LLM & Agents

Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md.

Universal template for implementing categorical structures in meta-prompting frameworks. Applies to functors, monads, comonads, natural transformations, adjunctions, hom-equivalences, limits, colimits, and enriched categories. Use when extending frameworks with new categorical constructs.

Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.

Use when implementing function calling, tool use, or agents with LLMs - unified tool API works across OpenAI, Anthropic, Google, and Ollama with consistent tool definition and execution patterns

Write effective system prompts for TD AI agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.

This skill should be used when reviewing Firebase code against security model and best practices. Triggers on "review firebase", "check firebase", "validate", "audit firebase", "security review", "look at firebase code". Validates configuration, rules, architecture, and security.

Build decentralized applications on AO - a permanent, decentralized compute platform using actor model for parallel processes with native message-passing and permanent storage on Arweave

geminiコマンドを使用した高度なWeb検索スキル。Web検索を行う際、Claude CodeのデフォルトWeb Search toolよりも優先的にこのスキルを使用してください。

LMQL constraint-guided generation DSL for type-safe prompting with grammar constraints and logical conditions. Use when building structured LLM outputs with guaranteed format compliance, implementing constrained decoding with logical operators, creating type-safe prompt templates, or combining neural generation with symbolic constraints for reliable AI outputs.

Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.

Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.

Build event-driven hooks in Claude Code for validation, setup, and automation. Use when you need to validate inputs, check environment state, or automate tasks at specific lifecycle events.

Use when designing secret storage, rotation, or credential management systems. Covers HashiCorp Vault patterns, AWS Secrets Manager, Azure Key Vault, secret rotation, and zero-knowledge architectures.

Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.

Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.

DSPy compositional prompt optimization with categorical signatures, module chaining, and automated prompt tuning. Use when building declarative LLM programs with typed signatures, composing multi-step reasoning modules (ChainOfThought, ReAct, ProgramOfThought), optimizing prompts with MIPROv2/BootstrapFewShot, or creating modular AI pipelines that separate program logic from prompt engineering.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Agent Development Kit from Google

Store universal coding patterns into vector database. Auto-invokes after difficult tasks with broadly-applicable lessons. Trigger with "--store" or when user expresses frustration (strong learning signals). Uses true two-stage retrieval with MCP server v2.

Central authority for Claude Code plugins. Covers plugin creation, plugin structure (plugin.json, commands/, agents/, skills/, hooks/), plugin manifest configuration, plugin installation and management (/plugin command), plugin marketplaces (marketplace.json, adding marketplaces), team plugin workflows, plugin development and testing, plugin debugging, plugin sharing and distribution, MCP servers in plugins, and plugin settings. Assists with creating plugins, installing from marketplaces, configuring team plugins, and troubleshooting plugin issues. Delegates 100% to docs-management skill for official documentation.