Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From cli-anything-web
Runs full pytest suite (unit, E2E, subprocess) for cli-anything-web CLI at <app-path>, verifies auth, parses results, updates TEST.md, analyzes failures.
npx claudepluginhub itamarzand88/cli-anything-web --plugin cli-anything-webHow this command is triggered — by the user, by Claude, or both
Slash command
/cli-anything-web:test <app-path>Files this command reads when invoked
This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# CLI-Anything-Web: Test Runner
> **Skills used:** `testing` (Phase 3)
Read the methodology overview:
@${CLAUDE_PLUGIN_ROOT}/HARNESS.md
Target: $ARGUMENTS
## Process
This command invokes the `testing` skill for Phase 3.
1. **Verify auth is working FIRST** — this is mandatory before any E2E test:
Auth status MUST show live validation succeeded. If it fails:
- Ensure playwright-cli is available (`npx @playwright/cli@latest --version`)
- Fix auth before running any tests
- Do NOT proceed with "auth not configured" — that is a broken test
2. Locate test directory: `<app>/.../testRuns pytest tests for CLI harness on local path or GitHub repo, verifies CLI resolution, and updates TEST.md with results if all pass.
/flowsTests end-to-end user flows (login, registration, checkout) on web app at <base-url> using Playwright, verifying test plan and app accessibility first.
/testllmExecutes LLM-driven test workflow: reads testing_llm/ specs, catalogs all tests including integrations, builds checklists, validates with evidence, produces verified report.
/testRuns a TDD workflow — write failing tests, implement code, and verify. Also supports a Prove-It pattern for bug fixes.
/testExecutes unit, integration, or e2e tests with coverage analysis, quality metrics, failure diagnostics, and optional watch mode or auto-fixes.
/testGenerates test strategy overview, unit and integration test code, coverage analysis, execution plan, and maintenance roadmap for a specified component or feature.
Share bugs, ideas, or general feedback.
Skills used:
testing(Phase 3)
Read the methodology overview: @${CLAUDE_PLUGIN_ROOT}/HARNESS.md
Target: $ARGUMENTS
This command invokes the testing skill for Phase 3.
Verify auth is working FIRST — this is mandatory before any E2E test:
cli-web-<app> auth login # playwright-cli (recommended)
cli-web-<app> auth login --cookies-json <file> # manual fallback
cli-web-<app> auth status
Auth status MUST show live validation succeeded. If it fails:
npx @playwright/cli@latest --version)Locate test directory: <app>/agent-harness/cli_web/<app>/tests/
Run full test suite:
cd <app>/agent-harness
python -m pytest cli_web/<app>/tests/ -v --tb=short 2>&1
If installed, also run subprocess tests:
CLI_WEB_FORCE_INSTALLED=1 python -m pytest cli_web/<app>/tests/ -v -s -k subprocess 2>&1
After running, verify the subprocess backend was used:
[_resolve_cli] Using installed command: — this confirms
the installed package is being tested, not the source fallbackParse test output: count passed, failed, skipped, errors
Update TEST.md with results in standard format
If failures exist, analyze and suggest fixes
See the testing skill for detailed testing patterns and the
standards skill for quality checks.
# Test Results — cli-web-<app>
## Summary
- **Total**: X tests
- **Passed**: X
- **Failed**: X
- **Date**: YYYY-MM-DD
## Unit Tests (test_core.py)
<list of test results>
## E2E Tests (test_e2e.py)
<list of test results>
## CLI Subprocess Tests
<list of test results>
If any tests fail: