Essential command-line tools and system utilities.
Comprehensive research workflow for feature implementation planning. Use this skill when gathering information about how to implement features, understanding technology choices, researching APIs and libraries, or exploring implementation approaches. Combines web search for general research with Context7 for API documentation, and includes structured questioning to clarify requirements.
Comprehensive guide for building functional tools for LiveKit voice agents using the @function_tool decorator. Use when creating tools for LiveKit agents to enable capabilities like API calls, database queries, multi-agent coordination, or any external integrations. Covers tool design, RunContext handling, interruption patterns, parameter documentation, testing, and production best practices.
Multi-round web search with low-frequency query generation. Prioritize GitHub/StackOverflow for actionable code, extract AI Overview insights, and perform deep link analysis. Use proactively for complex problems requiring external knowledge or when stuck on implementation challenges.
Connect to 100+ popular APIs using natural language - automatic authentication, request building, and response parsing
This skill should be used when the user asks to "create background task", "add async job", "implement task queue", "schedule periodic task", "use Celery", "use ARQ", "process async", or mentions background processing, task queues, job scheduling, workers, or async jobs. Provides multiple task queue framework patterns.
Automatically manage user's personal memory, context, and decision tracking. Invoked when context updates are needed or decisions are made.
Transforms conversations and discussions into structured documentation notes in Obsidian. Captures insights, decisions, and knowledge from chat context, formats with appropriate templates and frontmatter, and saves to vault with proper tagging, linking, and organization for easy discovery.
Expert guidance for creating, building, and using Antigravity subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
Quick reference cheatsheets for Kailash SDK patterns, nodes, workflows, and best practices. Use when asking about 'quick tips', 'cheat sheet', 'quick reference', 'common mistakes', 'node selection', 'workflow patterns library', 'cycle patterns', 'production patterns', 'performance optimization', 'monitoring', 'security config', 'multi-tenancy', 'distributed transactions', 'saga pattern', 'custom nodes', 'PythonCode data science', 'ollama integration', 'directoryreader patterns', or 'environment variables'.
Use this skill when users ask to build, create, design, or improve a Claude Code skill. This includes requests like "help me create a skill", "build a skill for X", "design a new skill", or "improve my existing skill". This skill provides step-by-step guidance for creating effective skills with specialized knowledge, workflows, and tool integrations.
Use PROACTIVELY for comprehensive, multi-source research combining web browsing, codebase exploration, and third-party code analysis. Orchestrates multiple specialized agents using Graph of Thoughts methodology. Ideal for: complex technical questions, comparing documentation vs implementation, understanding library internals, performance analysis, or resolving contradictory information.
Expert guidance for creating strands-cli workflow specifications (YAML/JSON). Use when creating, modifying, or troubleshooting strands-cli specs for: (1) Multi-step agent workflows (chain, routing, parallel, graph patterns), (2) Tool configuration (python_exec, http_request, custom tools), (3) Runtime and provider setup (Bedrock, OpenAI, Ollama), (4) Input/output handling and templating, or (5) Debugging validation errors
Plan, create, and review Claude Code skills/commands/agents with guided wizards and background agents aligned to v0.4 guidelines.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Analyzes codebases and conversation context to recommend relevant existing skills and suggest valuable custom skills to create. Use when exploring a project for the first time, when asked what skills would be useful, or when seeking to optimize workflow for a specific codebase.
FirstSpirit CMS template development using fs-cli. Helps set up fs-cli environment, export templates from FirstSpirit server, modify templates with Claude Code, and import changes back to server. Use when working with FirstSpirit templates, CMS development, or when user mentions fs-cli, FirstSpirit, or template synchronization.
Converts natural language descriptions into structured JSON schemas for Nano Banana Pro (Gemini 3 Pro Image). Use when creating marketing images, UI mockups, diagrams, data visualizations, or social media graphics that require precise control and reproducibility. Supports five schema types for product photography, interfaces, flowcharts, charts, and social content.
Evaluate agent and LLM outputs. Use when asked to evaluate agent performance, build evaluation frameworks, implement LLM-as-judge, compare model outputs, create rubrics, mitigate evaluation bias, or design evaluation pipelines and quality gates.
Use this skill to coordinate agent execution, validate sequential workflow compliance, and manage agent handoffs. This skill provides deterministic coordination between agents using bash scripts and validation systems. Replaces LLM-based coordination with reliable script-based enforcement.
Gemini CLI integration for context offloading. Use when calling gemini CLI, delegating large file analysis, summarizing code, or needing second opinions. Covers correct syntax, flags, environment variables, and common errors. Keywords: gemini, context offloading, large files, summarize, second opinion, gemini-assistant, gemini CLI.
