开发技能

Break a complex, multi-session engineering objective into a Markdown plan of executable steps. Each step includes its own context, tasks, checks, and completion criteria, with dependencies and parallel work identified and the plan reviewed for gaps.

中文简介正在准备中。当前显示英语简介。

• Planning a feature across multiple pull requests
• Mapping dependencies in a long refactor or migration
• Preparing handoff notes for agents working in later sessions

Plan and improve server-side applications built with Node.js, Express, and Next.js API routes. Get practical patterns for API structure, database queries, caching, authentication, error handling, background jobs, and logging.

中文简介正在准备中。当前显示英语简介。

• Designing REST or GraphQL endpoints
• Reducing inefficient database queries
• Adding caching or API authentication

Supports writing, reviewing, and refactoring modern C++17, C++20, and C++23 code using the C++ Core Guidelines. It helps check type safety, resource ownership, error handling, concurrency, templates, naming, and standard library usage for clear, consistent code.

中文简介正在准备中。当前显示英语简介。

• Writing modern C++ classes and functions
• Reviewing C++ code for safety and clarity
• Refactoring resource management and interfaces

Query a CodeGraph map of an initialized codebase to find symbols, callers, callees, focused context, and likely change impact. Summarize the structural evidence for planning, implementation, or review workflows.

中文简介正在准备中。当前显示英语简介。

• Finding where a symbol is defined and used
• Checking callers and callees before changing code
• Estimating the impact of a code change

Structure Android and Kotlin Multiplatform apps with clear module boundaries and dependency rules. Apply UseCase and Repository patterns, organize data sources, and keep domain models separate from database and network details using examples for common Kotlin tools.

中文简介正在准备中。当前显示英语简介。

• Plan modules for an Android or KMP project
• Separate domain, data, and presentation layers
• Design UseCases and repository interfaces

Coordinate coding work across Claude Code agents with Claude DevFleet. Turn a project request into linked missions, run agents in separate Git worktrees, track their progress, and review structured reports of changes, errors, and next steps.

中文简介正在准备中。当前显示英语简介。

• Splitting a coding project into linked agent missions
• Running independent coding tasks in parallel
• Tracking mission progress and reviewing reports

Helps build applications with the Anthropic Claude API and SDKs in Python or TypeScript. It covers messages, streaming, tool use, image input, batch requests, prompt caching, error handling, and multi-step agent workflows, with examples for common integration tasks.

中文简介正在准备中。当前显示英语简介。

• When building a Python app with Claude
• When adding streaming or tool calls
• When sending images to Claude

Use this skill to build shared Android, iOS, desktop, and web interfaces with Compose Multiplatform or Jetpack Compose. It provides practical patterns for UI state, navigation, reusable composables, theming, platform-specific UI, and reducing unnecessary recomposition.

中文简介正在准备中。当前显示英语简介。

• Managing screen state with ViewModels and StateFlow
• Adding type-safe navigation to a Compose app
• Designing reusable composables and a shared design system

Design or review REST APIs with consistent resource names, HTTP methods, status codes, response formats, pagination, filtering, rate limits, and versioning. The guidance helps shape endpoints that are clear for developers and suitable for public or internal services.

中文简介正在准备中。当前显示英语简介。

• Plan URL and method conventions for new endpoints
• Review an existing API contract
• Choose pagination and filtering patterns

Choose Claude Code skills and rules to install at user or project level. The workflow checks installed files and path references, reports problems, and can tailor the installed materials to a project's tech stack and preferences.

中文简介正在准备中。当前显示英语简介。

• Installing selected skills for a project
• Checking an existing installation for path issues
• Tailoring installed rules to a team's preferences

Define or review an API contract so architects, frontend and backend developers, and QA can agree on requests, responses, authentication, errors, and compatibility. It helps teams record who calls an interface and what each side must know before implementation and verification.

中文简介正在准备中。当前显示英语简介。

• Agreeing on API requests and responses before implementation
• Recording authentication and error code expectations
• Reviewing compatibility rules for an interface

Apply a file-processing cache keyed by SHA-256 content hashes. Results can be reused after a file is moved or renamed, while changed content naturally gets a new cache key. The pattern keeps caching in a service layer separate from pure processing functions.

