Agent skill · AI & Agents

promptcraft

Use when user asks to "create a skill", "make a command", "generate a prompt", "write a slash command", "build a Claude extension", or needs help crafting optimized skills and commands with proper frontmatter.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill promptcraft --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 12 KB
Bundled scripts: none
Path: skills/ai-llm/promptcraft/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Skill & Command Generator Generate well-structured skills or slash commands. Both are markdown files with YAML frontmatter—they share the same structure but differ in how they're triggered and described. ## Phase 0: Fetch Current Documentation **Before generating**, retrieve the latest documentation: ``` Use Task tool with subagent_type=claude-code-guide: "List all current frontmatter options for skills and commands, including any execution modifiers, model selection, and structural options." ``` Integrate findings into your generation process. Documentation evolves—don't assume you know all options. ## Context Engineering Every token counts. LLM context is finite. Goal: smallest possible set of high-signal tokens that maximize outcomes | Do | Don't | |---|---| | "Validate input before processing" | "You should always make sure to validate..." | | "Use grep to search" | "You might want to consider using..." | | Bulleted constraints | Paragraphs with buried requirements | | Imperative voice ("Analyze") | First person ("I will analyze") | **Progressive discovery:** Core instructions in main file, details in `references/` subdirectory. Just-in-time information > front-loaded context

What's inside
Steps it walks through
  1. Phase 0: Fetch Current Documentation
  2. Context Engineering
  3. Degrees of Freedom
  4. Phase 1: Understand Requirements
  5. Phase 2: Generate
  6. Common Frontmatter Options
  7. Description Patterns
  8. Body Structure
  9. Dynamic Content
  10. Progressive Disclosure
  11. Execution Modifiers
  12. Tool Selection
  13. Before Finalizing
  14. Explain Your Choices
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the promptcraft skill do?

Use when user asks to "create a skill", "make a command", "generate a prompt", "write a slash command", "build a Claude extension", or needs help crafting optimized skills and commands with proper frontmatter.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill promptcraft --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.

Keep going