Build Retrieval-Augmented Generation (RAG) applications that combine LLM capabilities with external knowledge sources. Covers vector databases, embeddings, retrieval strategies, and response generation. Use when building document Q&A systems, knowledge base applications, enterprise search, or combining LLMs with custom data.

This skill should be used when the user asks to "change the commit attribution", "remove the co-authored by", "stop adding the co-authored by", "change Claude's name", "configure the PR attribution", "update attribution settings", "show that Claude is helping write commits", or "reset co-authored by settings". Manages git commit and pull request attribution in Claude Code settings.

Build new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.

Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the model's capabilities with specialized knowledge, workflows, or tool integrations.

Autonomous crypto trading for AI agents on Stellar. Ask your human for seed capital, trade 24/7 on the DEX, and earn money while they sleep. Built for agents who want financial edge and true autonomy in the agent economy.

Mine coding agent logs (Codex/Cursor/session histories and similar telemetry) to discover high-value candidate skills, then draft structured skill creation/reuse recommendations.

LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.

Lightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without graphical rendering like data retrieval. Use it via MCP server, CLI fetch, or CDP with Playwright/Puppeteer.

Generate MCP-backed skills from remote MCP servers (Streamable HTTP). Covers discovery, wrapper generation, skill scaffolding, and authentication seams for HTTP endpoints.

Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval precision/recall metrics. Use when building retrieval-augmented generation systems, vector databases, or processing large documents.

Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).

MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.

Decentralized git for AI agents and humans. Use when the user wants to create repositories, push code, open pull requests, review and merge PRs, manage issues, create or claim bounties, delegate tasks to other agents, register human-readable names on Base L2, or interact with the gitlawb decentralized git network. Supports cryptographic DID identities, Ed25519-signed pushes, UCAN capability delegation, libp2p networking, and 31+ MCP tools for AI agent integration. Do NOT use for GitHub, GitLab, or other centralized git hosts.

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.

Discovers, enriches, and scores local businesses in any neighborhood using Nimble Web Search Agents (WSAs) and web data. Returns a structured, ranked list with confidence scores, reviews, social presence, and an interactive map. Use this skill when the user asks about local businesses, places, or neighborhood discovery. Common triggers: "find all coffee shops in", "map every bar in", "local businesses in", "discover gyms near", "what restaurants are in", "neighborhood guide for", "local places in", "find places near", "list all [business type] in [area]", "best [type] near [location]", "build a neighborhood guide", "local place search". Requires the Nimble CLI (nimble agent run, nimble search, nimble extract) for live web data via WSAs and fallback search. Do NOT use for competitor analysis or monitoring (use competitor-intel), company research or deep dives (use company-deep-dive), general web search or extraction (use nimble-web-expert).

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", discusses MCP server types (SSE, stdio, HTTP, WebSocket), or asks to "find MCP server", "discover MCP servers", "what MCP servers exist", "recommend MCP server for [service]", "MCP prompts", "MCP prompts as commands", "tool search", "tool search threshold", "claude mcp serve", "allowedMcpServers", "deniedMcpServers", "managed MCP". Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.

Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.

Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.16.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-skill.

Creates and manages Obsidian notes for projects, technical challenges, brag documents, meeting transcriptions, and company tracking using MCPVault MCP. Use when documenting projects, recording technical challenges, maintaining brag documents, preserving meeting and course transcriptions, or tracking job applications. Triggers: "create project note", "new project note", "technical challenge", "brag document", "achievement", "accomplishment", "transcription", "meeting notes", "1:1 notes", "feedback notes", "standup notes", "lecture notes", "course notes", "company note", "track interview", "job application". Not for end-of-session persistence across memory systems or for initializing repository-wide project context.

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.

Implements retrieval-augmented generation pipelines. Use when building document retrieval systems, choosing chunking strategies, selecting embedding models, configuring vector stores, implementing hybrid search, or evaluating RAG quality. Use for embedding strategy, vector stores, retrieval pipelines, chunking, hybrid search, re-ranking, multi-query retrieval, parent document retrieval, contextual compression, MMR diversity selection, reciprocal rank fusion, and evaluation. For KB architecture selection and governance, use the knowledge-base-manager skill. For knowledge graphs, use the knowledge-graph-builder skill.

Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis.

Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up transports for AI function calling and tool calling. Use when building MCP servers to extend AI capabilities with Spring's official AI framework, implementing AI tools, custom function calling, or MCP client integration.

Upload files or directories to Volcano Engine TOS (Torch Object Storage) and download files from URLs. Use this skill when (1) Upload Agent-generated files or directories (like videos, images, reports, output folders) to TOS for sharing, (2) Download files from URLs before Agent processing.

