prompt-creation
Create standardized context prompts for AI assistants in prompts/ directory. Two types: technology-stack (project config with versions/policies) or behavioral (assistant persona/rules). Enforces context gathering, validates schema compliance, ensures token efficiency. Uses JSON or markdown frontmatter format.'
npx skills add majiayu000/claude-skill-registry --skill prompt-creation --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.
What it does
Create standardized context prompts for AI assistants in prompts/ directory. Two types: technology-stack (project config with versions/policies) or behavioral (assistant persona/rules). Enforces context gathering, validates schema compliance, ensures token efficiency. Uses JSON or markdown frontmatter format.
How it works
- Mandates context gathering via 10 questions depending on prompt type (technology-stack or behavioral).
- Requires frontmatter with minimal metadata (4-6 fields; typically name, type, description, context/priority; optional tags).
- Uses a markdown body to contain all content: overview, rules, persona, instruction types, examples, guidelines, and decision trees.
- Follows a template workflow: copy PROMPT-TEMPLATE.md to prompts/{prompt-name}.md, fill placeholders, then validate structure against the frontmatter schema and the Markdown-content rules.
- Validates that frontmatter is concise (no nested objects beyond 1 level, no arrays with >3 simple strings, frontmatter < 10 lines).
- Ensures all content in the markdown body (not frontmatter) and that examples are in code blocks.
When to use it
- When creating context prompts for AI assistants
- When defining technology-stack configuration for projects
- When documenting behavioral rules for AI assistant personas
- When setting up language processing or communication guidelines
What it can touch
- Frontmatter fields: name, type, description, context/priority, tags (as per template).
- Markdown body sections: Overview/Purpose, Persona, General Rules, Instruction Types/Modes, Examples, Guidelines, Decision Tree, Related Skills/Prompts, References.
Caveats
- Frontmatter must follow the minimal metadata pattern with 4-6 fields; violations should be corrected (no nested objects beyond 1 level).
- Token efficiency emphasized; prefer Markdown over bloated frontmatter and avoid empty fields.
- Content must be in English.
Summary for developers
The skill enforces structured, token-efficient context prompts in prompts/, with mandatory context gathering and strict frontmatter/markdown formatting rules, supporting both technology-stack and behavioral prompt types.
--- name: prompt-creation description: Create context prompts for AI assistants in JSON or markdown frontmatter. Enforces mandatory context gathering (10 questions), validates schema compliance, ensures token efficiency. All content must be in English. Two types: technology-stack (project config) or behavioral (assistant persona). Trigger: When creating context prompts for AI assistants or documenting project configuration. skills: - critical-partner - conventions - english-writing --- # Prompt Creation Skill ## Purpose Create standardized context prompts for AI assistants in `prompts/` directory. Two types: technology-stack (project config with versions/policies) or behavioral (assistant persona/rules). Enforces context gathering, validates schema compliance, ensures token efficiency. Uses JSON or markdown frontmatter format. --- ## When to Use Use this skill when: - Creating context prompts for AI assistants - Defining technology stack configuration for projects - Documenting behavioral rules for AI assistant personas - Setting up language processing or communication guidelines Don't use this skill for: - Creating agent definitions (use agent-creation instead) - Creating skills (
- Purpose
- When to Use
- English Writing
- Critical Patterns
- Pattern 1: Frontmatter vs Markdown Body (CRITICAL STRUCTURE)
- Pattern 2: Mandatory Minimal Frontmatter
- Pattern 3: Mandatory Context Gathering (10 Questions)
- Pattern 4: Use Template from assets/
- Pattern 5: Choose Prompt Type and Naming
- Pattern 6: Token Efficiency
- Pattern 7: Validate Against Schema
- Pattern 8: Markdown Frontmatter (REQUIRED)
- Decision Tree
- Edge Cases
Create English practice prompt
What is the primary objective?
What persona should the assistant adopt?
Copy template to prompts directory
cp skills/prompt-creation/assets/PROMPT-TEMPLATE.md prompts/{prompt-name}.md
Fill placeholders: {prompt-name}, {type}, {description}, etc.
Validate frontmatter structure
cat prompts/my-prompt.md | yq eval '.frontmatter' - | \
yq eval-all '.' skills/prompt-creation/assets/frontmatter-schema.json -What does the prompt-creation skill do?
Create standardized context prompts for AI assistants in prompts/ directory. Two types: technology-stack (project config with versions/policies) or behavioral (assistant persona/rules). Enforces context gathering, validates schema compliance, ensures token efficiency. Uses JSON or markdown frontmatter format.'
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-creation --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.