中文简介正在准备中。当前显示英语简介。

• Caching repeated PDF or image processing
• Adding cache controls to a command-line tool
• Reusing results across batch runs

Record significant architecture choices as concise ADR documents alongside the code. Capture the context, alternatives, rationale, and consequences so developers can understand why a framework, database, API, or other design direction was chosen.

中文简介正在准备中。当前显示英语简介。

• Record a framework or database decision
• Document alternatives and trade-offs during planning
• Find the reasoning behind an existing design choice

Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.

中文简介正在准备中。当前显示英语简介。

• Designing an AI agent from a business need
• Generating a runnable agent project
• Planning tools, prompts, and orchestration

Assess a concrete long-running Python entrypoint to see where repeated work can safely run in parallel and whether the overhead is worthwhile. When source optimization is authorized, make a minimal refactor and require correctness and performance evidence before claiming an improvement.

中文简介正在准备中。当前显示英语简介。

• Assessing a slow Python command for parallel work
• Checking whether loop iterations are independent
• Reviewing a proposed process or thread pool

Configure a CarsXE API key by validating it with the CarsXE API, saving it for future sessions, and setting it for the current session. It can also check an existing key without changing it.

中文简介正在准备中。当前显示英语简介。

• Saving a CarsXE API key for future sessions
• Configuring the plugin after providing a key
• Checking whether the current API key is valid

Set engineering practices for teams where AI agents produce much of the code. Focus planning on clear acceptance criteria, review on system behavior and risk, and use deterministic tests and integration checks to evaluate generated changes.

中文简介正在准备中。当前显示英语简介。

• Setting development practices for an AI-assisted team
• Defining reviews for generated code and system behavior
• Raising regression and integration testing expectations

Set up an app backend through Cohesivity’s HTTP API, including databases, hosting, authentication, storage, realtime features, and AI model access. The skill guides agents through project setup and service provisioning while handling credentials and user approval requirements.

中文简介正在准备中。当前显示英语简介。

• Give a new app a database and backend services
• Add login or social authentication to a project
• Set up hosting and deployment

Fetch available vehicle years, makes, models, trims, or variants for cascading dropdowns using the CarsXE YMM Options API. It presents the matching options and can continue to the next selection level; full vehicle specifications are handled separately.

中文简介正在准备中。当前显示英语简介。

• Listing vehicle years for a dropdown
• Finding makes available for a selected year
• Browsing models or trims for a vehicle

Create, repair, audit, consolidate, or export agent skill packages built around SKILL.md. It checks for existing owners and evidence before proposing new skills, and can produce reports or platform-specific exported files for selected operations.

中文简介正在准备中。当前显示英语简介。

• Creating a structured SKILL.md package
• Checking or repairing a skill's structure
• Auditing a skill and producing a report

Takes one accepted change from implementation through required checks and closeout. It uses a fresh, author-distinct review only when requested or when a mistake could be costly, and reports evidence, unchecked work, and open decisions.

中文简介正在准备中。当前显示英语简介。

• Completing an approved code change
• Running required checks and reporting results
• Getting a focused review for a high-cost mistake

Get evidence-based advice on a plan, design, or code change. The skill identifies actionable findings with locations, consequences, and suggested next checks, while stating what it inspected and what remains unknown. Its feedback is advisory, not an acceptance verdict.

中文简介正在准备中。当前显示英语简介。

• Getting a second opinion on a plan or design
• Reviewing a proposed code change
• Finding risks in a supplied excerpt

Restructure code to extract, simplify, rename, or remove a bounded piece while preserving what callers observe. Compare focused checks before and after, including relevant error paths and output, and report behavior that could not be checked.

中文简介正在准备中。当前显示英语简介。

• Simplifying one function without changing its behavior
• Extracting repeated logic while preserving differences
• Renaming or moving code behind existing interfaces

Operate a Gas City software factory when it has been explicitly selected. Hand a task to its Mayor, inspect run, session, bead, and artifact state, and diagnose stalled workers. The skill returns runtime evidence; it does not decide whether the work is correct or complete.

中文简介正在准备中。当前显示英语简介。

• Hand a supplied task to the Gas City Mayor
• Inspect a run that appears stuck
• Check run, session, and bead state