← 返回 Skills 市场
Reader
作者
ProjectSnowWork
· GitHub ↗
· v1.0.0
· MIT-0
388
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install reader
功能描述
Local-first reading and distillation engine for documents and pasted text. Use whenever the user wants to read, summarize, extract key points, compare docume...
安全使用建议
This skill appears coherent and local-only: it reads files or pasted text, summarizes/extracts/compares, and logs sessions to ~/.openclaw/workspace/memory/reader/history.json. Before installing, consider whether you want processed text or file paths retained there — the history can contain sensitive material. If you prefer not to retain data, inspect or delete that file (or modify the scripts to disable logging) after running init_storage.py. Verify python3 is available and, if you want extra caution, run the scripts in a restricted environment (container or VM) and review the source files yourself. There is no networking, no credential requests, and no external dependencies in the provided code.
功能分析
Type: OpenClaw Skill
Name: reader
Version: 1.0.0
The 'reader' skill is a local-first document analysis tool that performs text normalization, summarization, and comparison. The code (scripts/lib/text_utils.py and scripts/lib/storage.py) uses standard Python libraries for file I/O and regex-based processing without any network calls, external dependencies, or suspicious execution patterns. All data is stored locally in a dedicated workspace directory as described in SKILL.md.
能力评估
Purpose & Capability
Name/description (local-first reading, summarization, comparison) aligns with the provided Python scripts. All files implement text loading, splitting, summarization, extraction, comparison and local session logging — nothing unrelated is requested.
Instruction Scope
SKILL.md and scripts limit operations to reading local files or direct text input and writing session metadata. No networking, external APIs, or environment-variable access are present. Note: the skill records sessions (file paths and operation types) and does store text-derived outputs in a local history file, which may retain sensitive content.
Install Mechanism
No install spec; instruction-only with included Python scripts. Requires only a local python3 binary and no external packages. No downloads or third-party installers are used.
Credentials
The skill requests no credentials or env vars (proportional). It does create and update ~/.openclaw/workspace/memory/reader/history.json to record sessions and metadata — this is reasonable for a local reader but means processed inputs (or references to file paths) are persisted locally.
Persistence & Privilege
always is false; the skill only writes to its own directory under the user's home. It does not modify other skills, system settings, or request elevated privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install reader - 安装完成后，直接呼叫该 Skill 的名称或使用
/reader触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
[email protected]: Read less. Understand more. Launched as a local-first reading and distillation engine for summarizing text, extracting key points, pulling action items, and comparing documents without external sync or credentials.
元数据
常见问题
Reader 是什么？
Local-first reading and distillation engine for documents and pasted text. Use whenever the user wants to read, summarize, extract key points, compare docume... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 388 次。
如何安装 Reader？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install reader」即可一键安装，无需额外配置。
Reader 是免费的吗？
是的，Reader 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Reader 支持哪些平台？
Reader 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Reader？
由 ProjectSnowWork（@projectsnowwork）开发并维护，当前版本 v1.0.0。
推荐 Skills