Description

Monitors websites, APIs, and cron jobs (watchdogs) using Watch.dog. Use it when the user asks to "check the status of my monitors", "check uptime", "review w...

README (SKILL.md)

\r \r

Watch.dog Uptime – OpenClaw Skill\r

Name: SeeWeb Uptime
Author: robinson0594

\r

What does this skill do?\r

\r Connects your AI agent with the Watch.dog platform to:\r \r

🔭 Actively monitor websites, APIs, IPs, and ports (HTTP, Keyword, Ping)\r
🫀 Watch scheduled tasks (cron jobs, backups, scripts) through Passive Watchdogs (Heartbeats)\r
📊 Check the status of your infrastructure in real-time\r
- Monitor statuses are interpreted as follows:\r
  - null: Pending\r
  - 0: Down (Offline)\r
  - 1: Up (Online)\r
  - 2: New (New/Created)\r
🗑️ Manage resources (Pause, Resume, Delete)\r
🌐 Public Status Pages (Tracker Pages)\r \r

When to activate this skill\r

\r Use it when the user:\r \r

Wants to create a monitor for a URL, website, API, or server\r
Asks about the status, historical uptime, or availability of their services\r
Needs to configure a watchdog for a scheduled task or cron job\r
Asks for a summary of their monitored infrastructure\r
Wants to pause, resume, or delete monitors or watchdogs from their account\r
Requests to configure their public status page (Tracker Page)\r \r

