Skip to content
SkillModel-led2,330 tokens in use

test-driven-development

Enforces red-green-refactor: a failing test first, minimal code to pass it, and deletion of any code written before its test.

322,762 stars on the repository MIT Licenseobra/superpowers · skills/test-driven-development
/plugin install superpowers@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing test-driven-development costs

17tokens idle
2,330tokens in use
4,104tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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

shelldetected

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 →
Excellent
  • Frontmatter12/15
  • Structure11/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources15/15

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 shell commands−5

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

    SKILL.md, line 118

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity56
  • Maintenance68
  • Community64
  • Maturity36
  • Momentum40

Test-Driven Development is the Superpowers skill for every feature, bug fix, refactor and behavior change. Its iron law is no production code without a failing test first. The agent writes one minimal test, runs it and confirms it fails for the right reason, writes the simplest code that passes, then runs the whole suite and refactors while it stays green.

What You Get

  • The red-green-refactor cycle with a diagram and paired good and bad examples
  • Mandatory verify-red and verify-green steps
  • A checklist to confirm before marking work complete
  • A table of common excuses and the reply to each
  • A bug-fix example that begins with a reproducing test

Common Use Cases

  • Building a new feature test first
  • Fixing a bug with a reproducing test
  • Refactoring with a safety net

What Makes It Unique

Many TDD guides describe the cycle. This one sets rules for an agent that talks itself out of tests: it requires deleting code written before its test, makes watching the failure a mandatory step, and extends verification to the full project suite, with any failure reported by name.

Under The Hood

Instructions with TypeScript examples and a reference file on writing good tests. The agent runs the project’s own test command, such as npm test, pytest or cargo test. The skill ships no scripts of its own.

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