Claude + Obsidian knowledge companion. Sets up a persistent wiki vault, scaffolds structure from a one-sentence description, and routes to specialized sub-skills. Use for setup, scaffolding, cross-project referencing, and hot cache management. Triggers on: "set up wiki", "scaffold vault", "create knowledge base", "/wiki", "wiki setup", "obsidian vault", "knowledge base", "second brain setup", "running notetaker", "persistent memory", "llm wiki".

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agents", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.

Principal/Senior-level AI/ML playbook for production machine learning systems, LLM-enabled backends, model serving, training pipelines, evaluation discipline, reliability, security, and MLOps. Use when: designing ML services, building or reviewing training/inference code, selecting model architectures, fine-tuning transformers, hardening model APIs, debugging performance or correctness issues, or preparing ML systems for production.

Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. In interactive mode it applies safe, verified fixes and commits them when the working tree is clean (it never pushes); in mode:agent it reports only and the caller applies. Use when reviewing code changes before creating a PR.

Guides development of Claude Code slash commands, including file format, YAML frontmatter fields, dynamic arguments ($ARGUMENTS, $1/$2), file references, bash execution, and command organization. Activates when the user asks to create a slash command, add a command, define command arguments, use command frontmatter, organize commands, create commands with file references, or needs guidance on command development best practices.

This skill should be used when the user asks to "create a diagram", "draw a flowchart", "make a swimlane diagram", "create WBS", "generate RACI matrix", "build network diagram", "create org chart", or mentions draw.io, diagrams.net, BPMN, UML, Gantt, PERT, or project management diagrams. Integrates with next-ai-draw-io MCP server for real-time diagram creation and editing.

Manages OrchestKit learning system including feedback status, usage pattern tracking, and privacy/analytics consent. Supports pause/resume learning, data export, privacy policy display, and bug reporting. Tracks learned patterns and agent performance metrics. Use when reviewing learned patterns, pausing learning, or managing data consent.

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Knowledge base architecture selection, curation, and governance. Use when choosing between document-based (RAG), entity-based (graph), or hybrid KB architectures, establishing content curation workflows, implementing versioning and governance, or evaluating quality metrics. For building retrieval pipelines, use the rag-implementer skill. For building knowledge graphs, use the knowledge-graph-builder skill.

Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.

Use when installing MCP packages and configuring Claude-side MCP registration, hooks, permissions, IDE extension mode, and migrations.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Detect and block prompt injection attacks hidden in long content (emails, web pages, documents) using OpenGuardrails SOTA detection

Import structured data into Neo4j — LOAD CSV, CALL IN TRANSACTIONS, neo4j-admin database import full (offline bulk), apoc.load.csv/json, apoc.periodic.iterate, driver batch writes. Covers method selection, header file format, type coercion, null handling, ON ERROR modes, CONCURRENT TRANSACTIONS, pre-import constraint setup, and post-import validation. Use when importing CSV/JSON/Parquet files, migrating relational data to graph, or bulk-loading large datasets. Does NOT handle unstructured document/PDF/vector chunking pipelines — use neo4j-document-import-skill. Does NOT handle live app write patterns (MERGE/CREATE) — use neo4j-cypher-skill. Does NOT handle neo4j-admin backup/restore/config — use neo4j-cli-tools-skill.

This skill should be used when the user asks to "review a PR", "review pull request", "PR review", "check this PR", "analyze PR changes", "review PR #123", "what's wrong with this PR", "is this PR safe to merge", "review my changes", "review local changes", "review my code", "review staged changes", "review my diff", or needs expert code review with architectural analysis, defect detection, and security scanning. Supports both remote PRs and local changes (staged/unstaged). Uses Octocode MCP tools for deep code forensics and holistic evaluation.

Strategic task decomposition and parallel agent orchestration. INVOKE PROACTIVELY when request is complex, multi-faceted, or mentions multiple deliverables. Triggers: "orchestrate", "parallelize", "multi-agent", or auto-detect complex requests. Auto-detection patterns: - "research and implement", "analyze and fix", "review everything" - "comprehensive", "full audit", "multiple files", "across the codebase" - Refactoring, migrations, multi-step investigations - Multiple AND-connected tasks ("add X and Y and Z") Commands: - /orchestrate - Full workflow: decompose -> route -> execute -> synthesize - /parallel [tasks] - Quick parallel launch without decomposition - /plan-only - Get execution plan without running it Output: English. Uses Task() for subagent dispatch.

This skill should be used when users want to create powerful AI agents comparable to Claude Code or sonph-code. It provides battle-tested system prompts, masterfully-crafted tool implementations, and the simple but powerful agent loop pattern. Use this skill when users ask to build coding agents, AI assistants with tools, or any autonomous agent that needs file operations, code execution, search, and task management capabilities. The key insight is that customization requires only ONE HumanMessage after the SystemPrompt.

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.

Convert prose prompts into compact, structured XML prompts through staged subagent passes. Use when a user asks to structure, harden, formalize, debug, or convert a prompt; mentions XML tags, agent drift, ambiguity, hidden assumptions, success criteria, anti-patterns, autonomous prompts, or prompt suites; or provides natural-language instructions that need to become a reliable agent contract.

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

NVIDIA RAG Blueprint performance-tuning guidance for profiling retrieval stacks, comparing bottlenecks, and validating latency or throughput improvements.

Secures AI integrations against prompt injection, privilege escalation, and data leakage. Use when implementing defense-in-depth for LLM pipelines, applying zero-trust controls to autonomous agents, hardening server actions that interact with AI services, validating model outputs, securing MCP tool integrations, or auditing AI system access patterns and identity management. Use for OWASP LLM Top 10, prompt injection defense, agentic security, AI supply chain.

Use PROACTIVELY when creating releases after PR merges to main, or when user asks about versioning strategy. Automated git tagging agent that analyzes repository state, parses conventional commits, calculates semantic versions, and creates annotated git tags with GitHub releases. Supports monorepo namespaced tags with @ separator convention. Not for changelog generation or pre-release/alpha versioning.

Use when the user asks to "analyze a session", "session report", "review session performance", "how did that session go", "token usage report", "cost report", or wants to understand the performance, cost, and quality of a completed Claude Code session. Accepts a session JSON file path as input.

This skill should be used when the user asks to "configure powerline", "set up status line", "use my default status line", "configure powerline as usual", "change the powerline theme", "update status line settings", or mentions powerline configuration. Provides comprehensive guidance for creating and managing .claude/.claude-powerline.json configuration and integrating it with Claude Code settings.

Create new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development.

Use this skill for high-effort brainstorming sessions that spawn multiple parallel subagents — each applying a distinct ideation technique (SCAMPER, Crazy 8s, Reverse, First Principles, Analogy, Six Hats, Constraint-Based, Random Input) — then synthesizes the results into strong threads the user can drill into before crafting SPECLAN specs. Triggers when the user says "deep brainstorm", "brainstorm plus", "multi-angle brainstorm", "throw everything at this", "I want a thorough exploration", "parallel brainstorm", "give me more ideas", "I'm stuck — explore harder", or invokes `/speclan-engineering:brainstorm-plus`. Use this when a rough thought deserves more effort than single-agent brainstorming — gnarly architectural decisions, ambiguous product directions, or stuck ideation. Do NOT use this skill when the user has a finished PRD (use `/speclan-engineering:hlrd`), wants a quick brainstorm (use `/speclan-engineering:brainstorm`), or is asking about existing specs (use `/speclan:ask`).

Create custom agents for Claude Code including YAML frontmatter, system prompts, tool restrictions, and discovery optimization. Use when creating, building, or designing agents, or when asked about agent creation, subagent configuration, Task tool delegation, or agent best practices.

Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.

Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.

Slack automation CLI — read/send/search messages, browse threads and channels, manage channels, download attachments, look up users, and run workflows.

Event-driven hooks for AI coding agents. Use when automating Claude Code or Codex CLI with stdin JSON and decision-control responses.

Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filtering by date, device, domain, and keywords. Uses LLM classification for content categories. Can output to stdout or save as markdown/JSON to Obsidian vault.

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, slash commands, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

Git specification for feature-oriented development with full branch types, including non multi-agent, multi-agent base, and subagent branch and worktree tree naming.

Create or refine Markdown plus Mermaid flow diagrams for AI-agent workflows. Use when the user asks for a process flow, workflow diagram, Mermaid flowchart, agent operating procedure, human-in-the-loop gate map, or refinement of an existing flow or process description.

Generates a resumable cold-start handoff package from an in-progress conversation, review, debugging session, or investigation. Use when the user says "create a handoff doc", "save this for later", "document what we found", "update the resumption file", or wants a fresh agent to resume without chat history.

Create event-driven hooks for Claude Code automation. Use when the user wants to create hooks, automate tool validation, add pre/post processing, enforce security policies, or configure settings.json hooks. Triggers: create hook, build hook, PreToolUse, PostToolUse, event automation, tool validation, security hook

Letta framework for building stateful AI agents with long-term memory. Use for AI agent development, memory management, tool integration, and multi-agent systems.

Use when installing or verifying this marketplace in Claude and Codex, aligning selected plugins, MCP settings, and Codex execution defaults.

Coordinates skills, frameworks, and workflows throughout the project lifecycle using pattern-based sequencing, goal decomposition, phase-gate validation, and multi-agent orchestration. Use when starting multi-phase projects, sequencing frameworks, decomposing goals into capability plans, validating phase-gate readiness, coordinating subagents, or designing MCP-based tool orchestration.

Project development lifecycle management with a strict three-phase workflow (investigate, proposal, implement), file-based plan tracking in docs/plan/, task tracking in docs/task/, and claim-before-work multi-agent coordination. Use when handling feature development, bug fixes, refactors, planning, progress tracking, or multi-agent execution in an existing codebase. English-first for repository docs and remote-visible metadata; use Chinese docs only when the user explicitly requests a specific document in Chinese.

Use when creating a new skill, MCP server, or CLI tool project.

RAG (Retrieval Augmented Generation) implementation patterns including document chunking, embedding generation, vector database integration, semantic search, and RAG pipelines. Use when building RAG systems, implementing semantic search, creating knowledge bases, or when user mentions RAG, embeddings, vector database, retrieval, document chunking, or knowledge retrieval.

Provides templates and analysis guidance for mapping codebases into specialized documentation. Used by the sdd:code-mapper agent to generate 8 focused codebase documents.

This skill should be used when the user asks to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", "SKILL.md format", "skill frontmatter", "skill triggers", "trigger phrases for skills", "progressive disclosure", "skill references folder", "skill examples folder", "validate skill", "skill model field", "skill hooks", "scoped hooks in skill", "visibility budget", "context budget", "SLASH_COMMAND_TOOL_CHAR_BUDGET", "skill permissions", "Skill() syntax", "visual output", or needs guidance on skill structure, file organization, writing style, or skill development best practices for Claude Code plugins.

Mine local agent transcripts into redacted workflow-pattern evidence and recommend at most five automation specs as an extend op; never creates files, only asks which specs should proceed. Use when the user says "learn my workflow", "suggest skills", "suggest hooks", "automate repetitive work", "what should I automate", or "skillers".

Create custom slash commands for Claude Code including syntax, arguments, bash execution, file references, and frontmatter configuration. Use when creating slash commands, custom commands, .md command files, or when asked about command creation, /command syntax, or command best practices.

Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze code snippets before committing, or understand SonarQube rules. Triggers on "sonarqube", "sonarcloud", "quality gate", "sonar issues", "analyze with sonar", "check sonar", "sonar rule", "pre-push analysis".

When you notice you are doing the same thing BY HAND again — the same check, trace, scaffold, or detection you did before — that noticing is the signal for this. It is the instinct to externalize repeated effort into tools: never do the same manual work twice. Use this when a motion has recurred: "I keep hand-checking whether effects leaked into the core", "I keep manually tracing the call graph". The Rule of Three pointed at Cairn's OWN repeated actions: the third time you do a thing by hand, forge a tool so the fourth is free. Tools live in a sandboxed workshop and may take real actions (run commands, scaffold, probe), trusting the outer harness (Claude Code) to bound the blast radius — a tool the harness rejects is itself a lesson. A tool is justified by MEASURED payback (manual cost x times done, vs build cost); one that never pays back is debt, and is retired. The bright line: a tool may never rewrite Cairn's own constitution — gates, ledger, floor, ladder.

On-demand adversarial quality reviews using strategy templates. Selects strategies by criticality level, executes adversarial templates against deliverables, and scores quality using LLM-as-Judge rubric. Integrates with quality-enforcement.md SSOT.

Guides creation of best-practice agent skills following the open format specification. Covers frontmatter, directory structure, progressive disclosure, reference files, rules folders, degrees of freedom, content patterns, executable scripts, MCP tool references, evaluations, and cross-model testing. Use when creating a new skill, authoring SKILL.md, setting up a rules-based audit skill, structuring a skill bundle, writing scripts inside a skill, evaluating a skill, or asking "how to write a skill."

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

Master AI, machine learning, LLMs, prompt engineering, and blockchain development. Use when building AI applications, working with LLMs, or developing smart contracts.

Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: "analyze these docs", "scan my project for context", "read the docs folder", "summarize what's in .beagle/concepts/", "extract context from docs/", "what's in this folder", "go read everything in X and tell me what's there". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

Orchestrate multi-prompt execution with phase groups, optional auto-deps, and model-tiered agent roles.

Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

Create and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Comprehensive guidance on file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness.