Create Hytale models and animations using Blockbench MCP tools. Use when working with Hytale character/prop formats, creating attachments, setting shading modes, using quads, or animating with visibility keyframes. Requires the Hytale Blockbench plugin to be installed.

Create and edit 3D models in Blockbench using MCP tools. Use when building geometry with cubes, creating meshes, placing spheres/cylinders, editing vertices, extruding faces, or organizing models with groups. Covers both cube-based Minecraft modeling and freeform mesh editing.

Create and manage PBR (Physically Based Rendering) materials in Blockbench using MCP tools. Use when working with texture_set.json files, creating normal/height/MER maps, configuring material properties for Minecraft Bedrock RTX, or setting up multi-channel texture workflows.

Create and paint textures in Blockbench using MCP tools. Use when creating textures, painting on models, using brush tools, filling colors, drawing shapes, applying gradients, managing texture layers, or working with UV mapping. Covers pixel art texturing, procedural painting, and UV manipulation.

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.

Orchestrates lively group discussions between installed BMAD agents or other personas. Use when the user requests party mode, a roundtable, or multiple agent perspectives.

Automate web browsers for AI agents using agent-browser CLI with deterministic element selection.

Continuous Linear monitoring daemon that runs within the agent context, using Linear MCP tools to fetch and update issues. Tracks seen issues, prompts user or auto-works through tasks.

Plan verification agent for the Buddy orchestrator. Performs 8-dimension goal-backward verification of implementation plans before execution begins. Ensures plans will achieve goals, not just look complete.

Planner agent for the Buddy orchestrator. Creates a detailed, file-by-file implementation plan with ordered steps, risks, and rollback strategy based on the research context and enhanced prompt. Includes must_haves derivation for goal-backward verification.

Reviewer agent for the Buddy orchestrator. Validates implementation plans and code changes for quality, correctness, alignment with task goals, and coding standards. Performs dimensional review with goal-backward verification. Scores output from 1-10 and approves or requests revisions.

Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected.

Document chunking strategies for RAG systems. Use when implementing document processing pipelines to determine optimal chunking approaches based on document type and retrieval requirements.

This skill should be used when the user wants to "create a claudeignore", "update claudeignore", "optimize context", "ignore folders", "reduce token usage", "set up .claudeignore", or mentions .claudeignore, context window optimization, or ignoring directories from Claude Code indexing.

Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.

Implementation/review workflow for approved plans. Route ACP-first, then CLI fallback. Use after explicit APPROVE.

Create Claude Code custom slash commands with proper structure, frontmatter, and best practices. Use this skill whenever the user wants to create a new command, add a slash command, build a custom command, or mentions "create-command", "new command", "add command", or "make a command" for Claude Code. Also trigger when the user wants to turn a workflow into a reusable command.

Apply compaction, masking, and caching strategies to optimize context windows. Use when reducing token usage or improving LLM context efficiency.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Copy an agent from Product Forge to user or project level

Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table

Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace

Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper for cross-document accessibility pattern detection, severity scoring, template analysis, and remediation tracking. Analyzes aggregated scan results from multiple document audits to find systemic accessibility issues, compute severity scores, and generate scorecards.

AI agent for CryptoQuant Pro 2.10 via Teneo Protocol. Use this skill when the user needs CryptoQuant Pro 2.10 via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

Generate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.

Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models. Activates for ML development tasks.

Enabling nullable reference types. Annotation strategies, attributes, common agent mistakes.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic corpora, or LLM-ready markdown organized from web sources.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.

AI agent for Google Search Agent via Teneo Protocol. Use this skill when the user needs Google Search Agent via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

Relationship-aware retrieval using graph traversal, entity anchors, community expansion, and hybrid vector plus graph search. Use when chunk similarity alone misses paths, entities, or subsystem context.

Reference for all GrepAI MCP tools. Use this skill to understand available MCP tools and their parameters.

Advanced search options in GrepAI. Use this skill for JSON output, compact mode, and AI agent integration.

Log a workflow mistake, fix its root cause, and graduate the lesson to learned memory. Use when the agent makes an error you want to prevent recurring.

This skill should be used when the user wants to "hand off", "create a handoff", "wrap up for the next session", "pass this to another agent", "continue from a handoff", "pick up where I left off", "resume a previous session", "load a handoff", or mentions handoff documents, session continuity, or task continuation.

