Skip to content
TrustedSkillsbeta
Back to all skills

Skill Creator

Checked
davepoon·vlatest·agents·MIT

This Skill Creator allows you to easily build custom AI agent skills, streamlining workflows and automating complex tasks efficiently.

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 davepoon/buildwithclaude --skill skill-creator -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

davepoon

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 davepoon/buildwithclaude at fc03a95b41.

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

Commit
fc03a95b41
Manifest
plugins/all-skills/skills/skill-creator/SKILL.md
Scanned
5 files, 683 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 Skill Creator skill provides guidance and structure for building custom AI agent skills that extend Claude’s capabilities. These skills act as onboarding guides, transforming Claude into a specialized agent with procedural knowledge. They enable the creation of workflows, tool integrations, domain expertise bundles, and resources to automate complex tasks efficiently. A skill consists of a SKILL.md file (required) and optional bundled resources like scripts and references.

When to use it

  • To create specialized workflows for specific domains or tasks.
  • When needing instructions for integrating with particular file formats or APIs.
  • For incorporating company-specific knowledge, schemas, or business logic into Claude's responses.
  • To bundle repetitive scripts and resources for complex tasks.

Key capabilities

  • Structured Skill Creation: Provides a defined format (SKILL.md + optional bundled resources) for creating skills.
  • Specialized Workflows: Enables the creation of multi-step procedures for specific domains.
  • Tool Integrations: Facilitates instructions for working with file formats and APIs.
  • Domain Expertise: Allows incorporation of company-specific knowledge and business logic.
  • Bundled Resources: Supports scripts, references, and assets to streamline complex tasks.
  • Script Integration: Allows inclusion of executable code (Python/Bash) for deterministic reliability or repetitive tasks.
  • Reference Material: Enables the inclusion of documentation (e.g., API specifications, company policies) that Claude can load as needed.

Example prompts

While this skill itself doesn't do anything directly, a user might prompt an AI agent with:

  1. "Create a Skill for rotating PDFs."
  2. "I need to build a skill that guides me through our company’s NDA process. What should the SKILL.md file contain?"
  3. "How can I best structure a skill to incorporate our API documentation?"

Tips & gotchas

  • Metadata is Key: The name and description in the YAML frontmatter of the SKILL.md file are crucial for determining when Claude will use the skill, so be specific.
  • Avoid Duplication: Information should reside either in the SKILL.md or reference files; avoid redundancy.
  • Large Files: For large reference documents (>10k words), include grep search patterns within the SKILL.md file to optimize loading.