prompt-improvement

# Prompt Improvement

## MANDATORY: Query Official Documentation First

> **STOP - Before improving ANY prompt, you MUST invoke the docs-management skill.**
>
> This is NOT optional guidance - it is a required execution step.

### Required: Query Documentation via docs-management Skill

**Invoke the `claude-ecosystem:docs-management` skill BEFORE making any improvements:**

Search for relevant documentation using natural language:

- Primary query: "prompt engineering chain of thought XML tags"
- Read the top results returned by the skill

### Why Documentation Query is Required

- **Training data is stale** - Your knowledge may be outdated
- **Official docs are canonical** - Anthropic's current best practices
- **Prevents hallucination** - Ground improvements in real documentation
- **Ensures accuracy** - Latest Claude 4.x guidance

### Recommended Query Topics

Query at least ONE of these topics based on your improvement needs:

- **Chain of thought:** "chain of thought thinking tags reasoning"
- **XML structure:** "XML tags structure prompts formatting"
- **Examples/multishot:** "multishot prompting examples few-shot"
- **Claude 4.x best practices:** "Claude 4 prompting best practices"

### Verification Checkpoint

Before improving a prompt, verify:

- [ ] Did I invoke the docs-management skill? (not just read about it)
- [ ] Did I receive documentation from docs-management?
- [ ] Did I READ at least one official doc returned by the skill?
- [ ] Are my improvements based on what I read from official docs?

**If ANY checkbox is unchecked, STOP and invoke the docs-management skill first.**

## Overview

This meta-skill replicates Anthropic's Console/Workbench prompt improver functionality within Claude Code. It provides workflows, patterns, and keyword registries to transform basic prompts into high-performance structured templates.

**What this skill provides:**

- The 4-step improvement workflow (quick reference)
- Keyword registry for docs-management queries
- D