ai-prompt
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness.
npx skills add majiayu000/claude-skill-registry --skill ai-prompt --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Prompt ## Purpose Prompt optimization and creation. Improves prompts, skill descriptions, and agent instructions using proven techniques: explicit over implicit, examples over rules, structured formatting, and positive framing. Can auto-enhance prompts for other skills or manually optimize user-provided text. ## Trigger - Command: `/ai-prompt "<text>"` (optimize text) or `/ai-prompt --skill <name>` (optimize a skill's description) - Context: writing a new prompt, improving an existing skill's description, crafting agent instructions. ## When to Use - Writing or refining skill `description` fields (CSO optimization) - Crafting system prompts for AI integrations - Improving agent instruction clarity - Before publishing any prompt-based artifact ## Optimization Techniques Apply these in order of impact: ### 1. Be Explicit Over Implicit | Before | After | |--------|-------| | "Handle errors properly" | "Wrap database calls in try/except, log the exception with stack trace, return a structured error response with HTTP 500" | | "Follow best practices" | "Apply guard clauses for early return, extract methods over 20 lines, name variables by intent not type" | ### 2. Show, Do Not Tell Re
- Purpose
- Trigger
- When to Use
- Optimization Techniques
- 1. Be Explicit Over Implicit
- 2. Show, Do Not Tell
- 3. Structure with XML Tags or Markdown
- 4. Explain WHY for Each Rule
- 5. Positive Framing
- 6. CSO Optimization (for skill descriptions)
- 7. Cialdini Principles (for discipline-enforcing skills)
- Procedure
- Optimizing text
- Optimizing a skill description
What does the ai-prompt skill do?
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ai-prompt --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.