Каталог навыков агентов

Quick reference for operating within jonmagic's second-brain workspace. Use when working with files in the brain reposit...

Use when starting any feature, project, or design work. Guides collaborative design refinement through incremental quest...

Facilitate structured brainstorming using parallel sub-agents to explore idea spaces. Use for IDEATION/CONCEPTUAL WORK O...

Use when the user asks to compare branches, analyze git diffs, review changes between branches, update specifications ba...

Expert in brand identity, logo design, and visual brand systems

Use this skill when creating, modifying, or reviewing API endpoints and routes. This includes SDK routes (/v1/*), Dashbo...

Use this skill when developing, implementing, or modifying Go backend code for the Brokle platform. This includes creati...

Use this skill when working with Brokle's domain-driven architecture, including creating new domains, modifying domain e...

Use this skill when implementing, reviewing, or debugging error handling in the Brokle codebase. This includes repositor...

Use this skill when developing, implementing, or modifying Next.js/React frontend code for the Brokle web application. T...

Use this skill when creating, running, or managing database migrations for PostgreSQL or ClickHouse. This includes creat...

Use this skill when writing, reviewing, or improving tests for the Brokle platform. This includes creating service tests...

Browser automation via Puppeteer MCP for JS-rendered content

Builder user experience systems for Three.js building games. Use when implementing prefab/blueprint save/load, undo/redo...

Router for 3D building game mechanics in Three.js. Use when creating survival games, sandbox builders, base builders, or...

Use when generating multiple curriculum-aligned concept files in parallel (5+ concepts) - researches curriculum, creates...

Analyzes JavaScript bundle sizes, identifies large dependencies, and suggests optimizations for webpack, vite, rollup. U...

Advanced memory and knowledge management workflows for Byterover MCP Server. Use when creating implementation reports wi...

Conduct a Cabinet meeting when User asks for "Cabinet meeting", "convene the Cabinet", "get perspectives from [agents]",...

Build queryable capability graphs from manifests using Codex for relationship inference between skills, resources, and c...

End-to-end career support for job seekers at all levels. Optimizes LinkedIn profiles, rewrites CVs for ATS systems, prov...

Invoke for Carmenta user-facing copy and voice review

Game building mechanics case studies and decision frameworks. Use when designing building systems, evaluating trade-offs...

Reads CLAUDE_NOTES.md to provide context about recent work, decisions, and current state of the homelab repository. Use...

Claude Code Ecosystem Architect - Master skill for creating Claude Code ecosystem components (skills, commands, hooks, s...

Plug in, Receive good vibes.

Determine what needs modification and identify potential side effects of changes. Use before implementing changes to und...

Apply changelog automation and semantic versioning patterns using Changesets or semantic-release: conventional commits,...

Update CHANGELOG.md and TEST-CHANGELOG.md with new entries following Keep a Changelog format and token optimization prin...

Implement chaos engineering practices and tools for resilience testing

Check bash script syntax without executing. Use before committing bash scripts or when verifying syntax correctness.

Check for pending Codex (GitHub AI) feedback on current branch's PR. Use to review and address AI suggestions before mer...

Launch and control Chrome with AT-SPI2 accessibility for browser automation. Use when asked to start chrome, open browse...

Cinder Usage Rules

Maintain Claude Code memory hygiene by auditing, organizing, updating, and optimizing memory files in `.claude/memory/`....

"Comprehensive guide for building, testing, and distributing Claude Code plugins including slash commands, Agent Skills,...

Use when user says "resume session", "what did I work on", or "find conversation about [topic]". Automatically searches,...

Enforce Claude Compass development standards and best practices. This skill should be used when writing or modifying cod...

Look up examples and patterns from the official Anthropic Claude Cookbooks repository. Use when you need reference imple...

path: /v1/skills/{skillid}

Shared utility script for getting Claude PID and Session ID. Source this in other scripts to access CLAUDE_PID and SESSI...

Use when implementing Claude API cost tracking, monitoring token usage, displaying cost metrics in Settings, or user ask...

Use when testing iOS apps on simulator, capturing screenshots for validation gates, automating UI testing with expo-mcp...

Use when starting Metro bundler for Expo development, debugging Metro errors, or enabling expo-mcp local capabilities -...

Use when executing validation gates 3A, 4A, or 6A-E, verifying phase completion with expo-mcp visual testing, or encount...

PlayFab MCP server with CI/CD and release-please

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...

Agent Skill（Claude Skill）是 Anthropic 推出的一种基于文件系统的模块化能力标准。它本质上是一种“渐进式披露” (Progressive Disclosure)的提示词管理机制。

在 only-danmuku 的 CleanDDD Kotlin 项目中编写或修改聚合/命令/查询/API 端点/事件/防腐层 Client/仓储/配置/测试时使用；遵循 代码实现规约.md 与 design/_gen + genDesig...

基于 cleanddd-requirements-analysis 结果输出 CleanDDD 建模蓝图，并在 only-danmuku 的 iterate/feature 目录交付 *_gen.json 建模元素与 *_update.sq...

需求澄清与拆解，识别干系人并将需求条目标注所属对象与业务实体；仅产出结构化需求描述，不做建模定义，可作为后续建模输入

Simplify code and remove legacy/backcompat shims while preserving behavior. Use when asked to clean up or simplify code.

Master CLI navigation and code exploration using modern command-line tools. Use this skill when navigating repositories,...

Apply modern CLI development toolchain patterns: Commander.js (default), oclif, Ink for Node.js command-line tools. Use...

Standalone CLI bridge - launch external AI CLIs (gemini, codex, claude) directly without MCP server. Use when you need t...

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents...

Delegate repetitive tasks to specialized agent to preserve context. Use when user asks to fix linting errors, fix diagno...

Master code organization - encapsulation with wrapper methods, file modularity (split >150 lines), one function one resp...

Proactive code health monitoring and quality gate enforcement. Use when validating code changes, reviewing PRs, or ensur...

Setup ESLint with Airbnb TypeScript config and Prettier formatter for code quality enforcement. Use when setting up new...

Use when reviewing code quality, before refactoring, when complexity increases, when code feels "hard to change", during...

Extract and maintain company-specific coding best practices from PR review comments. Use when the user requests to analy...

Identify relevant files, understand architecture patterns, and find code by functionality. Use when you need to understa...

Fix bugs using TDD starting from README + Issue (following codegen-test), aligning with existing implementation conventi...

Perform refactoring using TDD starting from README + Issue (following codegen-test), aligning with existing implementati...

A skill for writing Go tests in a TDD workflow. Follow README/Issue requirements and existing test conventions, add a ba...

This skill should be used when CodeRabbit code review feedback needs to be processed and fixed systematically. Use after...

MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use...

Automated code review workflow using OpenAI Codex CLI. Implements iterative fix-and-review cycles until code passes vali...

Collect pending worktree commits into a PR for review. Use this skill when subdirectory worktrees have accumulated 4-7+...

Implement or adjust the core color pipeline (parse, normalize, scale, resolve) guided by src/planning/spec-v0.3.md and s...

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands,...

Load skill knowledge via skill-summarizer agent

Interactive skill creation wizard for Claude Code Skills. Guides you through defining skill metadata (name, description)...

Create well-formatted git commits with conventional commit messages and emoji. Use when user asks to commit changes, sav...

Comprehensive guide for creating React components in the squared package and squareone app. Use this skill when creating...

{% include announce %}

{% include announce %}

Comprehensive concurrency and parallelism patterns for multi-threaded and async programming. Use when implementing async...

Pre-flight verification for scheduling constraint development. Use when adding, modifying, or testing constraints to ens...

--8<-- "includes/ccai-api-back-link.md"

Comprehensive content strategy review from reader's perspective. Acts as Chief Web Editor + Technical Writer to audit si...

Assembles relevant context for agent spawns with prioritized ranking. Ranks packages by relevance, enforces token budget...

Waypoint plans methodology and session survival patterns for Claude Code. Use when working on long-running features, nee...

Automatically save and restore development context to minimize cognitive load when resuming work. Use when switching tas...

Generate comprehensive context-setting markdown files for coding tasks by intelligently exploring codebase and structuri...

Implement APCA/WCAG2 contrast requirements and solver behavior per src/planning/spec-v0.3.md and src/planning/roadmap-v0...

Generates commit messages following Conventional Commits 1.0.0 specification. Use when committing changes, staging files...

Enforces conventional commit message and branch naming conventions with specific prefixes (feat, fix, docs, style, refac...

Find and resume Claude Code conversations by searching topics or filtering by date. Returns session IDs and project path...

Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decision...

Expert in writing compelling copy for web, marketing, and product

Install Cordon, a deterministic layer between untrusted content and agent actions, and verify the harness actually calls...

Generate and analyze test coverage reports. Use to identify coverage gaps, track coverage trends, and ensure quality thr...

Integrate coverport into Go repositories with Tekton pipelines to enable e2e test coverage collection and upload to Code...

Create memory files to track important learnings, decisions, and system changes. Use when implementing major features, m...