Skip to content

gpsaggese/helpers / .claude/skills/blog.write_ml_tutorial

blog.write_ml_tutorial

Verified

Write a blog post about an ML library or technique for a technical audience

FileKindSize
SKILL.mdskill md1.6 KB
---
description: Write a blog post about an ML library or technique for a technical audience
model: opus
---

# Goal
- Write a blog post about using an ML library or technique in a real-world
  application
- Target a technical audience with an ML and AI background that may not know the
  library or technique
- Promote the library and explain its benefits in simple terms
- Explain why it is better than alternatives for the use case

# Workflow

## Write the Post
- Follow this structure:
  - Title
  - **Subtitle**: short description of the post, in first person
  - **Introduction**: explain the library or technique and its benefits in simple
    terms
  - **Competitors**: explain the main competitors and why this library may be better
  - **Problem Statement**: explain the problem and how the library or technique
    solves it
  - **Solution**: explain the solution with code snippets, output examples, and
    screenshots, simple enough to follow without running the code
  - **Conclusion**: summarize the benefits and why it is better for the use case
  - **References**: list the references used to write the post
- Give each section a concise, interesting title

# Conventions
- Use Markdown and LaTeX for math equations
- Use Graphviz for diagrams
- Use the images referenced in the Markdown and Jupyter Notebook files in the
  project

# Verification
- [ ] Confirm the post follows the required structure (Title, Subtitle,
      Introduction, Competitors, Problem Statement, Solution, Conclusion,
      References)
- [ ] Confirm code snippets and screenshots let the reader follow along without
      running the code
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall