agentsclimarketplace

Prompt to skill

Skill thevibethinker/vibe-thinker-skills/prompt-to-skill

Portable, standalone Zo Computer skills you can install, reuse, and share.

Install
npx -y skills add thevibethinker/vibe-thinker-skills --skill prompt-to-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Convert complex prompts into reusable skills. Assess whether a prompt should become a skill, then scaffold a cleaner starter structure with stronger defaults and less template slop.

SKILL.md

4.6 KB, as published. Nobody here has run it

Prompt to Skill

Overview

This skill helps you decide when a prompt has become complicated enough to deserve its own skill, then gives you a better starter structure to build from.

The goal is not just to create folders. The goal is to turn an overgrown prompt into something another person — or a future version of you — can actually understand, route into, and maintain.

Quick Start

# Assess a prompt for conversion eligibility
python3 Skills/prompt-to-skill/scripts/assess.py "Prompts/MyPrompt.prompt.md"

# Scaffold a new skill with stronger default files
python3 Skills/prompt-to-skill/scripts/scaffold.py my-new-skill

# Optionally set the author field in generated frontmatter
python3 Skills/prompt-to-skill/scripts/scaffold.py my-new-skill --author your-handle.zo.computer

When to Use This Skill

Use this skill when a prompt is doing too much and would be clearer as a reusable capability.

Good candidates usually:

  • have multiple phases or decision points
  • reference scripts, tools, files, or external systems
  • require structured outputs or repeatable setup
  • need durable docs instead of conversational context
  • are likely to be reused, delegated, or shared

What the Scaffold Generates

The scaffold creates a stronger starter package than a bare placeholder:

  • SKILL.md with a real structure and a clearer acceptance bar
  • README.md for maintainer-facing context and first edits
  • scripts/main.py as a working example CLI entrypoint
  • references/NOTES.md for deeper implementation details
  • assets/.gitkeep when static resources are needed later

This is intentionally still a starter. You should replace the generic example behavior with the real workflow before publishing.

Eligibility Criteria

The assessment script evaluates prompts based on:

  • Length: 200+ lines suggests rising complexity
  • Script references: python3, bun, or N5/scripts/ usage
  • Phase structure: multiple steps or workflow stages
  • Schema requirements: JSON/YAML output specifications
  • Prompt references: dependencies on other prompts or skills
  • File operations: repeated file manipulation or transforms
  • Code blocks: embedded logic that should probably live elsewhere

Scoring thresholds:

  • 15+: strong conversion candidate
  • 8-14: convert if reuse/maintenance pain is real
  • Below 8: probably keep it as a prompt

Recommended Conversion Process

  1. Assess the prompt to see whether it has enough complexity to justify a skill.
  2. Decide the boundary: what belongs in docs, scripts, references, and assets?
  3. Scaffold the skill with a usable starter structure.
  4. Extract reusable logic from the prompt into files with clear roles.
  5. Tighten the docs so routing and prerequisites are obvious.
  6. Test the quick start and one real example workflow.
  7. Replace or slim the original prompt so it points to the new skill instead of duplicating it.

Usage

Assessment

# Basic assessment
python3 Skills/prompt-to-skill/scripts/assess.py "Prompts/MyPrompt.prompt.md"

# JSON output for scripting
python3 Skills/prompt-to-skill/scripts/assess.py "Prompts/MyPrompt.prompt.md" --json

Scaffolding

# Create a new skill in the default Skills/ directory
python3 Skills/prompt-to-skill/scripts/scaffold.py my-skill-name

# Create in a custom base directory
python3 Skills/prompt-to-skill/scripts/scaffold.py my-skill-name --base /path/to/directory

# Set a better author value in generated frontmatter
python3 Skills/prompt-to-skill/scripts/scaffold.py my-skill-name --author your-handle.zo.computer

Quality Bar for the Generated Skill

Before calling the scaffolded result reusable, make sure:

  • the description clearly says what the skill does and when to use it
  • the quick start actually works
  • required secrets, integrations, and runtime assumptions are explicit
  • examples contain no private names, paths, or tokens
  • the file reads like instructions, not leftover brainstorming

Implementation Notes

  • Skill names must be lowercase with single hyphen separators
  • The scaffold is designed to reduce blank-template drift, not eliminate editing entirely
  • If a skill does not need code, remove scripts/ rather than keeping dead starter files
  • If a skill grows long, move detailed implementation notes into references/ rather than bloating SKILL.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.