AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Test Driven Development

skill-hsienw-ai-agent-engineering-playbook-test-driven-development · by HsienW

Drive implementation with tests. Use when fixing bugs, changing behavior, adding logic, modifying contracts, or proving that agent-written code works and remains safe across regressions.

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-hsienw-ai-agent-engineering-playbook-test-driven-development

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-hsienw-ai-agent-engineering-playbook-test-driven-development)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Test Driven Development? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Test-Driven Development

Skill Interface

  • Name: test-driven-development.
  • Description: Drive implementation with tests when fixing bugs, changing behavior, adding logic, modifying contracts, or proving that agent-written code works and remains safe across regressions.
  • Parameters: Desired behavior, bug reproduction, affected logic or contract, existing tests, suitable test layer, fixtures or inputs, and available test commands.
  • Instructions: Use this skill before or during behavior changes. Start with a failing or relevant test, make the smallest implementation change, refactor while tests stay green, and run adjacent regression checks.

Use tests to prove behavior, not to document implementation trivia.

Cycle

  1. Red: write or identify a failing test that captures the required behavior or

bug.

  1. Green: make the smallest implementation change that passes.
  2. Refactor: simplify while keeping tests green.
  3. Regression: run adjacent existing tests that could be affected.

Bug Fix Pattern

  1. Reproduce the bug with a failing test, fixture, command, trace, or fixed

input/output pair.

  1. Confirm the failure matches the reported issue.
  2. Fix the root cause.
  3. Re-run the same reproduction and relevant regression tests.
  4. Keep the regression test unless it is too expensive and a documented manual

check is more appropriate.

Test Selection

  • Unit tests for deterministic logic.
  • Integration tests for boundaries, adapters, persistence, and schemas.
  • Contract tests for APIs, events, messages, and error envelopes.
  • End-to-end tests for critical user workflows.
  • Smoke tests for live providers only when environment and cost are acceptable.

Rules

  • Do not delete failing tests to get a green run.
  • Do not loosen assertions unless the old assertion was wrong.
  • Do not mock the core behavior being tested.
  • Do not hide races with fixed sleeps.
  • Do not claim unexecuted tests passed.

Coverage Checklist

Consider:

  • Normal success.
  • Invalid input.
  • Unknown fields or variants.
  • Upstream failure.
  • Permission denied.
  • Timeout and cancellation.
  • Retry or duplicate event.
  • Partial result or degraded behavior.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills