Каталог навыков агентов

Installs and configures Prettier, ESLint, EditorConfig, and other code quality tools to enforce consistent code style ac...

Execute automatically formats and validates code files using Prettier and other formatting tools. Use when users mention...

Format code on the current branch using Biome. Use when asked to format, lint, or clean up code before committing or cre...

Read-only repo health audit: Wasp Nest setup, agent readiness, CI, tests, lint, lockfiles, secrets, governance. Writes c...

Classify code tasks and execute task-specific checklists with quality gates. Route to WRITE, DEBUG, REVIEW, OPTIMIZE, RE...

仔细彻底阅读探索用户提供的代码目录/文件，分析拆解出对应的代码片段以供参考，颗粒度细到功能级别，只做片段提取不改变代码内容和页面布局结构，提取到./fragment-extractor目录下，按照指定模板格式生成代码片段模板文件，确保功能完...

Guide for extracting code or pseudocode from images using OCR and implementing it correctly. This skill should be used w...

Synchronize drift in existing repos. Use for stale comments or examples, parser/config errors, pre-existing failures, re...

Write, review, and debug code in any language. Powered by sovereign qwen2.5-coder model.

Extract Lanhu design HTML, CSS, and assets through Lanhu MCP for Claude Code design-to-code workflows. Called by design-...

Fast code generation agent optimized for speed and iteration

Create an Architecture Decision Record. Use when asked to write or draft an ADR for an architectural or technical decisi...

Generate or update CI/CD pipeline configuration. Use when asked to add or change GitHub Actions, GitLab CI, Jenkins, or...

Generate or update documentation. Use when asked to add comments, docstrings, module docs, README sections, or reference...

Generate or update tests for observable public behavior. Use when asked to add tests, cover edge cases, or improve test...

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns...

| ID | flutter-code-generation |

Use go:generate effectively - mockgen, stringer, templates, reducing boilerplate

Scaffolding, boilerplate generation, and project templates. Use for generating components, modules, APIs, and project st...

Use when generating boilerplate code, __init__.py files, or test scaffolds. Provides scripts that generate consistent, c...

What is generated, what generates it, and the rules around generated code (proto, GraphQL SDL, Prisma) in this repo.

Generate code implementation from design documents following structured phase-based workflow with token cost estimation...

Generates production-ready code with proper error handling, type safety, SOLID principles, and comprehensive documentati...

Generate Python boilerplate code for DAPR microservices, workflows, and actors. Creates properly structured services wit...

Cross-repo symbol / dependency query over the project's code-graph engine (ADR-001 NAVIGATION) — navigate object↔object...

How to read and refresh the generated code-structure graph at .claude/code-graph/graph.json (import/call relationships b...

AST-based code graph for fast symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp MCP server

Analyze codebases the way an agent sees them (codetopo).

Apply this repository's coding conventions and patterns. Use when writing or reviewing code in this codebase to ensure c...

Senior principal engineer for Raamattu Nyt codebase. Use when: (1) Implementing features with architectural implications...

Compact the current conversation into a handoff document for another agent to pick up.

Detects hardcoded values, magic numbers, duplicate constants, and leaked secrets using Ruff, Semgrep, jscpd, and gitleak...

Produce code that survives senior review. Use this skill whenever the user asks for code to be written, improved, refact...

Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela...

Night-shift code review: dispatch, apply findings, track.

Analyze codebase health - large files, test coverage gaps, duplicate code, dead/legacy code, and documentation issues. U...

Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus a...

Provides guidance for code quality improvements.

Helps with code analysis and refactoring tasks

General coding workflow for every code task.

Assist with code review, refactoring, and explanations. Use when analyzing or improving code.

Code review and assistance skill

Apply code hygiene standards for clean, maintainable code. Use when writing, refactoring, or reviewing code.

破壊的変更に基づいてプロジェクト内のコードを検索し、影響を受けるファイルと行を特定する。テストカバレッジも確認する

按骨架（design-to-code 产出）分批填充方法实现、解决 TODO：每批先读契约注释 + 调研/依赖文档，完成后验证实现是否满足契约。触发："骨架编码"、"填充骨架"、"实现代码"、"implement skeleton"、"开始...

Language-specific coding guidelines. Use when implementing code in Python or other supported languages.

actor: tech-lead | mandate: Build feature with automated tests | bounds: No architecture changes

Implement code changes by learning from and precisely matching existing codebase patterns, ensuring seamless integration...

Description: Deliver production-quality code for a requested task: plan → implement → verify → code review.

Implémente le code selon le plan validé, en respectant les conventions du projet. Utiliser après validation du plan, qua...

Pickle Rick's "God Mode" Implementation Skill. Executes technical plans with rigorous verification. Use when you are rea...

Implements production code for PHP/CakePHP applications based on functional design specifications

This skill should be used when the user asks to 'implement', 'write code', 'build a feature', 'create a function', 'add...

Implement development tasks in safe, reviewable increments. Use when the user wants code changes executed with clear seq...

Suggest improvements to existing code including refactoring opportunities, performance optimizations, and modernization....

Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using...

Code Injection Detector - Auto-activating skill for Security Fundamentals.Triggers on: code injection detector, code inj...

Educational code development skill that teaches programming concepts while building applications. Use when the user want...

Turn a noisy inbound request into a bounded intake artifact and an explicit next runx lane.

Cross-language read-only audit engine for production hardcode and leaked mocks/fake data in frontend, backend, mobile, t...

Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and f...

Code understanding tool selection. Use when exploring architecture, finding definitions, tracing call chains, assessing...

Use when dependency, call-chain, blast-radius, architecture, domain-flow, or unfamiliar-codebase analysis needs an optio...

Bridge between different computational materials science codes. Convert input/output formats, interface with post-proces...

Dual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), fina...

Efficient codebase investigation for rapid-go. Use when understanding existing code before modifications, tracing reques...

On how a system actually behaves, read the source first; code is authoritative, prose and docs can be stale.

Iteratively find and fix issues until no new actionable findings remain.

The Ultimate Senior Fixer. Combines planning, specification, and coding into a single, high-speed execution mode for one...

Evaluate code layout quality based on accuracy, consistency, readability, and maintainability rather than aesthetics. Us...

Audit a codebase's maintainability against a 5-level scale (structure, duplication, dependencies, consistency, how hard...

Provides Django web framework expertise including project structure, models, views, admin, Celery tasks, testing, and Py...

Provides Go programming expertise, including language syntax, idiomatic patterns, concurrency, and standard library usag...

Formate avec Prettier, lint avec ESLint (auto-fix) les fichiers modifiés. Si tout est propre, propose un commit des corr...

Run linters according to repository guidelines. Use immediately after creating or modifying code, or before committing c...

Run Python (ruff) and JavaScript (Biome) linting.

Use when the user wants the log statements in code standardized — audit and fix existing logging, correct log level / me...

Fix bugs, optimize performance, and maintain code quality in CClean-Killer. Use when asked to fix detection issues, fals...

Create, update, and review code-map and spec documents for features. Use this skill to document code execution flows, tr...

Atua como Especialista Sênior em Mapeamento de Aplicações, Código, Fluxos, Infraestrutura, Kubernetes, Nuvem e Grafos de...

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Ant...

Runs Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate reposi...

Runs Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate reposito...

Runs DeepSeek Harness headlessly for bounded repository tasks. Use when the user asks to delegate analysis or implementa...

Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini C...

Runs GitHub Copilot CLI programmatically for repository analysis and coding tasks. Use when the user asks to delegate wo...

Runs Hermes Agent in one-shot mode for bounded local tasks. Use when the user explicitly asks to delegate work to Hermes...

Runs Kimi Code in non-interactive prompt mode and parses its event stream. Use when the user asks to delegate a bounded...

Runs MiniMax Code headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to MiniMa...

Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a...

Runs OpenCode non-interactively for repository analysis and coding tasks. Use when the user asks to delegate work to Ope...

Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bo...

Runs the Code Mate Qoder CN CLI non-interactively with structured output. Use when the user asks to delegate a bounded c...

Runs Qwen Code headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Qwen Code...

Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety,...