用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/zeenie-ai/OpenCompany --skill file-read-skill命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | file-read-skill |
| description | Read raw file contents with line-based pagination support. |
| allowed-tools | file_read |
| metadata | {"author":"opencompany","version":"1.0","category":"filesystem"} |
Read raw file contents with line-based pagination. Uses the workspace-contained native filesystem backend.
Path sandbox: all paths resolve inside the per-workflow workspace root. Use workspace-relative paths (e.g. reports/data.csv); .. and ~ segments are rejected, and absolute paths are remapped into the workspace. Use fs_search with mode: "ls" to discover what exists.
| Field | Type | Required | Description |
|---|---|---|---|
| file_path | string | Yes | Path to the file to read |
| offset | int | No | Line number to start from, 0-indexed (default: 0) |
| limit | int | No | Maximum lines to read (default: 2000, max: 10000) |
Read a file:
{"file_path": "/path/to/file.py"}
Read with pagination:
{"file_path": "/path/to/large_file.py", "offset": 100, "limit": 50}
{
"content": "line one\nline two\n...",
"line_count": 2,
"file_path": "/path/to/file.py"
}
content is the selected text slice, without added line numbers; text line
endings are normalized to LFline_count counts the lines in the returned slice, not the whole filefile_path is the normalized virtual path inside the workflow workspacecontent; the tool result
does not include a separate encoding field, and line pagination is not
applied to that base64 representation基于 SOC 职业分类