Skills test-driven-development
📦

test-driven-development

Content revision r1 Medium Risk ⚙️ External commands

Apply Test-Driven Development

Teams often ship changes without proof that tests catch the intended behavior. This skill guides Claude, Codex, and Claude Code through strict red, green, refactor steps.

Supports: Claude Codex Code(CC)
📊 69 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "test-driven-development" from https://skillstore.io/skills/zhanlincui-test-driven-development.md and its manifest at https://skillstore.io/api/skills/zhanlincui-test-driven-development/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/zhanlincui-test-driven-development.md Signed manifest GET /api/skills/zhanlincui-test-driven-development/manifest Signed lockfile GET /api/skills/zhanlincui-test-driven-development/lockfile

Test it

Using "test-driven-development". Add retry behavior for failed operations.

Expected outcome:

The agent starts with one failing retry test, verifies the failure, adds minimal retry logic, and confirms the test passes.

Using "test-driven-development". Fix empty email validation.

Expected outcome:

The agent writes a failing validation test, implements the smallest validation change, and keeps the full test suite passing.

Using "test-driven-development". Review tests that use many mocks.

Expected outcome:

The agent flags assertions about mock existence and recommends tests that verify user-visible or domain behavior.

Security Audit

Medium Risk
v5 • 7/8/2026 Open versioned report

The static external-command and reconnaissance findings are false positives caused by markdown fences, examples, and ordinary testing language. I found one semantic risk: the skill encourages deleting implementation code when TDD was not followed, which can cause unwanted data loss without user confirmation.

2
Files scanned
672
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
SKILL.md:37-43SKILL.md:288
Destructive Development Workflow Instruction
The skill repeatedly tells agents to delete implementation code and start over when TDD was not followed. This can destroy user work if applied without explicit confirmation or version-control safeguards.
The cited lines directly instruct deletion as a workflow response. The behavior is not malicious, but it creates a real risk of unwanted data loss in active workspaces.

Risk Factors

⚙️ External commands (27)
SKILL.md:33-35 SKILL.md:35-49 SKILL.md:49-69 SKILL.md:69-76 SKILL.md:76-90 SKILL.md:90-95 SKILL.md:95-104 SKILL.md:104-117 SKILL.md:117-119 SKILL.md:119-135 SKILL.md:135-146 SKILL.md:146-151 SKILL.md:151-162 SKILL.md:162-172 SKILL.md:172-174 SKILL.md:174-202 SKILL.md:202-203 SKILL.md:203-295 SKILL.md:295-300 SKILL.md:300-303 SKILL.md:303-306 SKILL.md:306-309 SKILL.md:309-316 SKILL.md:316-319 SKILL.md:319-322 SKILL.md:322-366 SKILL.md:366-369
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/zhanlincui-test-driven-development/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/zhanlincui-test-driven-development/security.svg)](https://skillstore.io/skills/zhanlincui-test-driven-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/zhanlincui-test-driven-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhanlincui-test-driven-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/zhanlincui-test-driven-development.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

ZhanlinCui. (2026). test-driven-development security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhanlincui-test-driven-development/audits/5

BibTeX citation

@techreport{zhanlincui-zhanlincui-test-driven-development-2026, author = {ZhanlinCui}, title = {test-driven-development security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/zhanlincui-test-driven-development/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "test-driven-development security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "ZhanlinCui" date-released: "2026-07-08" url: "https://skillstore.io/skills/zhanlincui-test-driven-development/audits/5" identifiers: - type: other value: "skillstore:zhanlincui-test-driven-development:audit:5" description: "Skillstore immutable audit report identifier"

Compare variants

9 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
DMJGilbert Recommended

dmjgilbert-test-driven-development

Skillstore Score 79
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

obra

obra-test-driven-development

Skillstore Score 78
Evidence Confidence High
Skillstore usage 11
Updated

2026-08-21

Cycleaddict

cycleaddict-test-driven-development

Skillstore Score 78
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

Cygnusfear

cygnusfear-test-driven-development

Skillstore Score 78
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

DYAI2025

dyai2025-test-driven-development

Skillstore Score 75
Evidence Confidence Medium
Skillstore usage 8
Updated

2026-08-21

CodingCossack

codingcossack-test-driven-development

Skillstore Score 74
Evidence Confidence High
Skillstore usage 13
Updated

2026-08-21

ZhanlinCui Current

zhanlincui-test-driven-development

Skillstore Score 69
Evidence Confidence High
Skillstore usage 99
Updated

2026-08-21

sickn33

sickn33-test-driven-development

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

davila7

davila7-test-driven-development

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
85
Content
70
Community
83
Spec Compliance

What You Can Build

Implement a Feature Safely

Use the skill to define the expected behavior as a failing test before adding production code.

Fix a Regression

Reproduce the bug with a failing test, then implement the smallest change that makes it pass.

Improve Test Discipline

Use the checklist and anti-pattern guidance to review whether tests cover real behavior.

Try These Prompts

Start a Small Change 
Use test-driven development for this change. First write one failing test for the expected behavior, then implement the minimum code.
Fix a Bug with Proof 
Reproduce this bug with a failing test before changing production code. Show why the test fails, then make it pass.
Refactor Without Behavior Drift 
Use existing tests or add missing characterization tests first. Refactor only after tests prove the current behavior is covered.
Audit Test Quality 
Review these tests with the TDD and anti-pattern guidance. Identify tests that verify mocks instead of real behavior.

Best Practices

  • Run the new test once before implementation and confirm the failure reason.
  • Keep each test focused on one observable behavior.
  • Refactor only after the relevant tests are green.

Avoid

  • Writing implementation code before a failing test exists.
  • Testing mocks instead of the behavior users or callers receive.
  • Adding test-only methods to production classes.

Frequently Asked Questions

What workflow does this skill enforce?
It enforces red, green, refactor. Write a failing test, make it pass, then clean up safely.
Can it help with bug fixes?
Yes. It asks for a failing regression test before any production fix is added.
Does it run tests automatically?
No. It tells the agent to run the project test command, but execution depends on the workspace and tools.
Does it support Claude Code?
Yes. The report lists support for Claude, Codex, and Claude Code.
What testing styles does it discourage?
It discourages testing mock behavior, incomplete mocks, and production methods that only exist for tests.
When should a user approve exceptions?
A user should approve exceptions for prototypes, generated code, or configuration work before skipping TDD.

Developer Details

Author

ZhanlinCui

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/test-driven-development

Ref

88a205c7f635a966e31156313b590d59007c5caa

Maintenance freshness

7/18/2026

Usage

97 downloads · 182 views

File structure

📄 SKILL.md

📄 testing-anti-patterns.md