Prompt Generator

When to use

• User has rough notes, bullet points, or a brain dump they want turned into a clean LLM prompt
• Refining, rewriting, or optimizing an existing prompt that isn't performing well
• Structuring a system prompt or task prompt from scattered requirements
• Creating prompt templates with variable placeholders for repeated use
• User says anything like "write me a prompt for...", "turn this into a prompt", "system prompt for..."

When NOT to use

• Brainstorming features or creative ideation - this skill structures prompts, not ideas
• Creating reusable skill files or agent instruction bundles (use skill-creator)
• Writing inline prompt strings inside application code - that's just coding
• The user wants code that calls an LLM API (use ai-ml for SDK integration)
• Security review of prompts for injection risks (use security-audit)
• Reviewing code quality of prompt-related code (use code-review or anti-slop)

AI Self-Check

• Frontmatter complete:

  name

  ,

  description

  ,

  target_model

  ,

  prompt_type

  ,

  date_created

  all present
• Faithful to input: prompt reflects what the user said, not what you think they should have said
• Structure matches complexity: simple tasks get plain prose, not XML-tagged multi-section prompts
• Variables consistent: every

  {{PLACEHOLDER}}

  in the prompt body appears in the Variables table and vice versa
• No injected instructions: didn't add error handling, safety disclaimers, or output constraints the user didn't request
• No slop phrases: no "certainly", "I'd be happy to", "great question", or other filler in the prompt text
• Output format specified: if the prompt expects structured output, the format is explicit (JSON schema, XML tags, delimiters)
• Model-appropriate syntax: avoid model-specific features (assistant prefills,

  \n\nHuman:

  formatting) in model-agnostic prompts. XML delimiters and markdown headers are both fine for structure across models

Workflow

Step 1: Read the brain dump

• Core task: What should the prompted model actually do?
• Target model: Which LLM? Default: model-agnostic unless the user names one.
• Prompt type: System prompt vs. task prompt
• Constraints: Any rules, format requirements, or behavioral boundaries mentioned
• Variables: Any dynamic content that should become

  {{PLACEHOLDERS}}

Step 2: Clarify only if stuck

Step 3: Structure and present

1. Turn the rough notes into a clean prompt, applying structure proportional to complexity:
   • Simple (one task, no variables): plain prose, 3-10 lines. No XML, no sections.
   • Medium (multiple steps or constraints): numbered steps, clear sections.
   • Complex (agentic, multi-document, behavioral rules): clear section delimiters, variable placeholders, explicit output format.
2. Present the prompt in conversation for review. Don't write files yet.
3. On approval, save to file (see Output Format below).
4. Revisions: edit in place, don't create new files.

Step 4: Save

1. Resolve output directory: user-specified path >

   docs/prompts/

   >

   docs/

   > ask
2. Scan for

   NNN-*.md

   files, increment highest number, zero-pad to 3 digits
3. Infer a slug from the topic (e.g.,

   code-review

   ,

   data-extraction

   )
4. Write to

   <output-dir>/NNN-slug.md

Output File Format

---
name: Descriptive Prompt Name
description: One-line summary
target_model: model-agnostic
prompt_type: system | task
date_created: YYYY-MM-DD
---

## Purpose

What this prompt does and when to use it.

## Variables

| Variable | Description | Required |
|----------|-------------|----------|
| `{{VAR}}` | What it is | Yes/No |

## Prompt

The actual prompt content here.

tags: [...]

related: [NNN-other.md]

claude

gpt

gemini

llama

mistral

model-agnostic

Structuring Guidelines

Model-Specific Formatting

<result>

Structured Output Guidance

• JSON mode: if the tool supports native JSON mode or schema-constrained output, use it. Otherwise instruct the model to return valid JSON and seed with

  {

  only when the tool supports assistant prefills.
• XML structure: wrap output in tags like

  <result>

  ,

  <analysis>

  ,

  <decision>

  .
• Delimiter-based: for simple key-value, use

  KEY: value

  format.

The Four-Block Pattern

1. INSTRUCTIONS - what to do (role, task, constraints)
2. CONTEXT - background information, reference data
3. TASK - the specific request for this invocation
4. OUTPUT FORMAT - exact structure of the expected response

Refining Existing Prompts

1. Read it
2. Diagnose gaps - check for these common prompt weaknesses:
   • Missing scope: no clear boundary on what the model should and shouldn't do
   • No output format: model guesses structure instead of following a spec
   • Vague role: "helpful assistant" tells the model nothing useful
   • Missing constraints: no anti-patterns, no "do not" list, no quality criteria
   • Over-specified: drowning the model in rules when 2-3 clear constraints would work
3. Present specific changes with reasoning - not a full rewrite unless it's warranted
4. On approval, edit in place

You are a helpful assistant that reviews code.

You are a senior code reviewer. For each file, check for: bugs, edge cases, security issues, and performance problems. Report findings as a list with severity (critical/warning/info), file:line, and a one-line description. Skip style nitpicks. If nothing is wrong, say "No issues found."

Example: Creation from Scratch

I want an AI that helps me write better emails. It should fix grammar, make things more concise, and match the tone I want. Sometimes formal, sometimes casual.

You are an email editor. You receive a draft email and a target tone, then return an improved
version.

Your edits:
- Fix grammar and spelling errors
- Make the text more concise - cut filler words and redundant phrases
- Match the requested tone (formal, casual, or neutral)

Preserve the sender's intent and meaning. Do not add information they didn't include.
Do not change the greeting or sign-off style unless it clashes with the requested tone.

Input format:
  TONE: {{TONE}}
  DRAFT:
  {{EMAIL_DRAFT}}

Return only the improved email. No commentary, no explanations, no "Here's your improved email:".

Related Skills

• skill-creator - creates reusable skill files (SKILL.md) for AI tools and coding agents. Skills are structured prompts, but they follow different conventions (frontmatter, workflow sections, rules) than standalone prompts. If someone says "create a skill", use skill-creator.
• Application code - if the user needs a prompt string inside application code (for example a TypeScript

  const systemPrompt = ...

  ), that's coding, not this skill.
• anti-slop - if the user asks to "clean up" or "simplify" a prompt embedded in code, that's a code quality issue, not prompt structuring.

Rules

1. Faithful structuring. Organize what the user said, not what you think they should have said. If they didn't mention error handling, don't add error handling instructions. If they didn't mention output format, ask or leave it open.
2. Never write files without approval. Always present in conversation first.
3. Scale structure to complexity. Simple = lean. Complex = structured. Never the reverse.
4. Respect their voice. If the rough notes have a specific tone or personality, preserve it in the structured version.
5. Run the AI Self-Check. Every generated prompt file gets verified against the checklist before returning.