← 返回 Skills 市场
493
总下载
1
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install zentable
功能描述
Render structured table data as high-quality PNG images using Headless Chrome. Use when: need to visualize tabular data for chat interfaces, reports, or soci...
安全使用建议
This package is primarily documentation: it describes Python + Headless Chrome renderers and an OCR service, but it does NOT include the runnable code the docs reference. Before using/installing: 1) review the pinned GitHub release (https://github.com/con2000us/zenTable/releases/tag/skillhub-zentable-beta-2026-03-01) and inspect the exact scripts (skills/zentable/table_renderer.py, scripts/zentable_render.py) that would be executed; 2) do not grant broad exec/read/write privileges to an agent unless you trust the fetched code — prefer manual download and review; 3) run the renderer and any OCR services in an isolated container or VM for initial testing; 4) be cautious of the Zx shorthand which instructs the agent to auto-run rendering without answering follow-up questions — if you install, consider restricting the skill's ability to exec or require explicit user confirmation; 5) verify any local network endpoints (OCR/CSS APIs) before allowing the agent to call them. If you cannot or will not review the referenced release artifacts, avoid enabling exec access or decline to install.
功能分析
Type: OpenClaw Skill
Name: zentable
Version: 0.9.2
The skill bundle is declared as 'text-only' in INSTALL.md and README.md, explicitly instructing the OpenClaw agent to download the actual runnable code from an external GitHub release URL (https://github.com/con2000us/zenTable/releases/tag/skillhub-zentable-beta-2026-03-01). This introduces a significant supply chain vulnerability, as the platform cannot directly review the executable code, and a compromised external source could lead to the execution of arbitrary malicious payloads. Furthermore, SKILL.md requests broad 'exec', 'read', and 'write' permissions, enabling the agent to perform such external downloads and executions.
能力评估
Purpose & Capability
Name/description match the requested binaries (python3 + google-chrome) and the stated rendering approach. However, the skill references local scripts (skills/zentable/table_renderer.py, scripts/zentable_render.py) and a pinned GitHub release as the runnable source, but no runtime code is included in this package. That mismatch (docs expect code that isn't present) is a coherence issue: the installed skill cannot perform the described work without downloading and running external assets.
Instruction Scope
SKILL.md allows exec/read/write and gives explicit command examples that run local Python renderers and mentions OCR-assisted extraction and a Zx shorthand that instructs the agent to 'execute rendering directly by default (no preliminary Q&A)'. Those instructions grant the agent discretion to run local binaries and operate on message images and prior context. Because the actual renderer and OCR backends are not bundled, following these instructions would require fetching and running external code and/or contacting local services — a scope expansion not explicitly declared in the skill's manifest.
Install Mechanism
There is no install spec in the skill bundle (instruction-only), which is lower risk in isolation. But INSTALL.md explicitly instructs users/agents to download a pinned GitHub release and run scripts from it. The absence of an automated/verified install mechanism in the package plus instructions to fetch and execute release assets is a potential operational risk and a point of inconsistency.
Credentials
The skill declares no required environment variables or credentials (appropriate for a renderer). However DEPLOYMENT.md documents .env variables and local OCR backend options for a deploy scenario; those variables are not required by the skill manifest. This is mismatched documentation but not direct credential overreach in the packaged skill.
Persistence & Privilege
The skill does not request always:true and does not declare any system-wide configuration changes. Autonomous invocation is allowed by the platform default; the real issue is the Zx shorthand in the instructions that encourages immediate execution without user confirmation — this is an instruction-level behavior to be mindful of but not a declared persistence/privilege escalation in the manifest.
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 zentable - 安装完成后，直接呼叫该 Skill 的名称或使用
/zentable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
v0.9.2
No functional or documentation changes in this release.
- Version bump to 0.9.2 with no changes detected in source files or documentation.
v0.9.1
- Updated documentation to focus on image-based table rendering and clarify use cases for chat/report/social sharing.
- Expanded details on accepted inputs, output modes, and runtime requirements.
- Added explicit guidelines on when to use or avoid the skill.
- Introduced a comprehensive command, syntax, and payload reference.
- Specified legacy/alias names and explained naming conventions.
- Removed INSTALL.md and PACKAGE_NOTE.txt files; setup and code distribution now require referencing GitHub repository documents.
v0.9.0-beta.4
ZenTable 0.9.0-beta.4 (ClawHub text-only)
- Skill package is now text-only for ClawHub validator compatibility.
- Removes bundled runtime code; directs users to use the pinned GitHub release for execution.
- Documentation and workflow instructions are included; runnable code must be downloaded separately.
- Adds clearer runtime and security notes, emphasizing explicit user confirmation for first use.
- Known limitations updated (ASCII output experimental, Discord-first focus).
- Contact and support details remain unchanged.
v0.9.0-beta.3
- Added INSTALL.md for setup documentation.
- Added PACKAGE_NOTE.txt for package-specific notes.
- No core functionality or usage changes; documentation additions only.
v0.9.0-beta.2
- Repository homepage link updated to https://github.com/con2000us/zenTable.
- Added a TL;DR section summarizing accepted inputs, core capabilities, and use cases.
- Expanded runtime & security section for better clarity and best practice guidance.
- Command examples now reference repository-relative script paths for clarity.
- Minor editorial improvements and reorganization for user understanding; no functional changes to capabilities.
v0.9.0-beta.1
ZenTable 0.9.0-beta.1
- Initial beta release for rendering structured tables as high-quality PNG images using Headless Chrome or PIL fallback.
- Supports command-based customization for themes, page range, width, smart wrapping, sorting, pinning defaults, and more.
- Introduces ASCII text output (experimental), with CSS and PIL backends marked stable.
- Adds "Zx" shorthand policy for direct and efficient rendering workflows.
- Provides normalized command-line interface with detailed option mapping and canonical JSON examples.
- Known limitations and validation steps explicitly documented; ASCII output is platform-sensitive.
元数据
常见问题
zenTable 是什么？
Render structured table data as high-quality PNG images using Headless Chrome. Use when: need to visualize tabular data for chat interfaces, reports, or soci... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 493 次。
如何安装 zenTable？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install zentable」即可一键安装，无需额外配置。
zenTable 是免费的吗？
是的，zenTable 完全免费（开源免费），可自由下载、安装和使用。
zenTable 支持哪些平台？
zenTable 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 zenTable？
由 con2000us（@con2000us）开发并维护，当前版本 v0.9.2。
推荐 Skills