Каталог навыков агентов

Deep codebase analysis workflow for architecture, execution flow, data flow, business rules, external dependencies, data...

使用 341 种风格提示词和参考静帧制作代码动画、HTML 动效或视频。适用于按风格编号选型、组合视觉风格、把内容转成可编辑动画并渲染成片。

Generate boilerplate `# implements:` annotation for a function based on the artefact ID, inserting it as the first line...

Use when the user wants comments or documentation added to code — a specific file, code related to an API or interface e...

Use when annotating code with structured metadata, tags, and markers for AI-assisted development workflows. Covers annot...

Connect a Power Apps code app to data sources (SQL, SharePoint, Office 365, Dataverse, Copilot Studio agents). Use for p...

Create, scaffold, and initialize a new Power Apps code app from scratch. Guides through prerequisites, template selectio...

Deploy and operate a Power Apps code app: build/push, solutions, Pipelines, CSP, SDK migration, App Insights, PAC CLI fa...

Systematic techniques for reading and understanding unfamiliar legacy code without documentation

Designs feature architectures from existing codebase patterns, with implementation blueprints, file lists, and build seq...

Designs implementation blueprints for features using exploration findings and architectural best practices (converted fr...

Use when asked for an architecture blueprint or explicitly asked to run the code-architect subagent.

Application architecture patterns and code organization — clean architecture, hexagonal architecture, feature-based stru...

智能代码架构解读和分析工具。当用户请求分析项目架构、生成架构文档、识别设计模式、分析依赖关系、评估代码质量、或理解复杂项目结构时使用此skill。适用于接手新项目、代码审查、重构规划、技术选型评估等场景。

Especialista em Mapeamento de Código-Fonte, Arquitetura de Software, Análise de AST e Dependências entre Classes em Java...

Review recently written code for best practices, architectural consistency, and correct system integration. Use for revi...

This sop guides the implementation of code tasks using test-driven development principles, following a structured Explor...

Authorized source-code security review and SAST workflows: Semgrep and CodeQL pattern hunting, dangerous API identificat...

Audit code for actual defects, including bugs, application security issues, error handling gaps, and correctness problem...

Auditoria sistematica de codigo Python que detecta dead code, deuda tecnica y archivos inactivos con vulture, deadcode,...

Security audit, code quality review, and tech debt assessment for full-stack codebases. Run after major phases, at build...

对指定代码路径检查正确性、权限、数据处理与实际缺陷

Perform code audits for quality, security, and maintainability. TRIGGERS - Use when user needs help with code-audit rela...

Audits the entire codebase for bugs, security vulnerabilities, CLAUDE.md violations, dead code, duplicate code, and test...

Use for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunt...

This skill audits uncommitted changes, branches or PRs for bugs, edge cases, SOLID/DRY/SRP, architecture, security, perf...

Perform a structured audit of a codebase covering security, code quality, performance, dependencies, architecture, and t...

Perform comprehensive code audits on repositories or directories. Use when asked to audit code, review a codebase, analy...

Critically audit refactorings and design decisions against the real codebase, verify claims vs code, score only relevant...

Five-way parallel code audit. User pastes a Python file / function / diff → orchestrator fans out 5 specialist sub-agent...

Provides code auditing methodology, checklists, and best practices. Use when user asks to "audit code", "find technical...

系统化审计与代码优化 - Code Review / Simplifier / Council / Performance。

Agente autónomo especializado en auditoría de código (bugs, seguridad, performance).

Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and mainta...

[Implementation] [AUTO] Start coding & testing an existing plan (trust me bro)

Use when writing or reviewing code in any language, for the rules that hold regardless of stack: comments, size and shap...

Read-only bloat audit of any repo. jscpd duplication, knip or language dead-code tools with a spot-check, cloc size, fun...

Test skill with example code blocks that should NOT be detected as real references

The primary tool for code-navigation questions in ANY language (frontend or backend) — walk the structural graph from an...

用代码从零件搭 3D 场景并能反过来拆开：每个物件是一个往 Assembly 里加零件的函数（盒子、圆柱、球、线），渲染成技术插画（白灰三档面、细黑描边、白雾），正交等距相机在镜头之间连续运镜，外壳可以降下去露出内部，选中的部分能爆炸成零件...

Generate code explanation cards with syntax highlighting for tutorials and education. Creates title cards and explanatio...

Analyze and map code structure, data flow, and dependencies in legacy codebases. Use for understanding call stacks, depe...

Request approval before modifying files and verify changes are necessary

代码修改影响分析（通用）：判断改动是否解决了它该解决的问题、会牵连哪些调用方/页面/数据消费方、引入哪些回归风险；按改动性质分流策略（缺陷修复 / 行为等价优化 / 能力新增 / 契约变更 / 数据与状态变更）。触发："分析这个 bug 的...

Preserve rollback before materially risky edits.

Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR desc...

Restore requested code changes or checkpoints.

Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agent...

Use after code, test, packaging, CI, or browser-app changes to choose and run proportionate verification commands and re...

When the user asks for any coding work in a repository, or anything involving Cursor Origin or the `origin` CLI.

Detect and run project test, lint, and format commands; diagnose and fix failures when requested. Use when asked to run...

Check and lint Rust/TypeScript code using justfile tasks (just check-crate, just clippy-crate). Use after code changes,...

Map source file structure into navigable sections with line ranges and summaries for efficient agent navigation

各npmワークスペースの静的解析・単体テストを実行する（CIパイプラインシミュレーション）。CIチェックやコミット・PR前のコード品質検証を依頼されたときに使用すること。

Dead code detection and removal using knip (recommended) or standard tooling. Use when removing unused imports, variable...

Refactor and clean up code following best practices for readability and maintainability

This skill should be used when the user asks to clean up or simplify a codebase; find dead code, dead features, orphaned...

After iterating on code with multiple changes, reversals, or simplifications - technical debt accumulates. Use this skil...

Detect stale TODOs, unused imports, and dead code.

Find and fix surface hygiene (typos, naming, comment hygiene, editing artifacts, debug statements) and redundancies, non...

Detect and clean redundant code in Python and TypeScript projects. Finds unused imports, dead functions, stale comments,...

Code cleanup agent that organizes codebase by moving inline CSS to external files, extracting functions to proper locati...

Detects and refactors code duplication using PMD CPD. Use when identifying code clones, addressing DRY violations, or re...

Code clone detector: finds exact (Type 1), parameterized (Type 2), near-miss (Type 3), and semantic (Type 4) clones. Ris...

Guides code-focused Q&A for code review, bug diagnosis, and implementation suggestions. Asks about developer intent, rep...

Writes and updates terse, why-only code comments to house standard, and judges the comments in a diff via an isolated su...

Apply whenever writing or editing source code in any core's build agent (backend-eng, ui-builder, or equivalent). Govern...

Add JSDoc/docstrings with examples.

Generates meaningful comments and documentation for code to improve maintenance and readability. Use when adding documen...

Add detailed comments explaining WHY code works, its context, edge cases, and performance implications. Use when user me...

Guides Codex in writing high-quality, language-agnostic code comments and documentation. Use when asked to comment code,...

Apply whenever writing or editing code in any language, even if comments are not explicitly requested. Enforces comment...

Use specific checklists to ensure comprehensive and high-quality code commenting for general code, data declarations, an...

Apply strategic approaches to code commenting including when to comment, optimal comment density, performance considerat...

When and how to write code comments: the default is none, since code and tests carry the meaning and only the non-obviou...

Add or synchronize structured code comments for a repository, package, app, module, or file so humans and AI can underst...

Write purposeful, accurate, and maintainable code comments and API documentation across major programming languages. Use...

Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing c...

Extract comment locations from code files for analysis. Use when cleaning comments, auditing code documentation, or anal...

Code commenting guidelines and documentation standards. Use when adding comments to code or reviewing comment quality an...

Generate and validate conventional commit messages following the conventionalcommits.org spec. Use whenever the user wan...

Commit current changes using jj. Analyzes changes, suggests commit messages following repository conventions, splits whe...

Implement proper Git commit workflow with conventional commits, atomic changes, and meaningful messages. Use when commit...

Detects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying m...

Apply Steve McConnell-inspired construction rules when implementing routines, variables, classes, control flow, defensiv...

Use when Figma components should point at the project's blocks and Blade components through Code Connect - reading the e...

Creates and maintains Figma Code Connect files (`*.figma.tsx`) that map Figma components to code via the parser-based `f...

Enforces code consistency rules across all agents. Prevents unnecessary modifications to working code, ensures existing...

Enforce, review, and generate consistent code across registered languages: Python, Golang, Bash/Shell, Rust, PowerShell,...

Validates type consistency across Rust, TypeScript, PostgreSQL boundaries. Use when reviewing code, debugging type misma...

Automatically find relevant context from knowledge graph and code relationships while coding. Detects when context would...

Guide for code conventions and formatting

Trigger: writing production code or tests, applying test naming/assert style, extracting constants, placing DTOs or char...

Defines project-wide code conventions for magic number elimination, constant usage, performance optimization, and coordi...

Corrige et durcit le code d'une application web de façon disciplinée et mesurée. À utiliser quand l'utilisateur veut cor...