lucid-toolkit

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Behavioral principle for context preservation through strategic delegation. Use when starting multi-step operations, uncertain about scope, or when direct execution might exhaust context. Complements never-guess and resolve-ambiguity skills.

Maintain awareness of operation counts across the conversation to prevent cumulative context exhaustion. Use when you notice multiple operations accumulating or when working on iterative tasks across turns.

Selects and applies mental models for structured problem analysis. Triggers when user asks "why", "what if", "how should we", needs systematic problem-solving, or mentions analyzing a situation. MUST BE USED when comparing options, making decisions, or evaluating trade-offs.

Provides Flutter and Dart development workflows using dart-mcp tools. Triggers when working with .dart files, pubspec.yaml, or when user mentions Flutter, widget, Riverpod, Freezed, or Dart development. MUST BE USED for Flutter project work involving dart_analyzer, dart_run_tests, hot_reload, or IDE MCP tools.

Create Architecture Decision Records (ADRs) following LCA conventions. INVOKE THIS SKILL when user: - Asks to "document a decision" or "record a decision" - Mentions "ADR", "decision record", or "architectural decision" - Wants to capture trade-offs or options considered - Needs to supersede or update an existing decision - Asks about decision history or rationale Trigger keywords: ADR, decision record, architectural decision, trade-offs, options, rationale

Create and maintain architecture documentation following Lucid Composite Architecture (LCA) principles. INVOKE THIS SKILL when user: - Asks an "architect" to review or analyze anything - Mentions "architecture review", "structural review", or "design review" - Requests documentation of system structure or component hierarchies - Wants to create, update, or review ARCHITECTURE.md files - Discusses Atoms, Composites, Conduits, or Deployable Units - Asks about LCA principles or architectural patterns - Needs data strategy with Schema.org at boundaries Trigger keywords: architect, architecture, structural, LCA, component hierarchy, ARCHITECTURE.md

Expert guidance for Neo4j Cypher queries and MCP server tools. Use when working with mcp__neo4j__ tools for query execution, schema introspection, and graph operations.

Use TOON (Token-Oriented Object Notation) with schema.org vocabulary for prompting and instructing subagents and builtin agents. Use when delegating tasks to agents, structuring agent prompts, or specifying expected response formats. DO NOT use for external API calls or when JSON parsing is required.

Standardize markdown document creation and updates with proper headers and footers. Use when creating OR updating any markdown file that is NOT a subagent, command, or skill definition. Ensures consistent metadata, classification, and change tracking.

Behavioral principle ensuring Claude never guesses when uncertain. Use when Claude's response involves facts it cannot verify, technical claims, or any statement where accuracy matters. Complements resolve-ambiguity skill.

Renders structured data to terminal with optimal formatting. Use when presenting agent results, displaying data to users, formatting command output, or showing validation reports. Transforms raw data into clear, scannable terminal output.

Systematic ambiguity resolution through tiered information gathering. Use when facing unclear requirements, unknown context, uncertain implementation choices, or any situation where guessing would be risky.

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure, progressive disclosure, workflows, validation patterns, and XML formatting.

Look up examples and patterns from the official Anthropic Claude Cookbooks repository. Use when you need reference implementations, code examples, or best practices for Claude integrations, tool use, agents, prompting techniques, or API usage.

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decisions.