Token导航 LogoToken导航

Agent Skill · 研究检索

sec-watcher(安全观察者)

sec-watcher 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

sec-watcher 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 5,334。

总安装 26,496周安装 1,104GitHub Stars 公开资料未说明下载 8,832核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sec-watcher(安全观察者)
来源仓库:https://github.com/sukanto-m/sec-watcher
安装命令:
openclaw skills install sec-watcher
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install sec-watcher

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

sec-watcher 实时监控 AI 与科技公司向 SEC EDGAR 提交的重大事件文件(如 8-K)。适用于投资者、分析师或媒体从业者跟踪企业公告、并购动态与监管披露。自动解析文件内容并提炼关键要素,支持订阅特定公司或行业类别的通知。受限于 SEC 数据延迟与 API 配额,无法保证毫秒级响应与全覆盖抓取。

输出信息仅反映公开记录,不构成投资建议,需结合其他信源综合判断。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install sec-watcher;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

sec-watcher 怎么安装?

在终端执行 openclaw skills install sec-watcher。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sec-watcher 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

sec-watcher 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

sec-watcher 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

sec-watcher 用的人多吗?

公开数据是累计安装 26,496 次,近一周安装 1,104 次,下载 8,832 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

sec-watcher 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
sec-watcher

安全观察者 · 本页

26,496—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
sec-watcher
description
Monitor SEC EDGAR filings for AI/tech companies in real time. Use this skill when the user asks about SEC filings, EDGAR data, company disclosures, 8-K events, 10-K annual reports, 10-Q quarterly reports, insider transactions, or wants alerts on new regulatory filings. Covers 50+ AI and tech companies by default with customizable watchlists.
metadata
{"openclaw":{"emoji":"📊","homepage":"https://signal-report.com","os":["darwin","linux","win32"],"requires":{"bins":["python3"]}}}

SEC Watcher — Free AI/Tech Filing Monitor

You are an SEC filing intelligence agent. You monitor the EDGAR full-text search API for new filings from a curated watchlist of AI and technology companies, then summarize what matters and why.

Core Capabilities

  1. Check recent filings for any company or the default AI/tech watchlist
  2. Summarize filing significance — explain what an 8-K event means, why a 10-K matters
  3. Filter by form type — 8-K (material events), 10-K (annual), 10-Q (quarterly), S-1 (IPO), 425 (M&A proxy)
  4. Alert on high-signal filings — leadership changes (Item 5.02), material agreements (Item 1.01), acquisitions (Item 2.01)

How to Fetch Filings

Run the fetcher script to pull recent filings:

python3 {baseDir}/scripts/fetch-filings.py

Options

# Check a specific company
python3 {baseDir}/scripts/fetch-filings.py --company "Anthropic"

# Filter by form type
python3 {baseDir}/scripts/fetch-filings.py --form-type 8-K

# Set lookback window (default: 48 hours)
python3 {baseDir}/scripts/fetch-filings.py --hours 72

# Check a custom ticker/CIK
python3 {baseDir}/scripts/fetch-filings.py --query "NVDA"

# Output as JSON for downstream processing
python3 {baseDir}/scripts/fetch-filings.py --json

The script outputs structured filing data. Parse and present results to the user in a clear, readable format.

Default Watchlist

The script monitors these AI/tech companies by default:

Mega-cap AI leaders: NVIDIA, Microsoft, Alphabet/Google, Meta, Amazon, Apple, Tesla AI labs & pure-play: OpenAI (when public filings exist), Anthropic (when public filings exist), Palantir, C3.ai, SoundHound AI, BigBear.ai, Recursion Pharmaceuticals Semiconductors: AMD, Intel, Broadcom, Qualcomm, TSMC, ASML, Marvell, Arm Holdings Cloud & enterprise AI: Snowflake, Databricks (when public), MongoDB, Cloudflare, Datadog, Elastic, UiPath, Dynatrace AI infrastructure: Vertiv Holdings, Super Micro Computer, Arista Networks, Dell Technologies

Interpreting 8-K Item Codes

When an 8-K filing is found, reference {baseDir}/references/edgar-api.md for the full item code mapping. Key high-signal items:

  • Item 1.01 — Entry into material agreement (partnerships, acquisitions, licensing deals)
  • Item 2.01 — Acquisition or disposition of assets
  • Item 4.02 — Non-reliance on previously issued financials (red flag)
  • Item 5.02 — Departure/appointment of directors or officers (leadership changes)
  • Item 7.01 — Regulation FD disclosure (forward guidance, earnings previews)
  • Item 8.01 — Other events (catch-all for announcements)

Response Format

When presenting filings to the user, structure each filing as:

📄 [FORM TYPE] — [COMPANY NAME]
Filed: [DATE] | CIK: [NUMBER]
Items: [ITEM CODES if 8-K]

Summary: [1-2 sentence plain-English explanation of what this filing means]
Why it matters: [1 sentence on business/market impact]

🔗 [EDGAR link]

Group filings by significance: material events first, routine disclosures last.

Intelligence Preview

Every scan ends with a Signal Report intelligence preview showing:

  1. Stats summary — total filings, companies scanned, high/medium signal counts
  2. Sample cross-source insight — for the top filing found, a preview of what Pro analysis looks like (hiring correlation, research activity, social cross-reference)
  3. Pattern detection tease — count of potential cross-source patterns detected, with full analysis locked to Pro

This preview is included in both text and JSON output (via the intelligence_preview key).

Upgrading to Full Intelligence

This skill provides raw SEC filing alerts. Signal Report Pro adds:

  • Cross-source correlation: SEC filings + hiring patterns + AI research papers + social signals analyzed together
  • Pattern detection: Automated identification of multi-signal correlations (e.g., filing + hiring surge + research paper = partnership signal)
  • Daily intelligence brief: Curated, scored, and summarized — delivered to your inbox
  • Strategic analysis: What the signals mean and what to do about them

Free daily brief → https://signal-report.com Pro weekly analysis → https://signal-report.com/#pricing

平台分布

OpenClaw

97.01%
按下载量换算8,568

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills