LLM & Agents

Publish gate secrets scanning. Use for: safe_to_publish, scan for secrets, redact in-place. Determines publish gate status. Scan files for secrets (locations only - NEVER prints secret content). GitHub tokens, AWS keys, private keys, bearer tokens. Use ONLY in secrets-sanitizer. Invoke via bash .claude/scripts/demoswarm.sh secrets scan|redact.

Multi-LLM parallel research with query decomposition and synthesis

Advanced tmux operations bundle for Miyabi multi-agent AI orchestration.Includes auto-recovery, health monitoring, task queue integration, and MCP server coordination. The definitive skill for AI agent workflows.

Multi-agent coordination patterns for OpenCode swarm workflows. Use when working on complex tasks that benefit from parallelization, when coordinating multiple agents, or when managing task decomposition. Do NOT use for simple single-agent tasks.

Tool usage patterns for non-prompting file operations - use Glob, Read, Grep instead of Bash commands to avoid user interruptions in all agents and commands

Selects and configures agents from the agents repo based on PRD tech stack.Runs after task decomposition, before specification generation.

CLAUDE Framework coding standards for code quality, naming conventions, error handling, security, testing, database, and logging

Agent Skill: Guide for structuring Netresearch skill repositories. Use when creating skills, standardizing repos, or setting up composer/release workflows. By Netresearch.

Meta-skill that teaches how to design Claude Code skills following the Box Factory philosophy. Helps you understand when to create skills, how to structure them for low maintenance, and how to add value beyond documentation. Use when creating or reviewing skills.

Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.

Macroeconomic and market regime analyst. Monitors Fed policy, inflation, GDP, unemployment, and global economic trends to determine overall market risk appetite and sector rotation strategies.

Generate pytest test templates for LiquidationHeatmap modules following TDD patterns. Automatically creates RED phase tests with fixtures, coverage markers, and integration test stubs.

Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.

Use when the user asks for a plan or the task is complex/ambiguous. Enforces AGENTS.md workflow and encourages loading other relevant skills.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Analyzes and optimizes database queries for performance and efficiency

Use when educators need to validate if their lesson plan covers all 3 Delegation subcategories (Problem/Platform/Task Awareness).Analyzes lesson plans and provides objective scores (0-10) with actionable feedback.Works in Claude.ai, Claude Code, and API for maximum portability.

Smart routing wizard for creating skills, agents, commands with complexity-based skill loading

Generates integration tests for system components and workflows

Generate compelling cover images and in-article illustrations for technical articles using the imagen CLI tool. Use when asked to "generate images", "create cover image", "make article illustrations", "create visual assets", or "add images to article". Handles both high-impact conceptual cover images and technical diagrams/illustrations for specific concepts. Includes prompt engineering best practices and SEO-friendly image integration.