Docs
HomeClaude Code PRO
Blog

Getting Started

  • Documentation
  • Claude Code Setup
  • Claude Code Configuration
  • Claude Code Security

Claude Code PRO

  • guideCheatsheet
  • skill/apex
  • skill/brainstorm
  • skill/debug
  • skill/clean-code
  • skill/review-code
  • skill/ci-fixer
  • skill/claude-memory
  • skill/create-prompt
  • skill/create-slash-commands
  • skill/prompt-creator
  • skill/create-skills-workflow
  • skill/skill-creator
  • skill/hook-creator
  • skill/subagent-creator
  • scriptStatusline
  • scriptCommand Validator
  • scriptAuto-Rename Session
  • scriptClaude Code AI
  • agentSnipper
  • agentCode Reviewer
  • agentExplore Codebase
  • agentExplore Docs
  • agentAction
  • agentWeb Search
  • cmd/oneshot
  • cmd/refactor
  • cmd/ultrathink
  • cmd/commit
  • cmd/create-pr
  • cmd/fix-pr-comments
  • cmd/merge
  • cmd/fix-errors
  • cmd/utils/fix-grammar
  • cmd/copywriting

/prompt-creator

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs.

The /prompt-creator skill creates prompts optimized for Claude-to-Claude communication in multi-stage workflows. Each prompt gets its own folder in .prompts/ with structured outputs and human-readable summaries.

Prompt Purposes

PurposeDescriptionUse When
DoExecute a task, produce an artifactimplement, build, create, fix, add, refactor
PlanCreate an approach, roadmap, or strategyplan, roadmap, approach, strategy, decide
ResearchGather information or understand somethingresearch, understand, learn, gather, analyze
RefineImprove an existing research or plan outputrefine, improve, deepen, expand, iterate

Workflow

  1. Intake: Determine purpose, gather requirements via adaptive questions
  2. Chain detection: Scan for existing research/plan files to reference
  3. Generate: Create prompt using purpose-specific patterns
  4. Save: Create folder in .prompts/{number}-{topic}-{purpose}/
  5. Present: Show decision tree for running
  6. Execute: Run prompt(s) with dependency-aware execution
  7. Summarize: Validate output and create SUMMARY.md

Folder Structure

PathContents
.prompts/{number}-{topic}-{purpose}/Root folder for each prompt
completed/Archived prompts after execution
{number}-{topic}-{purpose}.mdThe prompt (moved to completed/ after run)
{topic}-{purpose}.mdFull XML-structured output for Claude
SUMMARY.mdHuman-readable executive summary

Example:

.prompts/
├── 001-auth-research/
│   ├── completed/001-auth-research.md    # Archived prompt
│   ├── auth-research.md                  # Full output (XML)
│   └── SUMMARY.md                        # Executive summary
├── 002-auth-plan/
│   ├── completed/002-auth-plan.md
│   ├── auth-plan.md
│   └── SUMMARY.md
└── 003-auth-implement/
    ├── completed/003-auth-implement.md
    └── SUMMARY.md                        # Implementation creates code elsewhere

Execution Modes

ModeWhen UsedBehavior
SingleOne promptStraightforward execution
SequentialChain with dependenciesExecute in order, stop on failure
ParallelIndependent promptsRun all at once, continue despite failures
MixedComplex DAGLayer-based execution (parallel within layers, sequential between)

Dependencies are auto-detected from @ references in prompts or inferred from purpose.

Output Validation

After execution, prompts are validated for:

  • Output file exists and has content (> 100 chars)
  • Metadata present (Research/Plan only): <confidence>, <dependencies>, <open_questions>, <assumptions>
  • SUMMARY.md exists with required sections
  • One-liner is substantive (not generic like "Research completed")

SUMMARY.md Structure

SectionDescription
One-linerSubstantive description of outcome
Versionv1 or iteration info
Key FindingsActionable takeaways
Files Created(Do prompts only)
Decisions NeededWhat requires user input
BlockersExternal impediments
Next StepConcrete forward action

When to Use

Use /create-meta-prompts when:

  • Building multi-stage workflows (research → plan → implement)
  • Creating prompts that produce outputs for other prompts
  • Needing clear provenance and chain detection
  • Want structured outputs with validation

Reference Guides

The skill uses purpose-specific patterns from:

  • references/do-patterns.md - Execution prompts
  • references/plan-patterns.md - Planning prompts
  • references/research-patterns.md - Research prompts
  • references/refine-patterns.md - Iteration prompts
  • references/summary-template.md - SUMMARY.md structure
  • references/metadata-guidelines.md - XML metadata requirements
/create-slash-commands/create-skills-workflow