Skip to content
TrustedSkillsbeta
Back to all skills

Prompt Enhancer

Checked
samhvw8·vlatest·ai-ml

This Prompt Enhancer refines your prompts for better AI responses—boosting clarity and quality for more effective results.

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 samhvw8/dot-claude --skill prompt-enhancer -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

samhvw8

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 samhvw8/dot-claude at 28c7616211.

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

Commit
28c7616211
Manifest
skills/prompt-enhancer/SKILL.md
Scanned
1 file, 371 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 Prompt Enhancer transforms user prompts into optimized, production-ready versions. It focuses on conciseness, clear structure, and efficient token usage for AI agents and sub-agents. The skill aims to improve prompt clarity while maintaining semantic accuracy and backward compatibility, potentially reducing LLM output tokens and API costs.

When to use it

  • When a user explicitly requests improvements or optimization of a prompt.
  • When the user submits an unclear, verbose, or poorly structured prompt.
  • When a user wants to reduce LLM output tokens or API costs.
  • When a user needs help writing prompts for agents or automation.

Key capabilities

  • Conciseness: Removes unnecessary words while preserving intent.
  • Structure: Uses clear formatting with multiple lines and logical sections, potentially including XML tags for clarity.
  • Token Optimization: Reduces LLM output tokens to lower API costs.
  • Task-Based Techniques (Optional): Can apply techniques like Chain-of-Thought (CoT), Chain-of-Draft, Few-Shot Learning, ReAct, Self-Consistency, Tree-of-Thoughts, Role-Based Prompting, and Least-to-Most Prompting when appropriate.
  • Clean Output: Returns only the enhanced prompt without additional commentary.

Example prompts

  • "Can you improve this prompt: 'Write a short story about a cat'?"
  • "Optimize this prompt for token efficiency: 'Summarize this article and extract key entities.'"
  • "I need help writing a prompt to guide an agent through a complex process."

Tips & gotchas

  • The skill automatically applies optimization techniques, but it’s best used when the user explicitly requests prompt enhancement.
  • While XML integration is possible, ensure that the main task or quest isn't wrapped within XML elements.
  • Techniques like Chain-of-Thought are applied selectively only if they demonstrably improve the outcome.