Skip to content
SkillModel-led892 tokens in use

Scaffold Exercises

Create exercise section and lesson folders with problem, solution and explainer stubs that pass the ai-hero-cli lint, then commit.

328,791 stars on the repository MIT Licensemattpocock/skills · skills/misc/scaffold-exercises
claude plugin install mattpocock-skills@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Scaffold Exercises costs

45tokens idle
892tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedwrites filesdetectedgitdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples15/15
  • Output10/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs git commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 76
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 76
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 76

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

Scaffold Exercises creates the directory structure for a course: numbered sections, numbered exercises and the problem, solution and explainer subfolders, each with a non-empty readme. It then runs the ai-hero-cli lint and fixes errors until it passes.

It also covers renaming and renumbering exercises with git mv.

What You Get

  • Section folders named XX-section-name and exercise folders named XX.YY-exercise-name
  • Stub readme files in each variant folder
  • A lint run that passes
  • A git commit of the result

Common Use Cases

  • Stubbing a new course section from an outline
  • Adding an exercise with explainer, problem and solution variants
  • Renumbering exercises while keeping git history
  • Fixing lint errors about empty readmes or stray gitkeep files

What Makes It Unique

It is specific to the ai-hero-cli course format, so it knows the lint rules: gitkeep files and speaker notes are banned, links must resolve and code folders need a main file. It defaults to an explainer stub when the plan is silent.

Under The Hood

The skill is Markdown with shell examples and an agent metadata file for Codex. The agent runs mkdir, writes readme files, runs pnpm ai-hero-cli internal lint, uses git mv for renames and finishes with git commit. All work stays inside the exercises folder of your repository.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers