Stats
Actions
Tags
From testbench
Runs tests for full suite, changed files only, or specific file. Parses output into failure reports with source context. Supports watch mode and coverage reporting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/testbench:runThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run tests and parse the output into actionable failure reports with source context. Supports full suite, changed-files-only, and single-file modes.
Run tests and parse the output into actionable failure reports with source context. Supports full suite, changed-files-only, and single-file modes.
Load each step through the fetch command (handles caching, decryption, and auth):
"~/.composure/bin/composure-fetch.mjs" skill testbench run {step-filename}
Do NOT read cache files directly — they are encrypted at rest. Always use the fetch command above.
| # | File |
|---|---|
| 1 | 01-load-config.md |
| 2 | 02-determine-scope.md |
| 3 | 03-execute.md |
| 4 | 04-parse-output.md |
| 5 | 05-report-and-store.md |
| 6 | 06-coverage.md |
npx claudepluginhub hrconsultnj/claude-plugins --plugin testbenchExecutes tests across stacks, diagnoses failures, auto-fixes simple issues, and generates coverage reports.
Scouts test coverage gaps, creates test files, continues incomplete suites, tracks persistent coverage using project test config and git analysis.
Parses JUnit XML, Jest JSON, pytest results, and coverage data to generate Markdown/HTML test reports with metrics, failures, slowest tests, and CI annotations.