agentsclimarketplace
Sign in

Abd test

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

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

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.

SKILL.md

1.6 KB, 336 tokens by cl100k_base, 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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most test skills give in 336 tokens

Counted across 1,201 of the 2,096 authors here whose files we hold, read 2026-09-06

  • Write a failing test before writing codein 43 of 1201, across 36 files
  • Run the full test suitehere, and in 36 of 1201, across 35 files
  • Test only one variable per experimentin 34 of 1201, across 17 files
  • Read product marketing context before asking questionsin 34 of 1201, across 14 files
  • Mock external dependenciesin 34 of 1201, across 30 files
  • Define primary, secondary, and guardrail metricsin 33 of 1201, across 16 files
  • Pre-determine sample size before startingin 31 of 1201, across 14 files
  • Test behavior rather than implementationin 31 of 1201, across 29 files
  • Formulate a hypothesis before designing a testin 30 of 1201, across 13 files
  • Document every test hypothesis, variant, and resultin 29 of 1201, across 11 files
  • Use descriptive test function namesin 25 of 1201, across 21 files
  • Commit to the methodology without stopping earlyin 24 of 1201, across 8 files

Said here and by no other author read

  • Read shared references before acting
  • Read plan and dev artifacts
  • Write tests covering all acceptance criteria
  • Fix test failures before writing artifacts

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.