Monitoring the web
Agent Skills for using Scout: web research, sourced answers, company enrichment, structured extraction, monitoring. Works in Claude Code, Claude.ai, the Agent SDK, and Vercel eve.
npx -y skills add Scout-AI-Labs/scout-skills --skill monitoring-the-webAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Watch the web for changes with Scout monitors. Use when the user wants to be notified of new results for a query on a schedule, track a competitor or topic over time, or set up a recurring search that posts to a webhook. Creates and manages scheduled searches that deliver only what's new.
SKILL.md
1.5 KB, 348 tokens by cl100k_base, as published. Nobody here has run it
Monitoring the web
A monitor is a saved search that runs on a cadence and reports new results to a webhook. Use it for competitor tracking, topic alerts, or any "tell me when something changes" request.
Create a monitor
curl -s https://core.usescout.sh/v1/monitors \
-H "Authorization: Bearer $SCOUT_API_KEY" -H "Content-Type: application/json" \
-d '{
"query": "acme corp pricing change",
"cadence": "daily",
"webhook": "https://your-app.com/hooks/scout",
"filter_prompt": "only new pricing or packaging changes"
}'
cadence takes a simple interval, or pass a cron expression for precise timing. filter_prompt (optional) tells the monitor what counts as a meaningful change so you aren't paged on noise.
Manage them
- List:
GET /v1/monitors - Inspect:
GET /v1/monitors/{id}, events atGET /v1/monitors/{id}/events - Pause / resume:
POST /v1/monitors/{id}/pause·/resume - Run now:
POST /v1/monitors/{id}/run - Update or delete:
PATCH/DELETE /v1/monitors/{id}
Notes
- Point the webhook at an endpoint you control; the monitor POSTs new results there as they appear.
- Start with a tight query and a
filter_prompt. Broad monitors generate noise, and noise gets muted.
Gives 0 of the 12 instructions most monitoring observability skills give in 348 tokens
Counted across 481 of the 483 authors here whose files we hold, read 2026-08-06
- link every alert to a runbookin 43 of 481, across 35 files
- use structured json loggingin 36 of 481, across 31 files
- alert on user-facing symptomsin 20 of 481, across 15 files
- emit structured JSON logs with stable event namesin 18 of 481, across 13 files
- propagate trace context across boundariesin 16 of 481
- use histograms for latency trackingin 14 of 481, across 9 files
- use OpenTelemetry for distributed tracingin 13 of 481, across 8 files
- include a correlation ID on every log linein 13 of 481, across 8 files
- Define service level objectivesin 10 of 481, across 7 files
- Call useAzureMonitor before importing other modulesin 9 of 481, across 2 files
- stop and ask for clarification if inputs are missingin 9 of 481, across 2 files
- define on-call questions before adding telemetryin 9 of 481, across 4 files
Said here and by no other author read
- create a monitor via the monitors API
- point the webhook at a controlled endpoint
- start with a tight query
- use a filter prompt to define meaningful changes
- pass a cron expression for precise timing
- list monitors via the monitors endpoint
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.