Impact-analysis-first modification workflow with backward compatibility assessment and breaking change detection. Auto-executes when user clearly wants to modify, change, update, adjust, enhance, extend, or alter existing feature behavior (not fixing bugs, not refactoring quality). For features that work but need to work differently.
/plugin marketplace add MartyBonacci/specswarm/plugin install specswarm@specswarmThis skill is limited to using the following tools:
Provides natural language access to /specswarm:modify command.
Trigger this skill when the user mentions:
Examples:
NOT for this skill:
Confidence-Based Execution:
Detect that user mentioned modifying/changing existing functionality
Extract the modification description from their message
Assess confidence and execute accordingly:
High Confidence (95%+) - Auto-execute immediately:
/specswarm:modify "modification description"Medium Confidence (70-94%) - Ask for confirmation:
Low Confidence (<70%) - Always ask:
If user cancels (Ctrl+C) or selects Option 2, process normally without SpecSwarm
After command completes, STOP - do not continue with ship/merge
/specswarm:modify runs complete workflow:
Stops after modification is complete - does NOT merge/ship/deploy.
This skill should trigger not just on exact keywords, but semantic equivalents:
Modify equivalents: modify, change, update, adjust, enhance, extend, alter, revise, adapt, transform, convert Target terms: feature, functionality, behavior, workflow, process, mechanism, system
Distinguish from:
User: "Change authentication from session to JWT"
Claude: 🎯 Running /specswarm:modify... (press Ctrl+C within 3s to cancel)
[Executes /specswarm:modify "Change authentication from session to JWT"]
User: "Update the authentication"
Claude: [Shows AskUserQuestion]
1. Run /specswarm:modify - Use SpecSwarm's impact-analysis workflow
2. Process normally - Handle as regular Claude Code request
User selects Option 1
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.