Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openakita/grep
Search file contents using regex pattern across directories. Cross-platform pure Python implementation (no external tools needed). Returns matching lines with file paths and line numbers.
Passed 5 of 10 test cases with the skill, and 5 of 10 without it.
and 3 more in the full report
4 fixed6 passed either way8 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
If max_results is omitted in a query, what is the default maximum number of matches returned?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies 50 as the default maximum results value | Missed | Passed |
The instructions your model reads when the skill loads.
跨平台内容搜索工具。
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| pattern | string | 是 | 正则表达式搜索模式 |
| path | string | 否 | 搜索目录（默认当前目录） |
| include | string | 否 | 文件名 glob 过滤（如 "*.py"） |
| context_lines | integer | 否 | 匹配行前后的上下文行数（默认 0） |
| max_results | integer | 否 | 最大返回匹配数（默认 50） |
| case_insensitive | boolean | 否 | 是否忽略大小写（默认 false） |
搜索函数定义:
{
"pattern": "def test_",
"include": "*.py"
}
搜索 TODO 标记（忽略大小写）:
{
"pattern": "TODO|FIXME",
"case_insensitive": true,
"max_results": 20
}
搜索并显示上下文:
{
"pattern": "class.*Error",
"path": "src/",
"context_lines": 3
test cases passed, vs 5 / 10 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.