Skip to content
TrustedSkillsbeta
Back to all skills

Skill Authoring Workflow

Checked
deanpeters·vlatest·other

DeanPeters' skill-authoring-workflow streamlines creation of custom AI skills through guided templates and automated testing.

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 deanpeters/product-manager-skills --skill skill-authoring-workflow -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

deanpeters

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 deanpeters/product-manager-skills at cfcb697f14.

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

Commit
cfcb697f14
Manifest
skills/skill-authoring-workflow/SKILL.md
Scanned
3 files, 421 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, DeanPeters' Skill Authoring Workflow, streamlines the creation and updating of AI skills. It transforms initial ideas, workshop content, or draft prompts into fully compliant SKILL.md assets ready for inclusion in a repository. The workflow ensures consistency and quality by enforcing standards and automated testing throughout the process.

When to use it

  • When you have an idea for a new skill but need guidance on structuring it.
  • When you already have existing content (like research or workshop materials) that needs to be formatted into a skill.
  • When refining an existing skill and ensuring it meets all requirements.
  • To avoid inconsistent quality ("looks good to me" roulette) when creating new skills.

Key capabilities

  • Guided Wizard: Helps create a skill from initial ideas using interactive prompts (build-a-skill.sh).
  • Content-first Generator: Converts existing source content into a skill format (add-a-skill.sh).
  • Automated Validation: Includes scripts to check frontmatter validity, section order compliance, metadata limits, and cross-reference resolution (test-a-skill.sh, check-skill-metadata.py, check-skill-triggers.py).
  • Workshop Facilitation Protocol: Defines a structured conversation flow for guided skill creation using numbered prompts and options.

Example prompts

  • "Run the guided wizard to help me create a new skill." (build-a-skill.sh)
  • "Convert my research document into a skill." (add-a-skill.sh research/your-framework.md)
  • "Test the skill 'my-new-skill' for compliance." (test-a-skill.sh --skill my-new-skill --smoke)

Tips & gotchas

  • Preflight is crucial: Use ./scripts/find-a-skill.sh to avoid creating duplicate skills.
  • Follow the workflow sequence: This document defines the logic and outputs, taking precedence over other instructions.
  • Strict validation: Always run the automated tests (test-a-skill.sh, check-skill-metadata.py) before committing changes.