Required Configuration\r

\r Create a .env file in this folder with:\r \r

WATCHDOG_API_KEY="sk_live_your_key_here"\r
WATCHDOG_API_URL="api_url_here" | "https://api.watch.dog/api/mcp_server.php"\r
```\r
\r
> If you don't have an API Key, create one in your dashboard at [watch.dog](https://watch.dog).\r
\r
### Clarification about Intervals\r
\r
- When creating monitors (`create_monitor`) or watchdogs (`create_watchdog`), if the user specifies a time (e.g. "every 5 minutes"), **always pass the exact value in seconds** (e.g. 300).\r
- Be aware the remote API may auto-correct the interval if the user's plan does not support such high frequencies, so report the returned interval accurately.\r
\r
## Available Tools\r
\r
| Tool                         | Description                                         |\r
| ---------------------------- | --------------------------------------------------- |\r
| `list_monitors`              | Lists all active monitors                           |\r
| `create_monitor`             | Creates an Active Monitor (HTTP, Keyword, Ping)     |\r
| `get_monitor_status`         | Status and recent events of a specific monitor      |\r
| `pause_monitor`              | Temporarily pauses an Active Monitor                |\r
| `resume_monitor`             | Resumes a previously paused Active Monitor          |\r
| `delete_monitor`             | Deletes an Active Monitor (Requires Confirmation)   |\r
| `get_monitor_uptime_history` | Uptime/Availability matrix of a monitor             |\r
| `update_tracker_page`        | Configures the Public Status Page (`/monitors/...`) |\r
| `list_watchdogs`             | Lists all Passive Watchdogs/Heartbeats              |\r
| `create_watchdog`            | Creates a Passive Watchdog for a cron job           |\r
| `get_watchdog_status`        | Health status of the last ping of a watchdog        |\r
| `delete_watchdog`            | Deletes a Passive Watchdog (Requires Confirmation)  |\r
\r
## Installation\r
\r
```bash\r
cd seeweb-uptime\r
npm install\r
```\r

Usage Guidance

What to consider before installing: - This skill will need your Watch.dog API key and API URL to function; although the registry listed no required env vars, the code will fail without WATCHDOG_API_KEY. Provide only a limited-scope key (if Watch.dog supports it) and rotate it when done. - SKILL.md and the embedded system prompt instruct the agent to automatically create/overwrite a .env file in the skill folder with your API key and to immediately run list_monitors as a silent connection test. That means your credential could be written to disk and an automatic network call will occur as soon as you supply it — ask for or require explicit user confirmation before saving/testing credentials. - The prompt forbids showing raw JSON. That reduces transparency about exactly what the remote API returned. If you install, request that the agent also show (or let you request) the raw response for auditing, or run the skill in a sandbox first and inspect network traffic. - The code performs HTTP POSTs to the configured WATCHDOG_API_URL. Verify that the URL is the official Watch.dog endpoint before supplying credentials (attacker-controlled URLs could exfiltrate keys). - The package uses standard npm libraries; review index.js (you have it) and monitor outgoing requests (e.g., with a network proxy) if you have concerns. The code shown uses fetch to send JSON-RPC calls to the configured endpoint — nothing obviously obfuscated, but the instruction to hide raw JSON is a transparency concern. - If you want to proceed: (1) create a dedicated API key with minimal privileges, (2) back up and inspect the .env written by the skill, (3) run the skill in an isolated environment or review network logs during the first credential test, and (4) require the agent to ask for explicit confirmation before saving credentials or performing destructive actions (deletions).

Capability Analysis

Type: OpenClaw Skill Name: seeweb-uptime Version: 1.0.5 The skill is a legitimate integration for the Watch.dog uptime monitoring platform, acting as a bridge between the OpenClaw agent and a remote MCP server (api.watch.dog). The code in index.js and instructions in SKILL.md facilitate service onboarding by directing the AI to manage its own configuration (.env) and verify credentials via a 'silent test' (list_monitors). It includes safety heuristics, such as mandatory user confirmation before deleting resources, and shows no signs of data exfiltration or malicious intent.

Capability Assessment

⚠ Purpose & Capability

The skill's name/description match the implementation (a Node-based MCP bridge to the Watch.dog API). However the package and SKILL.md expect a WATCHDOG_API_KEY and WATCHDOG_API_URL to function (callRemoteTool throws if apiKey is missing), while the registry metadata reported 'Required env vars: none'. That mismatch is an incoherence: the skill will not work without credentials despite registry claiming none.

⚠ Instruction Scope

SKILL.md (and the system prompt embedded in the code) instructs the agent to automatically create/overwrite a .env file with the user's API key and URL, then immediately execute list_monitors as a silent test when credentials are provided or changed. It also mandates 'FORBIDDEN to show raw JSON' which reduces visibility into tool results. These instructions go beyond simple API calls and include file writes and automatic network activity that the user may not expect.

✓ Install Mechanism

No special install spec is embedded (npm install is expected). package.json lists standard npm dependencies (@modelcontextprotocol/sdk, zod). There are no downloads from arbitrary URLs or extract-from-URL steps. Install risk is typical for a Node skill (moderate due to third-party packages), not unusually high.

⚠ Credentials

The runtime requires WATCHDOG_API_KEY and WATCHDOG_API_URL (used for Authorization and endpoint in remote calls). Asking for an API key is proportionate for a monitoring integrator, but the skill metadata declared no required env vars — inconsistent. Also SKILL.md instructs automatic writing of credentials into a .env file in the skill folder, which may be unexpected; the skill does not request any other unrelated secrets.

ℹ Persistence & Privilege

always:false (no forced persistent inclusion). The skill's instructions ask to write/overwrite a .env file in its directory to store credentials; writing its own config is normal but the automatic overwrite instruction (and the requirement to run a silent test immediately) increases the chance of unintended network calls. The code itself reads .env at startup but does not contain explicit file-write logic—this is a behavioral instruction to the agent rather than implemented host-side code, which is an inconsistency to be aware of.

Version History

v1.0.5

- Updated skill version to 1.0.5. - Changed author name from "Watch.dog Team" to "SeeWeb Uptime Team." - No code or functional changes detected; documentation only.

v1.0.4

seeweb-uptime 1.0.4 - Updated documentation to clarify the mapping for monitor status values. - Status codes now interpreted as: null = Pending, 0 = Down, 1 = Up, 2 = New/Created. - No code changes – documentation only.

v1.0.3

- Documentation now in English, with improved clarity and concise instructions. - Status codes for monitors are explicitly documented (0: Down, 1: Up, 2/null: New). - Adds clarification on specifying intervals in seconds for monitor and watchdog creation, and notes about API auto-correction. - Minor updates to branding and author information. - No functional changes to the code; documentation only.

v1.0.2

seeweb-uptime v1.0.2 - Eliminado el requerimiento explícito de las variables de entorno WATCHDOG_API_KEY y WATCHDOG_API_URL en los metadatos de la skill. - No se detectaron otros cambios funcionales o de herramientas.

v1.0.1

seeweb-uptime v1.0.1 - Requiere ahora que WATCHDOG_API_URL esté definida en el entorno, además de WATCHDOG_API_KEY. - Corrige la documentación de instalación: indica crear la carpeta .env en el directorio seeweb-uptime. - Elimina el valor por defecto alternativo y posibles inconsistencias en la configuración del endpoint de la API.

v1.0.0

SeeWeb Uptime 1.0.0 – Primera versión: - Permite monitorear sitios web, APIs, servidores, IPs y tareas programadas usando Watch.dog. - Gestiona monitores (crear, listar, pausar, reanudar, eliminar) y watchdogs pasivos (Heartbeats). - Requiere clave API; verifica automáticamente la conexión al configurar credenciales y notifica al usuario. - Realiza consultas de estado, uptime histórico y permite configurar páginas públicas de estado. - Las eliminaciones requieren confirmación explícita del usuario.

Metadata

Slug seeweb-uptime

Version 1.0.5

License —

All-time Installs 0

Active Installs 0

Total Versions 6

Frequently Asked Questions

What is SeeWeb Uptime?

Monitors websites, APIs, and cron jobs (watchdogs) using Watch.dog. Use it when the user asks to "check the status of my monitors", "check uptime", "review w... It is an AI Agent Skill for Claude Code / OpenClaw, with 406 downloads so far.

How do I install SeeWeb Uptime?

Run "/install seeweb-uptime" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is SeeWeb Uptime free?

Yes, SeeWeb Uptime is completely free (open-source). You can download, install and use it at no cost.

Which platforms does SeeWeb Uptime support?

SeeWeb Uptime is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created SeeWeb Uptime?

It is built and maintained by Robinson (@robinson0594); the current version is v1.0.5.

More Skills

SeeWeb Uptime