AgentStack
SKILL verified MIT Self-run

Tdd Intelligence

skill-cobusgreyling-grok-build-arsenal-tdd-intelligence · by cobusgreyling

|

No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-cobusgreyling-grok-build-arsenal-tdd-intelligence

✓ 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.

Are you the author of Tdd Intelligence? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

TDD Intelligence

True test-driven development with agentic discipline.

Core Loop

  1. Understand the desired behavior (read existing code, docs, issues).
  2. Write the smallest failing test (or characterization test for legacy) that expresses the goal.
  • Run the test and confirm it fails for the right reason.
  1. Implement the minimal code to make the test pass.
  2. Refactor for cleanliness while keeping tests green.
  3. Add any additional edge-case or regression tests suggested by the implementation.
  4. Verify the full relevant test suite still passes.

For Refactors and Legacy Code

  • First write characterization tests that lock in current (even if imperfect) behavior.
  • Then change implementation.
  • Confirm the characterization tests still pass (proving behavior preservation).

Rules

  • Never implement before at least one relevant test exists and is failing appropriately.
  • Prefer focused unit tests over broad integration tests for the core logic.
  • When editing UI or complex flows, combine with browser-qa or manual verification steps.
  • Update or add tests in the same diff as the feature when possible.

Subagent Support

Use a subagent to:

  • Explore the test surface area before writing tests.
  • Generate additional edge cases after the happy path is implemented.

Verification Commands

Always surface the actual commands the project uses:

  • Python: pytest ... -q --tb=short
  • Next.js: npm test or vitest
  • Rust: cargo test

Discover these via the repo rather than assuming.

Success Criteria

  • The new/changed behavior is covered by tests that would have failed before the change.
  • All tests in the affected area are green at the end.
  • Diff size remains reasonable (tests + implementation together).

Anti-Patterns

  • Writing implementation then retrofitting tests.
  • Skipping tests "because it's simple".
  • Large untested refactors justified by "we'll add tests later".

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.

Versions

  • v0.1.0 Imported from the upstream source.