Skip to content
Development
Skill

/cad-coverage

Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in the project's own framework

From plugin
cadence
534 skills30 agents3 hooks
Install
$ npx -y skills add crenshawdev/cadence --skill cad-coverage --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/cad-coverage

Context preview

The summary Claude sees to decide when to auto-load this skill.

Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in the project's own framework

SKILL.md

cad-coverage.SKILL.md
name: cad-coverage
description: "Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in the project's own framework"
argument-hint: "[phase number]"
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Grep
  - Glob
  - AskUserQuestion

<objective> Close the test-coverage gaps for a completed phase. One question drives it: which phase requirements have NO test that would fail if that requirement regressed? Those are the gaps. Audit them, then generate real tests to cover them, in the project's own test framework.

Audit and generate in one un-duplicated flow. No fixed stack, no Playwright/E2E default - the test kind and runner follow the code and `workflow.test_command`. </objective>

<execution_context> @${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/coverage.md </execution_context>

<process> Run the coverage workflow end-to-end. Coverage means a test that would FAIL if the requirement broke - not a test that merely runs the code. Get user approval on the gap test plan before generating, and verify generated tests actually run. </process>

Ships withcadence

Appearance is cheap. Verification is the work. Cadence is for developers using Claude Code on software they will still own after the session ends. Claude can write a convincing plan, produce working code, and tell you the job is finished.

Get the whole plugin

Other skills on cadence.