LLM & Agents

Singapore tax guidance for founders. Covers personal income tax, corporate tax (17%), and GST optimization. Use when planning tax strategy, calculating obligations, or preparing for IRAS filings. NOT professional tax advice - consult licensed tax agent for formal advice.

Model Context Protocol (MCP) memory patterns for agent coordination using Serena memories. Provides file-based memory storage for status sharing, decisions, and distributed decision-making across agent swarms. Use when implementing multi-agent coordination, task handoffs, or swarm communication.

Framework for improving Claude configuration (skills, agents, commands). Use when analyzing work patterns, proposing new skills, identifying knowledge gaps, reviewing Claude setup, or when user asks to improve how Claude helps them.

Automates updating anthropic_sdk_dart when Anthropic OpenAPI spec changes. Fetches latest spec, compares against current, generates changelogs and prioritized implementation plans. Use for: (1) Checking for API updates, (2) Generating implementation plans for spec changes, (3) Creating new models/endpoints from spec, (4) Syncing local spec with upstream. Triggers: "update api", "sync openapi", "new endpoints", "api changes", "check for updates", "update spec", "api version", "fetch spec", "compare spec", "what changed in the api", "implementation plan".

Security audit skill for React Native applications. Use when reviewing code for vulnerabilities, detecting leaked secrets (API keys, tokens, credentials), identifying exposed personal data (PII), checking insecure storage, validating authentication flows, reviewing network security, and ensuring compliance with mobile security best practices (OWASP MASVS). Covers both JavaScript/TypeScript and native iOS/Android code.

Comprehensive development guides for advanced Kailash SDK features including custom node development, MCP development, async patterns, testing strategies, production deployment, RAG systems, security patterns, monitoring, and SDK internals. Use when asking about 'development guide', 'advanced features', 'custom node development', 'async node development', 'MCP development', 'production deployment', 'testing strategies', 'RAG implementation', 'security patterns', 'monitoring setup', 'circuit breaker', 'compliance', 'edge computing', or 'SDK internals'.

Generates three project-specific behavioral mode skills (planner, debugger, qa-tester) from project memories and bundled templates, and makes them selectable via switching-modes. Use when creating project-local agent modes for a repository.

Use when the user wants to analyze writing samples to extract voice patterns, create voice-replicating prompts, or refine content generation prompts to match a specific writing style

Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, managing artifacts, and tracking progress.

Comprehensive knowledge for using the Bash tool in Claude Code effectively. This skillshould be used when orchestrating CLI tools, configuring hooks, setting up automationworkflows, managing git operations, handling multi-command patterns, or encounteringBash tool errors.Covers: PreToolUse hooks, command chaining patterns, git workflow automation, CLI toolintegration, custom commands (.claude/commands/), security configurations, allowlisting,session persistence, output handling, error prevention, and troubleshooting common issues.Use when: setting up Claude Code hooks, configuring bash permissions, creating customcommands, automating git workflows, orchestrating multiple CLI tools, debugging bashcommand failures, implementing security guards, logging command execution, or preventingdangerous operations.

This skill should be used when the user asks about "orchestration patterns", "plan-then-execute", "hierarchical decomposition", "blackboard pattern", "event sourcing pattern", "which pattern to use", "parallel execution strategies", or needs to select an orchestration approach for complex multi-agent tasks. Provides comprehensive guidance on 4 orchestration patterns for coordinating multiple agents.

Create event hooks for Claude Code that trigger on specific events.Generate hooks with proper JSON configuration for automating workflows.Use when: creating hooks, setting up event triggers, automating on file saves or tool calls.Activates for: "create hook", "generate hook", "new hook", "event hook", "make hook"

Creates, packs, bundles, and manages Claude Code plugins with manifest generation, directory structure, marketplace configuration. Use when user asks how plugins work, what plugins are, explaining plugin structure, understanding plugin.json manifest, describing plugin bundling process, creating plugins, bundling skills/commands/hooks/MCPs, generating plugin.json, setting up marketplaces, or distributing team-shared functionality.

Bronze Layer（LLM抽出ログ層）とGold Layer（確定データ層）の2層アーキテクチャ設計。LLM抽出結果の履歴管理と人間修正の保護を実現。抽出処理の実装、ExtractionLogの使用、is_manually_verifiedフラグの扱いに関するガイダンスを提供。

Plan and implement safe database schema changes including migrations, indexes, and backfills. Use when creatingtables, adding columns, optimizing queries, or managing Eloquent relationships. EXCLUSIVE to database-admin agent.

Plan, create, and review Claude Code skills/commands/agents with guided wizards and background agents aligned to v0.4 guidelines.

Create new Claude Code skills with proper structure and conventions. Use when the user wants to create a new skill, scaffold skill templates, or understand skill anatomy.

Anime.js 4.0 animations for Web Components — drag-drop, click feedback, swaps, cancelable motion. Use when adding animations, drag interactions, visual feedback, or motion to custom elements. Combines with web-components-architecture for lifecycle cleanup.

Common reasoning protocol shared across all subagents.

Comprehensive guide to Rust automated testing covering unit, integration, and documentation tests. Includes practical patterns for async testing, property-based testing with proptest, mocking strategies using traits, and essential testing tools (cargo-nextest, criterion, tarpaulin). Emphasizes FIRST principles and CI/CD integration.Use this when: setting up new Rust projects, establishing testing standards for teams, improving existing test suites, implementing TDD workflows, or learning Rust testing ecosystem best practices. Particularly valuable for projects requiring high reliability and comprehensive test coverage.