Каталог навыков агентов

Use when reviewing code for security vulnerabilities, conducting threat modeling, ensuring SLSA compliance, or performin...

Review JSON serialization for scenes, prefabs, and components. Use when: (1) implementing serializable components, (2) d...

This skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "s...

This skill should be used when the user asks about "how sprints work", "sprint phases", "iteration workflow", "convergen...

int swooleprocess::kill($pid, $signo = SIGTERM);

Task decomposition, dependency analysis, and parallel execution orchestration. Use when breaking down features into task...

Test-Driven Development combined with emergent playtesting for Quest Keeper AI. Use when running playtest sessions, writ...

Microsoft Teams.ai integration patterns for dx-toolkit - Memory API, Anthropic SDK, MCP client setup

Terraform infrastructure-as-code patterns for AWS and Azure provisioning. Use when creating or modifying .tf files, writ...

Design, implement, and maintain high‑value TypeScript test suites using popular JS/TS testing libraries. Use this skill...

Microservices architecture for Tzurot v3 - Service boundaries, responsibilities, dependency rules, and anti-patterns fro...

BullMQ and async patterns for Tzurot v3 - Job queue architecture, Discord interaction deferral, idempotency, retry strat...

Railway deployment operations for Tzurot v3 - Service management, log analysis, environment variables, health checks, an...

Documentation maintenance for Tzurot v3 - Updating CURRENT_WORK.md, folder structure, and keeping docs current. Use at s...

Git workflow for Tzurot v3 - Rebase-only strategy, PR creation against develop, commit message format, and safety checks...

Security best practices for Tzurot v3 - Secret management, AI-specific security (prompt injection, PII scrubbing), Econo...

Meta-skill for writing and maintaining Claude Code skills. Use when creating new skills, updating existing skills, or re...

Use when writing tests, debugging test failures, mocking dependencies, or using fake timers. Covers Vitest patterns, moc...

官网：https://www.maniskill.ai/research

Guide for Vercel AI SDK v5 implementation patterns including generateText, streamText, useChat hook, tool calling, embed...

Verify a CVlization inference example is properly structured, builds successfully, and runs inference correctly. Use whe...

Verify a CVlization training pipeline example is properly structured, can build, trains successfully, and logs appropria...

Technical support and database management for OpenLink Virtuoso Server with RDF Views generation, SPARQL queries, and co...

Generate VSCode color themes, package them as .vsix files, and install to VSCode. Use when creating custom VSCode themes...

Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS s...

为太阳神三国杀和FreeKill生成Lua代码的小工具

Preferred: JavaScript and TypeScript, Pug, CSS (SCSS), HTML

Use when adding a new framework/stack to create-faster CLI tool - addresses copy-first mentality, incomplete implementat...

Claude Code architecture advisor. Classifies knowledge and delegates to appropriate skills. Use when deciding where to p...

Create and manage agents (orchestrators, skills, sub-agents). Use when user mentions "create agent", "build agent", "rec...

This skill enables you to design, build, and validate AgenticFlow automation workflows from natural language requirement...

Create and maintain AgentV YAML evaluation files for testing AI agent performance. Use this skill when creating new eval...

AI4PKM helper for onboarding guidance, quick help, and Gobi Desktop/CLI workflow integration.

Use this skill when designing REST, GraphQL, or gRPC APIs. Provides comprehensive API design patterns, versioning strate...

Compare LLM models using the Artificial Analysis API. This skill should be used when the user asks to compare AI models,...

Create Astro/Starlight MDX content pages. Use when the user says "write a new article", "add a blog post", "create conte...

Audit a checkpoint specification for realism and design decision forcing. Reviews specs to remove hand-holding, hidden c...

Better-auth integration for authentication. Use when implementing login, registration, protected routes, or email verifi...

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple se...

Diagnose and troubleshoot bitcoin-auth token generation and verification issues. This skill should be used when users en...

Create a new blog post for dabase.com using Hugo with SEO-friendly title and description

Create engaging, SEO-optimized blog posts for any industry or topic

This skill enables web searching using Brave Search API directly via curl. Use when searching for current information, n...

Quickstart SDK for INDA HR API v2 integration

Debugs Buck2 build failures systematically by analyzing error logs, checking common issues (cache, visibility, cycles),...

Create Buck2 tests with local resources (processes, services, databases) using LocalResourceInfo and ExternalRunnerTestI...

