Agent Skills
› opensquilla/opensquilla
› text-file-read
text-file-read
GitHub读取UTF-8文本文件并以原始字节形式输出到标准输出。专为需要往返磁盘供用户手动编辑的场景设计，避免内置工具添加行号导致结构化数据损坏。支持限制最大文件大小及处理解码错误。
Trigger Scenarios
需要将文件内容原样传递给下游解析器
用户需要在步骤间手动编辑文件内容
Install
npx skills add opensquilla/opensquilla --skill text-file-read -g -y
SKILL.md
Frontmatter
{
"name": "text-file-read",
"metadata": {
"opensquilla": {
"risk": "low",
"requires": {
"anyBins": [
"python",
"python3"
]
},
"capabilities": [
"filesystem-read"
]
}
},
"entrypoint": {
"args": [
"--input",
"{{ with.input }}",
"--max-bytes",
"{{ with.max_bytes | default(200000) }}"
],
"parse": "text",
"command": "python {baseDir}\/scripts\/read.py",
"timeout": 10
},
"provenance": {
"origin": "opensquilla-original",
"license": "Apache-2.0"
},
"description": "Read a UTF-8 text file and emit its raw content on stdout. Tiny helper for meta-skills that need to round-trip an artefact through disk so the user can hand-edit it between steps (e.g. tweak script.txt during a review pause). Unlike the builtin read_file tool — which returns line-numbered output for model display — this returns bytes verbatim, suitable for downstream parsers."
}
text-file-read
Reads a UTF-8 text file and prints its contents verbatim to stdout (no line numbers, no decoration). Use this when a meta-skill needs to round-trip an artefact through disk between steps so the user can hand-edit the file during a clarify pause.
This skill exists alongside OpenSquilla's builtin read_file tool
on purpose: read_file is designed for LLM display and prepends a
lineno\t prefix to every line, which corrupts structured files
(scripts, SRT, YAML) when piped back into downstream parsers. This
skill returns the bytes unmodified.
Inputs (with:)
| key | required | default | notes |
|---|---|---|---|
input |
yes | — | Absolute path of the file to read. |
max_bytes |
no | 200000 |
Refuse to read files larger than this. Guards against accidental binary reads. |
Output
The file's UTF-8 content on stdout. No trailing newline added or stripped.
Failure modes
- Path missing → exit 1, stderr explains.
- File exceeds
max_bytes→ exit 1, stderr carries the actual size. - Decode error → exit 1 (file isn't valid UTF-8).
Version History
- 7f72a32 Current 2026-07-05 18:40
