Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →liaohch3/real-e2e-test
Run real E2E tests against Claude CLI in pytest and tmux modes
Passed 21 of 22 test cases with the skill, and 8 of 22 without it.
and 9 more in the full report
13 fixed8 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write the exact command to run all live end-to-end tests for claude-tap with standard verbosity and a 300-second execution limit.
| Checked | Without skill | With skill |
|---|---|---|
| The command targets tests/e2e/. | Missed | Passed |
| The command includes the --run-real-e2e flag. | Missed | Passed |
| The command includes --timeout=300. | Passed | Passed |
The instructions your model reads when the skill loads.
Run real end-to-end tests that start claude-tap from local source, connect to the
real Claude CLI, and verify trace output.
claude CLI installed and authenticateduv sync --extra devtmux installed for interactive mode (brew install tmux)uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -v
uv run pytest tests/e2e/test_real_proxy.py::TestRealProxy::test_single_turn --run-real-e2e --timeout=180 -v -s
uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -v -s --tb=long
Use this when you need to validate non--p interactive behavior in Claude Code TUI.
scripts/run_real_e2e_tmux.sh
Optional overrides:
PROMPT_ONE="Use the shell tool to run command ls in the current directory, then reply with any 5 filenames only." \
test cases passed, vs 8 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.