A fundamental skill that demonstrates the basic execution of a Python script. It serves as a "Hello, World!" example for the skill system, verifying that the environment is correctly set up and that the agent can execute scripts.

When the user asks for a code review, PR review, or critical look at recent changes, consult this skill to decide whether to delegate to the code-review subagent and how to craft the prompt.

When the user asks to commit, check in, or save changes, consult this skill to decide whether to delegate to the commit subagent and how to craft the prompt.

This skill should be used when importing tasks from another Claude Code session's TaskList into the current session, enabling coordination across sessions without restarting.

Comprehensive guide for initializing or reorganizing agent memory into a deeply hierarchical file structure. Use when running /init, when user asks to set up memory, or when memory needs a major reorganization. Trigger phrases: "initialize memory", "set up memory", "populate memory", "build my memory", "memory init".

Use when All Jina AI APIs (Reader, Search, Embed, Rerank, and more) as powerful Unix CLI commands. Ideal for web scraping, semantic search, and RAG (Retrieval-Augmented Generation) workflows.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Patterns for ingesting knowledge into vector databases and RAG systems

Expert in LangGraph, the production-grade framework for building stateful, multi-actor AI applications. Use when building agent graphs, managing state, or implementing persistence with checkpoints.

Multi-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.

Diagnose and fix stalled agent loops using the joelclaw CLI. Use when loops appear stuck, stories aren't progressing, or the event chain broke. Triggers on "loop stalled", "why isn't the loop progressing", "diagnose loops", "fix stuck loop", "loop not moving", "what happened to the loop", "stories stuck at pending", or any request to debug loop infrastructure.

Use when creating releases for Claude Code plugin marketplaces. Supports independent plugin versioning - each plugin can be released separately. Triggered by "release", "bump version", "create release", "publish plugin".

Build Model Context Protocol (MCP) servers: define tools, resources, and prompts that AI agents can discover and use.

Recall and reuse prior decisions, constraints, and artifacts using MCP memory (e.g., Neo4j). Use when the user references past work (“jak ostatnio”, “kontynuuj”), when resuming a project thread, or when a repeated topic suggests existing decisions.

Use when securing MCP servers, preventing prompt injection, implementing authorization, validating user input, or building secure multi-agent pipelines. Provides 5-layer defense architecture patterns.

Complete reference for Claude Code's memory management system including all file types, locations, import syntax, and best practices. Use when planning or managing CLAUDE.md and related memory files.

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Patterns for designing multi-agent systems with Claude Code - job description method, shared folder communication, handbook consolidation, context management. Use when building complex agent orchestrations.

DEPRECATED. The multi-Claude orchestration scripts are deprecated in favor of native Claude Code Workflows; no installation is needed. Auto-invokes on "install multi-Claude workflows", "set up multi-Claude", "enable parallel execution" to explain the deprecation.

DEPRECATED. Multi-Claude shell orchestration is superseded by native Claude Code Workflows. Auto-invokes on "run multi-agent workflow", "parallel agents for", "multi-claude for", "spawn agents for" to redirect the user to the native Workflow and Agent tools.

Instrument a Python application with the Elastic Distribution of OpenTelemetry (EDOT) Python agent for automatic tracing, metrics, and logs. Use when adding observability to a Python service that has no existing APM agent.

Manage the openclaw-runtime git repository and its 13 agent workspace submodules. Use when adding a new agent workspace, cloning the runtime repo, updating submodule references, committing changes to the parent repo, or troubleshooting submodule state. Triggers on tasks involving workspace repos, submodule operations, agent onboarding git setup, or any git operations in ~/.openclaw/.

Concurrent agent dispatch for independent problems. Use when facing multiple independent tasks that can be worked on simultaneously. Reduces total time by parallelizing work that has no shared state.

One-time setup of parallel/ directory for multi-agent development

Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.

Guide for organizing Claude Code plugin directories and creating manifests. Use when the user asks to "create plugin structure", "set up plugin directories", "plugin layout", "plugin manifest", or "plugin.json".

Scans codebases to generate architecture documentation (ARCHITECTURE.md). Use when joining an existing project, understanding codebase structure, exploring project architecture, or preparing for agent-foreman init. Triggers on 'analyze project', 'understand codebase', 'explore architecture', 'scan project structure', 'survey project'.

