agentleFS
pchemguypchemguy/Skill-SDD-Manager/skills/sdd-tdd/SKILL.md

sdd-tdd

Skill0 starsChanged 37 days agoMITView on GitHub

Use when defining an SDD project's testing strategy, deriving test scenarios from accepted contracts, writing or reviewing tests, reproducing a bug, or guiding a test-first red-green-refactor cycle for a selected implementation task.

The file

Files
SKILL.md

Design tests and guide test-first implementation

Choose the requested operation and load its references:

WorkLoad
Define testing strategy and scenario coveragetesting strategy
Guide a feature, bug fix, or behavior change through TDDtest-first cycle and writing good tests
Write, revise, or review tests, doubles, or test helperswriting good tests

Use the selected TASKS or FEATURE-TASKS entry, accepted SPEC contracts, relevant design, PLAN and layout, inspected implementation, and project test commands. sdd-manage coordinates scope and a current sdd-orient handoff establishing Git eligibility, governing instructions, and ownership of dirty changes. Strategy and review can remain read-only; test edits and execution follow the authorized scope and environment.

For new or changed behavior and bug fixes, establish a test that fails for the intended reason before the production change. Observe the failure, guide the smallest implementation that satisfies the accepted contract, and refactor with checks remaining green. sdd-tdd owns test strategy, scenarios, test changes, and development-cycle test execution. The active implementation workflow, sdd-implement for main task work or sdd-steer for a checkpoint amendment, owns production changes and applies the GREEN and production-refactoring steps; this skill supplies the test and evidence at each handoff. A strategy-only request does not authorize implementation.

Preserve existing work when resuming. If code predates the tests, report missing test-first evidence and use characterization or a safe isolated baseline where appropriate; do not delete or reset code to reconstruct an unobserved history. Follow applicable project policy and previously authorized exceptions for work that cannot use a meaningful test-first cycle. When an exception is still required and undecided, explain the concrete limitation and defer that decision to the user.

Return the testing strategy or test changes, covered contracts and scenarios, actual RED and GREEN commands and outcomes, regression results, remaining coverage gaps, and any exception or blocker. Do not invent a failed run or infer whole-project correctness from a focused passing test. sdd-verify owns the verification campaign and acceptance assessment; the active implementation workflow owns completion updates, commits, pushes, and issue-closure coordination. sdd-docs owns documentation maintenance and sdd-report presents completion evidence.

This skill adapts both Superpowers TDD and its test-writing companion. See upstream provenance and adaptation and the included license.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.