Skip to content
How I AIHow I AI

Claude Skills explained: How to create reusable AI workflows

Today I dive into Anthropic’s latest feature that lets anyone create reusable workflows for Claude—no coding required. I break down exactly what Claude Skills are, how to build them from scratch, and how to use them inside Claude Code and Cursor to automate recurring AI tasks like generating PRDs, writing changelog summaries, and turning demo notes into follow-up emails. *What you’ll learn:* 1. What Claude Skills are and how they differ from Claude Projects and custom GPTs 2. How to structure a Skill (metadata, instructions, and linked files) 3. Why defining workflows in natural language beats rigid automation tools 4. How to create Claude Skills using Claude Code and Cursor 5. How to validate your skills with Python scripts and folder references 6. How to upload and use Claude Skills inside Claude’s web or desktop app 7. Practical examples: turning changelogs into newsletters, demo notes into emails, and more *Brought to you by:* ChatPRD—An AI copilot for PMs and their teams: https://www.chatprd.ai/howiai *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction (01:39) What are Claude Skills and how do they work? (08:30) The structure of Claude Skills files (11:00) Demo: Creating Skills using Claude’s built-in skill creator (16:08) A more efficient workflow: Creating Skills with Cursor (17:42) Using Python validation scripts (18:37) Testing Skills with Claude Code (20:52) Creating a changelog-to-newsletter Skill (22:16) Creating a demo-to-follow-up-email Skill (23:45) Uploading Skills to the Claude web interface (26:04) Conclusion and summary *Tools referenced:* • Claude: https://claude.ai/ • Claude Code: https://claude.ai/code • Cursor: https://cursor.sh/ *Other references:* • Equipping agents for the real world with Agent Skills: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills • Anthropic Skills Documentation: https://docs.claude.com/en/docs/claude-code/skills?utm_source=chatgpt.com • Claude Projects: https://claude.ai/projects _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire Vohost
Oct 22, 202527mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Build reusable Claude workflows using Skills, Cursor, and Claude Code

  1. Claire Vo explains Anthropic’s new Claude Skills feature as a lightweight way to package reusable, task-specific instructions (and optional files/scripts) that Claude can invoke on demand.
  2. She clarifies that a “Skill” is essentially a folder containing a required SKILL.md (with metadata + instructions) plus optional referenced resources and executable Python scripts for validation or consistent logic.
  3. After trying Claude’s built-in “create a skill” flow (which produced too many files and had download friction), she recommends a faster workflow: generate Skills in Cursor using the docs, then run and iterate them in Claude Code.
  4. She demos creating and using two practical Skills (changelog→newsletter and demo notes→follow-up email), then shows how to zip and upload a Skill to the Claude web UI, noting naming constraints (lowercase/hyphenated).

IDEAS WORTH REMEMBERING

5 ideas

Claude Skills enable on-demand, reusable AI workflows.

Instead of copying prompts from docs or relying on always-on project context, Skills let Claude pull in task-specific instructions when the conversation context calls for them.

A Skill is a folder, not a “magic agent object.”

The core asset is a folder containing SKILL.md plus any supporting files; you either point Claude Code at that directory or zip it for upload to claude.ai.

Good Skills combine metadata + highly explicit instructions.

The YAML metadata (name/description) helps Claude choose when to use the Skill, while detailed instructions define the workflow, output format, and decision points.

Relative file references help manage context cleanly.

You can keep templates, examples, and extra guidance in adjacent files and link them (e.g., ./templates/...), so Claude only pulls what’s needed rather than bloating the main prompt.

Python scripts reduce variability and add guardrails.

Bundled scripts can validate formatting (e.g., YAML correctness, required sections) or implement consistent transformations, avoiding “LLM rewrites the tool every time” drift.

WORDS WORTH SAVING

5 quotes

Claude Skills solves a really interesting problem for anybody using AI, which is reusable workflows with a set of instructions that you wanna call on demand.

— Claire Vo

A Claude Skill, the actual object, the thing that you make, is a folder.

— Claire Vo

My preference... is, you know what? If these models are so great at natural language, we should be able to define things in natural language.

— Claire Vo

It created 12 files when I really only needed five.

— Claire Vo

I just said, 'Okay, here's the latest changelog'... and it inferred what I wanted, based on the skills available in my folder.

— Claire Vo

What Claude Skills are and why they matterSkills vs Projects/Custom GPTs (dynamic, task-specific invocation)Skill folder anatomy: SKILL.md + resourcesMetadata (YAML), instructions, relative file referencesPython scripts for validation and consistencyWorkflow: Cursor for authoring, Claude Code for testingDeploying to claude.ai via zip + naming constraints

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome