mcpField
T
testing

testing

github.com/nmnmccTesting & quality351 installsUpdated 7w ago
Repository

About testing

A testing skill for deciding when to add or run a test based on concrete uncertainty and the value of its result. It guides agents to define the behavior, choose a boundary with an independent oracle, exercise a distinguishing case, and report what remains untested.

Key features

  1. 01Identify concrete uncertainty
  2. 02Define possible wrong behavior
  3. 03Choose a boundary and oracle
  4. 04Test distinguishing cases and recovery
  5. 05Report untested areas

Use cases

  1. 01Deciding whether a change needs a new test
  2. 02Selecting a focused test for a suspected failure
  3. 03Reporting test evidence before a release decision

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nmnmcc/skills --skill testing

After installing, type/testingin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlreferences/guide.md

Details

From the project README

Testing

Treat a test as an experiment. Add or run one when a concrete unknown remains, a credible wrong behavior is possible, and the result would change the implementation or release decision.

  1. State the required behavior and the wrong behavior still left open.
  2. Choose the smallest boundary with an independent oracle.
  3. Exercise the case, boundary, failure, or recovery that can distinguish them.
  4. Read every result and report what remains untested.

Read the detailed guide for test sensitivity, doubles, flaky signals, properties, or suite design. A justified "no new test" is a valid result when existing evidence is sufficient.

Comments

Markdown supported