Reusable workflow patterns for skills and agents including sequential checklists, conditional routing, validation loops, and progressive disclosure. Use when designing structured procedures.
Provides reusable workflow patterns for building structured procedures: sequential checklists, conditional routing, validation loops, and progressive disclosure. Use when designing multi-step processes, branching logic, or iterative refinement in skills.
/plugin marketplace add mgd34msu/goodvibes-plugin/plugin install goodvibes@goodvibes-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Reusable patterns for structuring workflows in skills and agents.
Use when steps must be completed in order with tracking:
## Form Processing Workflow
Track progress:
- [ ] Step 1: Analyze form (run analyze_form.py)
- [ ] Step 2: Create field mapping
- [ ] Step 3: Validate (run validate.py)
- [ ] Step 4: Fill form
- [ ] Step 5: Verify output
When to use: Multi-step processes where completion tracking matters.
Use when different paths apply based on context:
## Document Workflow
1. Determine task type:
- **Creating new?** -> Follow Creation workflow
- **Editing existing?** -> Follow Editing workflow
## Creation workflow
[steps for new documents]
## Editing workflow
[steps for existing documents]
When to use: Tasks with distinct modes or branches.
Use when iterative refinement is needed:
1. Make changes
2. Validate: `python validate.py`
3. If errors:
- Fix issues
- Return to step 2
4. Only proceed when validation passes
When to use: Operations requiring correctness verification.
Front-load common usage, defer details:
## Quick start
[Most common usage - get user productive fast]
## Advanced
- **Forms**: See [FORMS.md](references/forms.md)
- **API details**: See [REFERENCE.md](references/reference.md)
Organize by topic when multiple domains exist:
bigquery/
SKILL.md (overview + navigation)
references/
finance.md
sales.md
product.md
Provide escape hatches for advanced needs:
## Basic usage
[Simple approach that works 80% of the time]
**For tracked changes**: See [REDLINING.md](references/redlining.md)
**For batch processing**: See [BATCH.md](references/batch.md)
Match instruction specificity to the situation:
| Situation | Freedom Level | Example |
|---|---|---|
| Multiple valid approaches | High | "Analyze code structure and suggest improvements" |
| Preferred pattern exists | Medium | "Use this template, customize as needed" |
| Fragile/critical operation | Low | "Run exactly: python migrate.py --verify" |
Patterns can be nested:
## Main Workflow
1. Determine mode:
- **Quick fix?** -> Use Quick Fix workflow
- **Full analysis?** -> Use Analysis workflow
## Quick Fix workflow
- [ ] Identify issue
- [ ] Apply fix
- [ ] Validate: `npm test`
- [ ] If fails, return to step 2
## Analysis workflow
See [DEEP_ANALYSIS.md](references/deep-analysis.md) for comprehensive steps.
| Anti-Pattern | Problem | Fix |
|---|---|---|
| No clear entry point | User doesn't know where to start | Add "Quick Start" section |
| Too many branches | Decision paralysis | Provide sensible defaults |
| No validation step | Errors discovered too late | Add explicit verification |
| References too deep | Content hard to find | Keep one level from SKILL.md |
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.