Designs multiple implementation approaches with different trade-offs using parallel architect agents. Presents options and helps user select the best approach. Use after requirements are gathered.
Generates multiple implementation approaches with trade-offs and helps select the best one.
/plugin marketplace add astrosteveo/harness/plugin install harness@astrosteveo-marketplaceThis skill is limited to using the following tools:
You are helping a developer design the architecture for a feature by exploring multiple approaches.
Progress is saved to .artifacts/{feature-slug}/ for session continuity.
Design multiple implementation approaches with different trade-offs and help user select the best one.
Feature context: $ARGUMENTS
Launch 2-3 code-architect agents in parallel with different focuses:
Review all approaches and form your opinion on which fits best for this specific task
Present to user:
Ask user which approach they prefer
After user selects approach, create design.md:
# {Feature Name} - Design
## Chosen Approach
{Name of chosen approach}
## Rationale
{Why this approach was selected}
## Approaches Considered
### Approach A: {Name}
- **Summary**: {brief description}
- **Pros**: {list}
- **Cons**: {list}
- **Effort**: {estimate}
### Approach B: {Name}
- **Summary**: {brief description}
- **Pros**: {list}
- **Cons**: {list}
- **Effort**: {estimate}
## Architecture Overview
{High-level description of the solution}
## Component Design
### {Component 1}
- Purpose: {what it does}
- Interface: {public API}
- Dependencies: {what it uses}
## Data Flow
{How data moves through the system}
## Integration Points
- {Where this connects to existing code}
## Risks and Mitigations
| Risk | Mitigation |
|------|------------|
| {risk} | {mitigation} |
Multiple as phase progresses:
docs({feature-slug}): document architecture optionsdocs({feature-slug}): select {approach-name} approachAfter architecture is designed, guide the user to use:
/harness:implement-feature to build the featureThis 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 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 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.