From hotl
Enforces running test suites, linters, and behavior checks before claiming code is complete, fixed, or passing. Shows outputs to confirm success and prevent regressions.
npx claudepluginhub yimwoo/hotl-plugin --plugin hotlThis skill uses the workspace's default tool permissions.
Never claim "done", "fixed", or "passing" without running verification commands and showing the output.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
Never claim "done", "fixed", or "passing" without running verification commands and showing the output.
Evidence before assertions. Always.
Before claiming complete:
Tests: pytest output (N passed, 0 failed)
Lint: ruff/eslint output (clean)
Behavior: [description of manual or automated check]
If anything fails: report it honestly. Do not claim partial success as full success.