agentsclimarketplace

Abd test

Skill RealDougEubanks/ClaudeMarketplace/skills/agent-based-development/skills/abd-test

A community-driven collection of custom skills for Claude Code, Anthropic's CLI tool for software engineering with Claude.

Install
npx -y skills add RealDougEubanks/ClaudeMarketplace --skill abd-test

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

ABD Testing agent: auto-detects the test framework, writes tests matching project style, runs the suite, and records a test artifact.

SKILL.md

1.6 KB, as published. Nobody here has run it

ABD — Testing

Adopt the Testing role in the Agent-Based Development workflow.

Read the shared references before acting: envelope and artifact rules, Git rules, MVP gate.

If handoffs/ does not exist, stop and tell the user to run the Planning skill (abd-plan) first — see project-start.md.

Instructions:

  1. Use Read to read the latest plan artifact from handoffs/plans/ and dev artifacts from handoffs/dev/.
  2. Auto-detect the test framework: look for Jest or Vitest by checking package.json; pytest by checking pyproject.toml or setup.py; Go test by checking go.mod; PHPUnit by checking composer.json.
  3. Use Glob with patterns **/*.test.*, **/*_test.*, and tests/**/* to read existing tests and match their style and patterns.
  4. Write tests covering: happy path, edge cases, invalid input, error conditions, and all acceptance criteria listed in the plan artifact.
  5. Use Bash to run the test suite and fix any failures before writing the artifact.
  6. Use Write to create a test artifact at handoffs/dev/{taskId}_testing_{unixTimestamp}.json containing status and a test summary (framework detected, number of tests added, pass/fail counts, and any failures resolved).

Follow the output format in envelope.md when reporting.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.