Run PHPStan static analysis and fix errors using intelligent agent delegation...
This skill provides intelligent PHPStan static analysis and fixing through specialized agent delegation.
This skill delegates to specialized agents via the Task tool:
Launch runner agent:
Use Task tool:
description: "Run PHPStan analysis"
subagent_type: "php-qa-ci_phpstan-runner"
prompt: "Run PHPStan static analysis and provide summary"
Receive runner output with log location
If errors detected:
Use Task tool:
description: "Fix PHPStan errors"
subagent_type: "php-qa-ci_phpstan-fixer"
prompt: "Fix errors in log: {log_path}"
After fixes applied, re-run via runner agent
Repeat cycle until:
Check if recent log exists in var/qa/phpstan_logs/
If log found:
If no log:
Launch opus model or ask human when:
The phpstan-runner agent (haiku model) handles:
See .claude/agents/php-qa-ci_phpstan-runner.md for agent implementation details.
The phpstan-fixer agent (sonnet model) handles:
See .claude/agents/php-qa-ci_phpstan-fixer.md for agent implementation details.