Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md improvements, and fetches latest docs on-demand. Use when user wants to optimize their Claude Code workflow, create configurations (agents/skills/commands), or set up project documentation.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

Master Moon Dev's Ai Agents Github with 48+ specialized agents, multi-exchange support, LLM abstraction, and autonomous trading capabilities across crypto markets

Android-specific code review workflow additions for Bitwarden Android. Provides change type refinements, checklist loading, and reference material organization. Complements bitwarden-code-reviewer agent's base review standards.

Retrieval-augmented generation (RAG) skill for the D&D 5e System Reference Document (SRD). Use when answering questions about D&D 5e core rules, spells, combat, equipment, conditions, monsters, and other SRD content. This skill provides agentic search-based access to the SRD split into page-range markdown files.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

This skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is determined to be vague and requires systematic research, question generation, and execution guidance.

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.

Hugging Face integration. Manage Models, Datasets, Spaces. Use when the user wants to interact with Hugging Face data.

Google Gemini integration. Manage Users, Conversations. Use when the user wants to interact with Google Gemini data.

Anthropic integration. Manage data, records, and automate workflows. Use when the user wants to interact with Anthropic data.

Open Policy Agent integration. Manage data, records, and automate workflows. Use when the user wants to interact with Open Policy Agent data.

OpenAI integration. Manage Assistants, Files. Use when the user wants to interact with OpenAI data.

Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.

Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.

Reusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM queries. Structured prompts for consistent results.

Build multi-agent AI systems for construction estimation. Use CrewAI/LangGraph to orchestrate specialized agents: QTO agent, pricing agent, validation agent. Automate complex estimation workflows.

Extract structured data from construction documents using LLMs. Process RFIs, submittals, contracts, specifications. Convert unstructured PDFs to structured JSON/Excel.

Build n8n pipeline for automated cost estimation from Revit/IFC using DDC CWICR database and LLM classification.

Semantic search in DDC CWICR construction database using vector embeddings. Find similar work items and resources for cost estimation.

Ultracite multi-provider linting/formatting (Biome, ESLint, Oxlint). Use for v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, or encountering configuration, type-aware linting, monorepo errors.

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh perspective with synthesis.

Google Gemini CLI for second opinions, architectural advice, code reviews, security audits. Leverage 1M+ context for comprehensive codebase analysis via command-line tool.

Dynamic MCP server discovery and code-mode execution via central registry. Use for multiple MCP integrations, tool discovery, progressive disclosure, or encountering MCP context bloat, changing server sets, large tool sets.

Google Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering immutability errors, quota issues, polling failures. Supports Gemini 3 Pro/Flash (Gemini 2.5 legacy).

Use when scala collections including immutable/mutable variants, List, Vector, Set, Map operations, collection transformations, lazy evaluation with views, parallel collections, and custom collection builders for efficient data processing.

Use when writing SOPs that require precise requirement levels using RFC 2119 constraint keywords (MUST, SHOULD, MAY). Covers proper usage of requirement keywords for deterministic agent behavior.

Use when Elixir OTP patterns including GenServer, Supervisor, Agent, and Task. Use when building concurrent, fault-tolerant Elixir applications.

Use when setting up or organizing Claude Code project memory (CLAUDE.md, .claude/rules/) for better context awareness, consistent behavior, and project-specific instructions.

Multi-agent code review with confidence-based filtering

Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.

Load MR context for the current branch using GitLab MCP tools

Load PR context for the current branch using GitHub MCP tools

Ingest the Project Intake Form and kick off Concept → Inception with agent assignments, accepts optional guidance to tailor process

Preflight issue bodies for prompt-injection and supply-chain risk before address-issues acts on them

Orchestrate SDLC phase gate validation with multi-agent review and comprehensive reporting

Generate behavioral specifications (Layer 3) from use cases and architecture documents using multi-agent orchestration

Address open issues using issue-thread-driven agent loops with 2-way human-AI collaboration

Enable agent loops to learn from similar past tasks and share patterns across loops

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

Regenerate CLAUDE.md for Claude Code with hook file architecture

AUTO-INVOKE for ANY AIWG capability question, framework/addon/extension query, steward routing, MCP profile, or when unsure where to start. ALWAYS consult before filesystem search on .claude/.factory/.codex/.warp/etc. AIWG core utilities quick reference — always-on framing, steward, index, meta operations.

