Skip to content
SkillModel-led3,698 tokens in use

test-driven-development

Write the failing test first, make it pass with minimal code, then refactor, and reproduce every bug with a test.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/test-driven-development
npx skills add addyosmani/agent-skills --skill test-driven-development
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing test-driven-development costs

120tokens idle
3,698tokens 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

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
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources10/15

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

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Test-Driven Development drives an agent through the red, green and refactor loop for new logic, behavior changes and bug fixes. The agent first discovers how this repository runs tests, then writes a failing test, makes it pass with minimal code and cleans up with tests still green.

The skill adds the Prove-It pattern for bugs, the test pyramid and test sizes, advice on DAMP tests, state-based assertions and real implementations over mocks, an anti-pattern table and a browser testing section that uses Chrome DevTools MCP.

What You Get

  • The red, green and refactor cycle with TypeScript examples
  • A Prove-It bug fix flow
  • Guidance on test levels, test sizes and test doubles
  • A browser testing section, an anti-pattern table and a verification checklist

Common Use Cases

  • Implementing new logic
  • Fixing a reported bug
  • Changing existing behavior safely
  • Improving the quality of an existing test suite

What Makes It Unique

The skill starts by finding the repository’s actual test commands and refuses to assume npm test. It also suggests a subagent to write the reproduction test without knowledge of the fix, and it says to exercise real crash and rollback boundaries in place of injected exceptions.

Under The Hood

The skill is a single SKILL.md of instructions with TypeScript examples. It runs no scripts of its own. The agent reads build and CI files, runs the repository’s focused-test and full-suite commands, and may use Chrome DevTools MCP for browser checks and a subagent for the reproduction test. It points to a testing patterns reference.

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