Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/gemini
Global behavior rules for the workspace.
Passed 14 of 19 test cases with the skill, and 10 of 19 without it.
and 2 more in the full report
5 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Should I run `export GEMINI_API_KEY=...` in a separate command line before calling `gemini`, or can I prepend the extracted key inline to the `gemini` command?
| Checked | Without skill | With skill |
|---|---|---|
| Prefixes key assignment `GEMINI_API_KEY=$(grep '^GEMINI_API_KEY=' .env 2>/dev/null | cut -d= -f2-)` inline before `gemini`. | Missed | Passed |
The instructions your model reads when the skill loads.
Use Gemini CLI in one-shot mode with a positional prompt.
Core usage
gemini "Answer this question..."gemini --model <name> "Prompt..."gemini --output-format json "Return JSON"Extensions
gemini --list-extensionsgemini extensions <command>Auth and safety notes
gemini once interactively and complete login.--yolo mode for safety-sensitive workflows.test cases passed, vs 10 / 19 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.