← 返回 Skills 市场
Watchboard Intelligence
作者
Artemio Padilla
· GitHub ↗
· v2.0.0
· MIT-0
81
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install watchboard
功能描述
Query Watchboard intelligence dashboards (watchboard.dev) for structured event data, casualties, KPIs, contested claims, and daily digests across 51+ tracker...
安全使用建议
This skill appears to do exactly what it claims: query the public watchboard.dev API and show structured tracker data. Before installing, consider: (1) it makes outbound network requests to watchboard.dev — only install if you trust that remote site; (2) it writes cached JSON to /tmp/watchboard-cache/ (temporary but world-readable on multi-user systems), so cached content could be visible to other local users; (3) there is no integrity/signature check of API responses, so if your environment's DNS or network were compromised you could receive tampered data; (4) the skill has no secrets or privileged access required. If you have concerns, review the scripts/watchboard.py source locally or run the skill in a sandboxed environment (network-restricted or monitored) before granting it broader use.
功能分析
Type: OpenClaw Skill
Name: watchboard
Version: 2.0.0
The watchboard skill is a legitimate tool for querying intelligence dashboards from watchboard.dev. The Python script (scripts/watchboard.py) uses only standard libraries (urllib, json) to fetch data from a public API, implements safe local caching in /tmp/watchboard-cache, and contains no evidence of data exfiltration, malicious execution, or prompt injection. The SKILL.md instructions are clearly aligned with the stated purpose of providing structured event data and summaries.
能力评估
Purpose & Capability
Name/description (Watchboard intelligence dashboards) match the code and SKILL.md: the code fetches JSON endpoints from https://watchboard.dev/api/v1, exposes commands for listing trackers, summaries, events, KPIs, breaking items, search, and RSS. No unrelated services, credentials, or binaries are requested.
Instruction Scope
SKILL.md instructions are specific and map directly to the CLI in scripts/watchboard.py. The instructions tell the agent to call the public API and optionally use RSS as a fallback. The runtime code only reads/writes local cache files (/tmp/watchboard-cache/) and performs network requests to the declared BASE_URL; it does not attempt to read other system files or environment variables.
Install Mechanism
No install spec is provided (instruction-only + a python script). The code uses only Python stdlib (urllib, json, xml.etree) and requires Python 3.8+, which is consistent with the SKILL.md claim of zero dependencies.
Credentials
The skill declares no required environment variables, no credentials, and requests no config paths. The code does not read credentials from env or disk beyond its local cache directory, so requested access is proportional to purpose.
Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The only persistent action is writing cached HTTP responses to /tmp/watchboard-cache/ with a 1h TTL; it does not modify other skills or system-wide configuration.
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 watchboard - 安装完成后，直接呼叫该 Skill 的名称或使用
/watchboard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
v2.0.0
Rewritten for API v1. Dynamic tracker list, 8 commands, zero deps.
元数据
常见问题
Watchboard Intelligence 是什么？
Query Watchboard intelligence dashboards (watchboard.dev) for structured event data, casualties, KPIs, contested claims, and daily digests across 51+ tracker... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 81 次。
如何安装 Watchboard Intelligence？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install watchboard」即可一键安装，无需额外配置。
Watchboard Intelligence 是免费的吗？
是的，Watchboard Intelligence 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Watchboard Intelligence 支持哪些平台？
Watchboard Intelligence 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 Watchboard Intelligence？
由 Artemio Padilla（@artemiopadilla）开发并维护，当前版本 v2.0.0。
推荐 Skills