tdd
An agent skill by cursor, from cursor/plugins. Tags: debugging, development, qa, testing, validation.
What it does
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill tddOr 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/cursor/plugins
cp -r plugins/pstack/skills/tdd ~/.claude/skills/tddSafety box score
Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-16. 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 documentation-only TDD workflow skill. It mainly tells the agent to write and run focused regression tests or the closest executable check before fixing a bug, so the only real exposure is local test execution and any automation used to reproduce the bug.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | The skill explicitly directs the agent to run tests and other executable checks, e.g. "Run the new test before fixing" and "use the closest executable regression check". |
| Network access | 0 (none) | No network calls, downloads, or remote data transfers are defined in the skill file. |
| Filesystem reach | 0 (none) | It does not instruct writes, deletes, or edits outside the project; it only discusses creating or running regression tests in the local codebase. |
| Secrets & credentials | 0 (none) | The skill never asks for tokens, keys, passwords, env files, or other secret material. |
| Privilege & persistence | 0 (none) | There is no sudo, global install, service registration, or shell/OS configuration change in the skill. |
| Instruction hijack surface | 0 (none) | The file contains normal workflow guidance only; it does not tell the agent to ignore instructions, hide actions, or follow remote content. |
| Irreversible actions | 1 (low) | It authorizes the agent to carry out local regression checks, including "manual reproduction command" and "browser automation," but not to deploy, send messages, or otherwise act externally. |
| Transparency | 0 (none) | The skill file is plain Markdown with no binaries, embedded code blobs, or unreadable installers. |
Before installing
- Confirm your project’s tests are safe and cheap to run locally, since this skill prefers executing them before any fix.
- If your bug reproduction might use browser automation, verify that a local browser session is acceptable in your environment.
- Check whether you want a strict test-first workflow; this skill will push the agent to create a regression check when one is practical.
Rated 2026-10-16 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- pstack/skills/tdd/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- blast-radius — Find what a change could break somewhere else before it ships, beyond the diff.
- check-compiler-errors — Run compile and type-check commands and report failures
- control-cli — Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.
- control-ui — Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.
- principle-prove-it-works — Apply after completing a task, before declaring done.
- principle-test-behavior-not-implementation — Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value.