Skip to content
TrustedSkillsbeta
Back to all skills

Skill Authoring

Checked
pproenca·vlatest·agents·MIT

Skill Authoring empowers users to easily create and customize AI skills, streamlining development and tailoring automation to specific needs.

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 pproenca/dot-skills --skill skill-authoring -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

pproenca

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 pproenca/dot-skills at cf93c57cac.

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

Commit
cf93c57cac
Manifest
skills/.curated/skill-authoring/SKILL.md
Scanned
52 files, 2,810 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, "Skill Authoring," provides guidance and best practices for creating and optimizing AI agent skills, specifically those designed for Claude Code and utilizing Model Context Protocol (MCP) tools. It offers a design and development guide containing 46 rules across eight categories to improve skill creation, review, and overall effectiveness. The goal is to ensure skills are reliable, easily discoverable, and efficient in their use of context tokens.

When to use it

  • When creating new Claude Code skills or MCP tools.
  • During the writing or reviewing of SKILL.md metadata and descriptions.
  • To optimize skill trigger reliability and ensure activation.
  • For structuring content using progressive disclosure techniques.
  • When testing skill activation behavior and overall functionality.

Key capabilities

  • Description Engineering: Guidance on crafting effective skill descriptions that drive activation through specific capabilities and keywords.
  • Content Structure: Best practices for organizing skill content, including prioritizing critical instructions in the first 100 lines and utilizing progressive disclosure to save tokens.
  • Trigger Optimization: Techniques for ensuring skills trigger reliably with real user phrases and edge cases.
  • MCP Tool Design: Considerations for designing tool interfaces within agent workflows.
  • Skill Metadata Design: Rules for formatting skill names, frontmatter, and directory structure.

Example prompts

While this skill is a guide for creating AI skills, rather than an active tool itself, a user might ask:

  • "What are the best practices for writing a description to ensure my Claude Code skill activates correctly?"
  • "How should I structure my SKILL.md file to use progressive disclosure effectively?"
  • “What are the rules around naming conventions for AI agent skills?”

Tips & gotchas

  • Prioritize Descriptions: Skill activation heavily relies on accurate and descriptive metadata. Vague descriptions can lead to inconsistent or failed activations.
  • Front-load Important Information: Claude may truncate longer content, so place essential instructions and constraints within the first 100 lines of the SKILL.md file.
  • Test Activation Thoroughly: Don't just test execution; ensure your skill triggers reliably with various user inputs.