capitalthought

Multipov Tests — Testing skill for Claude Code

Testing community

Run a multi-agent test-focused review on $ARGUMENTS (default: test files touched in the current branch) via the multipov.ai MCP server.

How to install Multipov Tests

Installs to ~/.claude/skills/capitalthought-multipov-docs-multipov-tests/SKILL.md

Terminal

mkdir -p ~/.claude/skills/capitalthought-multipov-docs-multipov-tests && curl -fsSL https://raw.githubusercontent.com/capitalthought/multipov-docs/HEAD/skills/multipov-tests.md -o ~/.claude/skills/capitalthought-multipov-docs-multipov-tests/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Multipov Tests does

Run a multi-agent **test-focused** review on `$ARGUMENTS` (default: test files touched in the current branch) via the multipov.ai MCP server.

This is the **test-quality** sibling of `/multipov-code`. Use it to pressure-test your tests — not the production code. It answers: are there untested paths? Do the tests actually assert behavior? Are edge cases covered? Is mocking masking bugs? Are integration tests hitting real systems? Is coverage lopsided (1000 lines of happy-path, 10 lines of error-h

Alternatives in Testing

Deliver — Delivery phase - Review, validate, and test with multi-AI quality assurance 2.8k ★
Mda — MDA Open Spec — a Markdown superset for agent-facing documents 615 ★
Grid Tester — Use the @grid-tester agent for test strategy, TDD, or flaky test diagnosis: $ARGUMENTS 523 ★