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

Spawn sub-agent to process focused context and return structured result

Validate phase gate criteria with multi-agent review and generate pass/fail reports

Full multi-agent investigation workflow

Continuously identify, assess, track, and retire risks throughout the SDLC with register and RAG reporting

Orchestrate multi-agent artifact generation using the Primary Author, Parallel Reviewers, Synthesizer, Archive pattern

Interactive wizard that wires up @playwright/mcp end-to-end — detects the user's browsers, walks through Playwright MCP Bridge extension install, captures the per-install token, registers the MCP server in the AIWG registry with --extension and the env block, injects into the active provider's config, and verifies the connection.

Map source file structure into navigable sections with line ranges and summaries for efficient agent navigation

Scan source code and report agent-readiness metrics with actionable recommendations

Orchestrates issue-driven agent loops that post cycle status to issue threads and incorporate human feedback in each cycle.

View and configure agent loop settings — show, set, reset, and apply named presets

Launch an AIWG Mission — durable, audited dynamic agent orchestration toward a completion criterion. AIWG owns the conductor (activity-log, gates, best-output, checkpoint/resume, cost); native primitives drive worker mechanism. Surfaces as /aiwg-mission in Codex (AIWG-owned, no plugin dependency).

AUTO-INVOKE when user mentions knowledge base, wiki, KB, semantic memory, llm-wiki, knowledge ingest, document corpus. Knowledge-base framework quick reference — discovery phrases for KB ingest/health, semantic-memory kernel skills, llm-wiki profiles.

Execute a UAT plan against live MCP connections, tracking pass/fail per test and filing issues on failure

Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.

Generate a human-readable manifest for an AIWG skill chain — agent assignments, requires/ensures contracts, data flow, and parallelization opportunities.

Triage research-corpus artifacts for LLM residue, placeholder/template markers, unresolved citation markers, non-final experiment language, and submission risks. Per-REF scoring → pass / review / quarantine. Conservative — flags for human review, does not decide misconduct. Runs via `aiwg corpus integrity-scan`.

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping.

Orchestrate multi-agent teams across AIWG providers natively on Claude Code or emulated via Mission Control elsewhere

Scaffold a new agent definition file inside an existing addon or framework

Manage AIWG behavior bundles that bind reactive directives and toolset configurations to specific agent types

Discover MCP tools and generate a phased UAT plan with agent-executable test specifications

Manage the AIWG MCP server — start it, configure clients, and maintain the registered server registry

Manage the AIWG MCP server — start it, configure clients, and maintain the registered server registry

Generate an aggregate agent quality report from evaluation results, showing scores, regressions, and recommendations

Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance

Install plugins into Claude Code from the AIWG marketplace with registry lookup, download, and local deployment

Resume an interrupted agent loop from last checkpoint

Remove a previously installed Claude Code plugin and unregister it from the local plugin registry

Analyze LLM pipeline costs and generate concrete optimization recommendations with savings estimates

Run evaluation tests against an agent to assess quality and archetype resistance

Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt

Show status overview of all LLM inference pipelines in the current project

List installed Claude Code plugins with version, install date, and enabled status

Production prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback

Attach to a running agent loop's live output stream

Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them

Start an agentic session with pre-flight health checks, auto-repair, optional MCP injection, and provider launch

Abort a running agent loop and optionally revert changes

Check status of current or previous agent loop

Build or rebuild the SDLC artifact index for agent-navigable discovery

Show analytics and metrics from agent loop execution history

View and manage agent loop reflections and episodic memory

Expert guidance for Microsoft AutoGen multi-agent framework development including agent creation, conversations, tool integration, and orchestration patterns.

Expert guidance for LlamaIndex development including RAG applications, vector stores, document processing, query engines, and building production AI applications.

Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.

Expert guidance for working with Hugging Face Transformers library for NLP, computer vision, and multimodal AI tasks.

Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.