architecture review

Assess Airflow Improvement Proposals by comparing Confluence specifications with pull requests, commits, and codebase files. Produce evidence-backed progress reports showing delivered items, remaining work, and specification updates needed across one or more proposals.

中文简介正在准备中。当前显示英语简介。

• Check implementation progress for an Airflow proposal
• Compare specification deliverables with shipped code
• Compile a progress report across multiple proposals

Scan a codebase or selected changes for security issues, then request targeted patch files for findings. Independent agents verify reported issues and proposed fixes, while you review and apply patches yourself.

中文简介正在准备中。当前显示英语简介。

• Auditing an entire repository or a selected area
• Checking security issues in branch or pull request changes
• Scanning a single commit

Scan a codebase to create project documentation and project-specific agent instructions. The first run examines the whole project; later runs focus on changed files, with human confirmation required before updating agent instructions after architectural changes.

中文简介正在准备中。当前显示英语简介。

• Create documentation when starting agent-assisted development
• Refresh project documentation after architecture changes
• Check changed code for documentation drift

Create a copilot-instructions.md file from an existing codebase. Identify technology versions, architecture, naming conventions, and testing practices, then turn observed patterns into project-specific guidance for GitHub Copilot without introducing unsupported assumptions.

中文简介正在准备中。当前显示英语简介。

• Create GitHub Copilot instructions for an existing project
• Document version compatibility requirements
• Capture established coding and testing conventions

Generate a customizable AI prompt for finding representative examples in an existing codebase. Configure analysis depth, categories, and snippets so GitHub Copilot can produce exemplars.md with real file references and explanations of coding conventions.

中文简介正在准备中。当前显示英语简介。

• Collecting existing code examples for team guidance
• Documenting patterns to follow when adding features
• Configuring the depth and format of a code example guide

Review an AI agent codebase against ten OWASP ASI security risk areas. Examine tool permissions, input validation, identity checks, audit logs, and other controls, then summarize coverage, gaps, and recommended improvements in a report.

中文简介正在准备中。当前显示英语简介。

• Reviewing agent security before production deployment
• Mapping existing controls to ten security risk areas
• Preparing findings for a security review or audit

Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.

中文简介正在准备中。当前显示英语简介。

• Understanding an unfamiliar project's structure
• Locating authentication code and API endpoints
• Checking file counts and estimated AI tokens

Audit a codebase before production deployment across eight areas, including security, databases, dependencies, and AI usage. Receive findings with file locations, manual checklists, and a release verdict that blocks shipping when critical issues remain.

中文简介正在准备中。当前显示英语简介。

• Check an application before its first production release
• Find security and database issues before deployment
• Review backup restoration and rollback readiness

Build or update a Figma design system from an existing codebase. Organize shared design values, light and dark themes, reusable components, and documentation through staged reviews, then check consistency, accessibility, and links between design and code.

中文简介正在准备中。当前显示英语简介。

• Creating shared color and spacing variables from code
• Setting up light and dark themes
• Building a reusable component library with documentation

Learn the complete OpenSpec workflow through a small task in an actual codebase. The agent explains each stage while creating a proposal, specifications, design, and tasks, then implements the change and archives its records.

中文简介正在准备中。当前显示英语简介。

• Learning OpenSpec through a real code change
• Understanding proposals, specifications, designs, and tasks
• Practicing a complete change cycle with a small fix

Audit saved project learnings against the current codebase to find outdated explanations, overlapping documents, and contradictions. Maintain the documentation with evidence-based updates, consolidation, replacement, or deletion, and deliver a per-document report with committed changes when applicable.

中文简介正在准备中。当前显示英语简介。

• Checking saved learnings against current code
• Consolidating overlapping knowledge documents
• Correcting outdated paths and links

Delegate checks for AGENTS.md rule violations to a dedicated agent. It scans the codebase, fixes high-impact issues in a separate working copy, runs full validation, and creates a pull request, tracking progress across runs through memory.

中文简介正在准备中。当前显示英语简介。

• Checking code for AGENTS.md rule violations
• Prioritizing high-impact rule violations for fixes
• Checking compliance within a chosen focus area

Collect deliberate shortcuts marked with ponytail: comments into a file-by-file debt report. Show each shortcut’s stated limit and revisit trigger, flag missing triggers, and summarize counts without changing the codebase.

中文简介正在准备中。当前显示英语简介。

• Listing deliberately deferred code improvements
• Finding shortcuts without revisit triggers
• Reviewing limits and upgrade paths by file

Review and simplify the ego-lite codebase by finding unused code, duplicated state, and unnecessary layers. The skill checks real callers and API requirements, explains behavior changes, and coordinates implementation, tests, and documentation updates.

中文简介正在准备中。当前显示英语简介。

• Audit unused code and APIs
• Consolidate duplicated state or processing
• Review unnecessary compatibility layers

Explore how a public GitHub repository is organized using GitDiagram. Get explanations tied to component names and source paths, an interactive architecture diagram, and a narrated explainer video when one is available.

中文简介正在准备中。当前显示英语简介。

• Preparing to work in an unfamiliar public codebase
• Understanding major components and their source paths
• Exploring component connections in an interactive diagram

Coordinate large code migrations in reviewable batches. The agent changes local files, while the Composio CLI connects tracking issues, pull requests, and automated checks so each batch can be tested and reviewed before proceeding.

中文简介正在准备中。当前显示英语简介。

• Upgrading frameworks across many files
• Renaming an API throughout a monorepo
• Migrating configuration files or test tools