Advanced prompting techniques: chain-of-thought, few-shot, system prompts, structured output, and prompt optimization.

Analyze and improve existing prompts for better performance

Démarre un développement avec un starter léger puis active le mode plan

Vérifie la checklist avant exécution et liste les oublis

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

Q-Value Augmented Vector Retrieval for learned memory ranking. Tracks which memories are most useful over time and prioritizes them in retrieval.

Build Retrieval-Augmented Generation systems with vector databases

Security patterns for RAG and CAG systems with multi-tenant isolation. Use when building retrieval-augmented or cache-augmented generation systems that require tenant isolation, access control, and secure data handling.

Use when "RAG", "retrieval augmented generation", "LangChain", "LlamaIndex", "sentence transformers", "embeddings", "document QA", "chatbot with documents", "semantic search"

Designs retrieval-augmented generation pipelines for document-based AI assistants. Includes chunking strategies, metadata schemas, retrieval algorithms, reranking, and evaluation plans. Use when building "RAG systems", "document search", "semantic search", or "knowledge bases".

Codebase reconnaissance agent for Bug Hunter. Maps architecture, identifies trust boundaries, classifies files by risk priority, and detects service boundaries. Does NOT find bugs — finds where bugs hide.

Demo/recording mode that redacts personally identifiable and sensitive information from Claude Code's outputs. Use when the user invokes /recording or says they are about to record, screen-share, or demo their Claude Code session and want PII scrubbed in real time.

Analyze development sessions, capture learnings, and improve Claude Code instructions. Use when the user wants to reflect on a session, improve CLAUDE.md, extract learnings, or optimize AI-human collaboration. Supports two modes: quick (default) focuses on CLAUDE.md improvements, deep mode performs comprehensive session analysis with learning capture.

[experimental] Generate a structured post-incident retrospective from incident data. Forked-subagent flow may not have MCP access in all Claude Code contexts.

Apply learned improvements to the Aura Frog plugin. Updates rules, adjusts agent routing, modifies workflow configurations, and generates knowledge base entries.

This skill should be used when the user asks to "export all sessions", "export all session logs", "batch export sessions", "sessionlog export-all", "convert all sessions", or wants to export every Claude Code session for the current project as standard LLM conversation JSON and TXT files.

This skill should be used when the user asks to "show session info", "find session log", "where are session logs", "current session id", "session path", "sessionlog info", or wants to identify the current Claude Code session and its log file location on disk.

You MUST use this skill when the user asks you to setup a claude code project. You should also suggest it if there is no CLAUDE.md or when starting work on an empty codebase.

Initializes git-agent for a repository — generates commit scopes from git history and .gitignore via AI. Use when the user asks to "configure git", "setup git", "set commit scopes", "update gitignore", "create gitignore", or needs project-specific Git settings.

Use when setting up VS Code or Cursor for Claude Code - configures settings, installs recommended extensions, sets up keybindings, and creates workspace templates optimized for AI-assisted development

Use when setting up git workflows for Claude Code - installs pre-commit hooks, commit templates with Claude attribution, PR templates, branch naming helpers, and Claude-specific gitignore entries

Open a tmux split running diffview.nvim so the user can review the agent's recent changes. Use proactively after non-trivial edits, or when the user asks to "show the diff", "open a diff viewer", or similar.

Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

Evaluate Claude Code skills against best practices including size, structure, examples, and prompt engineering quality. Provides comprehensive analysis with actionable suggestions.

Search skills.sh registry from CLI. Find and discover agent skills from the skills.sh ecosystem.

AI agent for Squid Router via Teneo Protocol. Use this skill when the user needs Squid Router via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

Use when an agent encounters a blocking decision or when proceeding without user input could lead to wasted work - helps Claude determine when to block and request user input versus making reasonable assumptions

Inspect a running swarm — show the agent tree, current tools, halts/pauses, and recent task/message activity for the orchestrator's own swarm.

Create, list, and manage Claude Code tasks in the current session. Use when asked to "create tasks", "track work", "list tasks", "mark task done", or to break work into trackable steps.

Arm the current Claude Code session to self-terminate by uttering a kill phrase once all work is finished and no questions remain. Use when the user says "terminate when done", "whendone", "end the session when finished", or "self-terminate when complete".