Skip to content
TrustedSkillsbeta
Back to all skills

Create Meta Prompts

Checked
kyldvs·vlatest·ai-ml·MIT

Generates optimized, layered prompts to guide AI models toward more nuanced and complex creative outputs.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add kyldvs/setup --skill create-meta-prompts -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

kyldvs

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned kyldvs/setup at c9a0ecb004.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
c9a0ecb004
Manifest
.claude/skills/create-meta-prompts/SKILL.md
Scanned
11 files, 3,008 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows you to generate meta-prompts, which are prompts designed to guide and improve the performance of other AI agents. It helps craft instructions that shape an agent's behavior, output style, or reasoning process. The tool is specifically designed for creating these higher-level prompting structures rather than direct task requests.

When to use it

  • Refining Agent Behavior: You want to encourage a specific tone (e.g., formal, humorous) in responses from another AI agent.
  • Improving Reasoning: You need an agent to think step-by-step or explain its reasoning before providing an answer.
  • Controlling Output Format: You require the output of another agent to adhere to a specific structure (e.g., JSON, Markdown table).
  • Defining Roles & Constraints: You want to clearly define the role and limitations for an AI agent performing a task.

Key capabilities

  • Generates meta-prompts.
  • Designed for guiding other AI agents.
  • Shapes behavior, output style, and reasoning.

Example prompts

  • "Create a meta-prompt that instructs an AI to respond in the style of Ernest Hemingway."
  • "Generate a prompt to guide an agent to think step by step before answering questions about history."
  • "I need a meta-prompt to ensure an agent always outputs data as a JSON object. Can you create one?"

Tips & gotchas

The effectiveness of this skill relies on understanding how to structure prompts for other AI agents. It's not intended for directly executing tasks, but rather for crafting the instructions that other agents will follow.