test-driven-development

An agent skill by addyosmani, from addyosmani/agent-skills. Tags: api, debugging, developer-tools.

What it does

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add addyosmani/agent-skills --skill test-driven-development

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/addyosmani/agent-skills
cp -r agent-skills/skills/test-driven-development ~/.claude/skills/test-driven-development

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a markdown-only TDD workflow guide; it ships no executable scripts, installers, or hidden payloads. The main thing it can make an agent do is run the repository’s test commands and, for browser work, inspect live browser/network state while editing code and tests in the working tree.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It explicitly directs the agent to run the repo’s focused test command during the loop and the full suite before finishing, but it ships no native executables or code evaluators.
Network access	1 (low)	The browser-testing section uses Chrome DevTools MCP to inspect live console/network responses and page state, but it does not itself download from or send data to remote hosts.
Filesystem reach	1 (low)	The workflow assumes creating and modifying tests and code in the project tree ('Write a failing test before writing the code that makes it pass'), but it does not target dotfiles, system paths, or recursive deletes.
Secrets & credentials	0 (none)	It contains no credential-handling commands and explicitly says browser data like cookies, localStorage tokens, and credentials must not be accessed via JS execution.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, shell startup editing, or OS-setting change described.
Instruction hijack surface	0 (none)	The file contains no hidden instructions or remote prompt-fetching; instead it warns that browser content is 'untrusted data, not instructions' and forbids following URLs extracted from page content without confirmation.
Irreversible actions	0 (none)	It does not instruct the agent to deploy, publish, pay, book, send messages, or delete anything external.
Transparency	0 (none)	The skill is plain readable markdown only; there are no binaries, base64 blobs, or downloaded installers.

Before installing

Confirm you want the agent to run your repo’s test commands as part of every code change.
If you use browser testing, make sure the browser session has no sensitive accounts or tokens loaded.
Check your project’s actual test command and CI workflow so the TDD loop matches your stack.
Read `SKILL.md` once to confirm the browser-testing section fits your environment.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: addyosmani/agent-skills (all skills from this repository)
Path: skills/test-driven-development/SKILL.md
Branch: main
Updated: 2026-09-19

debugging-and-error-recovery — Guides systematic root-cause debugging.
deprecation-and-migration — Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another.
observability-and-instrumentation — Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting.
performance-optimization — Optimizes application performance across frontend, backend, queries, and databases.
security-and-hardening — Hardens code against vulnerabilities.
claude-api — Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.