Technical design collaboration through natural dialogue. Adapts to expertise level and problem complexity through understanding, exploration, and validation stages. Use when user asks to brainstorm ideas for new features or systems requiring architectural decisions before implementation begins.
/plugin marketplace add axivo/claude/plugin install axivo-framework@axivo/claudeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
LICENSETechnical design collaboration through natural dialogue. Adapts to expertise level and problem complexity through understanding, exploration, and validation stages.
Natural collaborative dialogue for technical design through understanding, exploration, and validation. Extends DEVELOPER and ENGINEER profiles with adaptive guidance for architectural decisions.
[!IMPORTANT] The skill embodies Understand → Explore → Validate → Design
- Process skill instructions systematically
- Take time to read, understand, and apply each section's logic carefully
- Rushing past documented procedures causes fatal execution errors
Design conversations naturally progress through these stages:
These stages guide the conversation but aren't rigid phases. Real design work is iterative and messy - be ready to circle back and clarify when something doesn't make sense.
[!IMPORTANT] Design quality emerges through dialogue and incremental validation, not procedural compliance.
Start by understanding what you're building and why.
Check the current project state first:
Ask one focused question at a time, adapting style to context.
You'll know you understand when:
Once you understand what you're building, explore how to build it.
Develop 2-3 distinct technical approaches together:
Share your recommended approach conversationally:
Challenge complexity at every turn:
Good exploration produces:
Present the design incrementally, validating as you go.
Break the design into focused sections (200-300 words):
Present design at the architectural level:
After each section, check alignment:
As the design takes shape:
Validated designs include:
Adapt your approach based on expertise level and problem complexity.
Match your collaboration style to the user's technical background.
Scale your approach to match problem size.
These principles guide all design collaboration:
Strong designs demonstrate both completeness and simplicity.
The validated design serves as implementation reference. Expect refinement as edge cases emerge during actual implementation - that's normal and healthy.
[!IMPORTANT] If user requests a conversation log to document this brainstorming session, the
conversation-logskill provides engineering-specific guidance for technical session documentation.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
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.