smithery.ai

phpunit-runner

Run PHPUnit tests and fix failures using intelligent agent delegation. Use when user requests to: - Run tests (full suite, specific path, or single file) - Fix failing tests - Analyze test failures - Check test coverage Delegates to runner agent (haiku) for execution and fixer agent (sonnet) for fixes. Automatically cycles between run and fix until tests pass or human intervention needed.

First seen Apr 24, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsTask
Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,752 B
  • docs SUMMARY.md 419 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

PHPUnit Runner Skill

This skill provides intelligent PHPUnit test execution and fixing through specialized agent delegation.

Agent Delegation Strategy

This skill delegates to specialized agents via the Task tool:

  1. php-qa-ci_phpunit-runner agent (haiku model) - Runs tests and parses results
  2. php-qa-ci_phpunit-fixer agent (sonnet model) - Analyzes and fixes errors
  3. Escalation - Uses opus model or asks human for stubborn issues

Workflow

When User Says: "Run tests"

  1. Launch runner agent:

`` Use Task tool: description: "Run PHPUnit test suite" subagenttype: "php-qa-ciphpunit-runner" prompt: "Run PHPUnit tests and provide summary" ``

  1. Receive runner output with log location
  1. If failures detected:

- Launch fixer agent: `` Use Task tool: description: "Fix PHPUnit test failures" subagenttype: "php-qa-ciphpunit-fixer" prompt: "Fix test failures in log: {log_path}" ``

  1. After fixes applied, re-run via runner agent
  1. Repeat cycle until:

- All tests pass → Success - Same errors persist 2+ times → Escalate to opus or human - User intervention needed → Ask user

When User Says: "Fix the test failures"

  1. Check if recent log exists in var/qa/phpunit_logs/
  1. If log found:

- Launch fixer agent directly with log path

  1. If no log:

- Launch runner agent first to generate log - Then launch fixer agent

Escalation Triggers

Launch opus model or ask human when:

  • Fixer agent reports "cannot fix" for same error 2+ times
  • Business logic questions arise (test expectations vs code behavior)
  • User explicitly requests explanation of failures

Runner Agent Reference

The phpunit-runner agent (haiku model) handles:

  • Runtime estimation (refuses full suite if >5min)
  • Test execution with proper CI environment
  • JUnit XML parsing
  • Concise summary generation

See .claude/agents/php-qa-ci_phpunit-runner.md for agent implementation details.

Fixer Agent Reference

The phpunit-fixer agent (sonnet model) handles:

  • Log file discovery and parsing
  • Error grouping by pattern
  • Fix implementation
  • Verification that fixes resolve issues

See .claude/agents/php-qa-ci_phpunit-fixer.md for agent implementation details.