Skip to content
TrustedSkillsbeta
Back to all skills

Meta Prompt

Checked
mindrally·vlatest·ai-ml·Apache-2.0

Meta Prompt helps refine your prompts for optimal AI responses by suggesting improvements and variations – boosting clarity & effectiveness.

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 mindrally/skills --skill meta-prompt -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

mindrally

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 mindrally/skills at 7682ca7771.

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

Commit
7682ca7771
Manifest
meta-prompt/SKILL.md
Scanned
1 file, 123 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

The Meta Prompt skill provides tools to improve AI response quality through evaluation and analysis of solution paths. It offers a framework for critiquing responses, assigning scores (0-10), and determining if a complete solution has been provided. Additionally, it guides the analysis of the reasoning steps taken by an agent towards answering questions or completing tasks.

When to use it

  • When you need to assess the quality of an AI's response to ensure accuracy and completeness.
  • To understand how an AI arrived at a solution, identifying potential areas for improvement in its reasoning process.
  • When debugging an agent’s problem-solving approach by examining its observations, thoughts, and actions.
  • For evaluating the clarity and conciseness of generated text.

Key capabilities

  • Response Quality Evaluator: Provides a structured framework for assessing AI responses with fields for reflections, score (0-10), and solution status (found_solution).
  • Evaluation Criteria: Offers specific criteria to guide response evaluation: accuracy, completeness, clarity, conciseness, and relevance.
  • Question-Answering Trajectory Analyzer: Enables analysis of the steps taken by an AI agent, including observations, thoughts, and actions.
  • Action Types: Defines specific action types like Search[entity] and Lookup[keyword] for analyzing agent behavior.

Example prompts

  • "Evaluate this response: [AI Response]"
  • "Analyze the trajectory of how you arrived at this answer."
  • "Critique this solution based on accuracy, completeness, and clarity."

Tips & gotchas

  • The skill is designed for evaluating existing AI responses or analyzing completed task trajectories. It doesn't directly generate content itself.
  • Pay close attention to the evaluation criteria when providing feedback; thoughtful reflections are encouraged.
  • found_solution should only be set to true if the response fully addresses the question or completes the task.