Scaffolds new Buck2 projects with proper BUILD/PACKAGE files, SPDX headers, and depot shims. Use when creating new Rust...

Runs common Buck2 queries for dependency analysis, target inspection, and build graph exploration. Use when investigatin...

This skill should be used when determining which Buck2 targets are affected by code changes for incremental builds and t...

Comprehensive testing workflow that should be used proactively after ANY code changes. Covers immediate testing, recursi...

Builds AI agents on Cloudflare using the Agents SDK with state management,real-time WebSockets, scheduled tasks, tool in...

Use when creating reusable GitLab CI/CD configurations, building component catalog entries, or packaging pipeline templa...

Builds remote MCP (Model Context Protocol) servers on Cloudflare Workerswith tools, OAuth authentication, and production...

Use when working with C3 architecture docs - navigating, understanding, designing, or auditing.Triggers: "C3", "architec...

Classify a change set as behavior vs structure, then recommend the correct PR label (change:behavior or change:structure...

Generate a Keep a Changelog entry from git commits

Use when live coding music with SuperCollider via ClaudeCollider MCP server.

Sync auto-approved permissions from all community-patterns directories (including community-patterns-2, -3, etc.) to the...

Clean Architecture principles for Modular Monolith with bounded contexts and minimal shared kernel. **ALWAYS use when wo...

Generate CLI demo GIFs using vhs (Charmbracelet). Use when creating terminal recordings for README files or documentatio...

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering renderi...

Build Optimizely CMS components for Astro v5. Use when creating/modifying components, pages, experiences, or working wit...

Code annotation requirements for pikru. Use when writing or porting Rust functions from C code. All ported functions mus...

Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments pa...

Codebase organization for pikru. Use when you need to find where specific functionality lives.

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creat...

Automate the workflow from creating a branch to opening a GitHub pull request. Use when the user says "create a PR", "co...

Community superstitions - unverified observations from pattern development. Use when encountering undocumented edge case...

ZSH completion system patterns and conventions. Use when implementing custom completion handling, writing completion fil...

Vitest browser mode component testing. Use for testing Svelte 5 components with real browsers, locators, accessibility p...

Codebase analysis using code-index-mcp for indexing and ast-grep for AST patterns. Extracts structural patterns, depende...

Operate the Agent Hive Cortex orchestration engine. Use this skill when running Cortex commands, analyzing project depen...

Generate public-facing documentation for a connector targeted at end users.

Engage in critical thinking by questioning assumptions, exploring alternative perspectives, and uncovering latent topics...

Use when Konflux pipelines fail, are stuck, timeout, or show errors like ImagePullBackOff. Covers PipelineRun failures,...

Use when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - cover...

Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative sh...

Enter and manage Deep Work sessions in Agent Hive. Use this skill when starting a focused work session on a project, gen...

This skill enables GitHub repository documentation exploration using DeepWiki API directly via curl. Use when researchin...

Deploy and update patterns. Use when deploying new patterns, updating existing deployments, or testing syntax. Includes...

Automated contract verification, detection, and remediation across multiple languages using formal preconditions, postco...

Use this skill when creating or evolving design systems for applications. Provides design token structures, component ar...

CSS custom property architecture, theme systems, design token organization, and component library integration. Use when...

Challenge and stress-test ideas through adversarial thinking. Use when user wants to "poke holes", "challenge this", "wh...

Skill for analyzing and improving compliance in the dismech knowledge base. Use this skill when checking disorder file c...

Skill for validating and repairing evidence references in the dismech knowledge base. Use this skill when working with e...

Skill for adding and validating ontology term references in the dismech knowledge base. This skill should be used when w...

Implements CRDT (Conflict-Free Replicated Data Types) for distributed state management with automatic conflict resolutio...

Research and document write/create APIs of a source system to enable write-back testing functionality.

Use when documenting stacks, databases, or ORMs in create-faster MDX docs - focuses on technical changes and what we add...

> 文档更新于2018/12/29，点击查看更新日志。

Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke...

Interact with a running Emacs instance via MCP. Use this skill when the user asks to interact with Emacs buffers, set up...

Svelte 5 error handling. Use for error boundaries, async await expressions, loading states, and form errors.

EVE Online ESI API patterns and zkillboard integration. Covers ESI endpoints, authentication, data models, zkillboard Re...