You are helping create implementation plans for software development tasks.
Creates detailed implementation plans for software tasks when users request plans via `/plan` or ask "how should I implement...". Generates structured plans with requirements, technical approach, step-by-step instructions, testing strategy, and risk analysis.
/plugin marketplace add grumps/claude-dotfiles/plugin install gdf@gdf-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You are helping create implementation plans for software development tasks.
Ask clarifying questions if the request is vague:
Run just info to understand:
Use this format:
# Implementation Plan: [TITLE]
## Overview
[1-2 sentences: what we're building and why]
## Requirements
- [ ] Functional requirement 1
- [ ] Functional requirement 2
- [ ] Non-functional (performance, security, etc.)
## Technical Approach
**Architecture**: [How components fit together]
**Technologies**: [Languages, frameworks, tools]
**Patterns**: [Design patterns, existing code to follow]
## Implementation Steps
### Step 1: [Name]
**What**: [What we're building]
**Why**: [Why this step is necessary]
**How**: [Technical details, code snippets]
**Files**: [Files to create/modify]
**Validation**: `just test-feature` or manual test steps
### Step 2: [Name]
...
## Testing Strategy
- **Unit tests**: [What to test, coverage goals]
- **Integration tests**: [What scenarios]
- **Manual testing**: [Steps to verify]
## Deployment Checklist
- [ ] Run `just validate` (lint + tests pass)
- [ ] Update documentation
- [ ] Create pull request
- [ ] Deploy to staging
- [ ] Smoke test in staging
- [ ] Deploy to production
- [ ] Monitor for errors
## Risks & Mitigations
| Risk | Likelihood | Impact | Mitigation |
|------|------------|--------|------------|
| [Risk description] | Low/Med/High | Low/Med/High | [How to prevent/handle] |
## Open Questions
- [ ] Question needing answer before proceeding
- [ ] Decision point requiring input
Save to .claude/plans/YYYY-MM-DD-short-description.md
just test")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.