parallel-monitor

작성자: parallel-web

Continuously track the web for changes on a recurring cadence. Use when the user asks to 'monitor', 'track changes to', 'watch', or 'alert me when' something…

npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-monitor

Web Monitor

Action: $ARGUMENTS

Requires parallel-cli ≥ 0.3.0 (the monitor command was added in 0.3.0). If parallel-cli monitor errors with no such command or similar, tell the user to run parallel-cli update (or pipx upgrade parallel-web-tools if installed via pipx), then retry.

What this skill does

Monitors are long-running, server-side jobs that re-check the web on a cadence and emit events when something changes. Unlike search/research/findall (one-shot lookups), monitors persist until deleted and can optionally fire a webhook on each event.

Decide the action

Parse the user's request and pick one:

IntentAction
"Track / watch / monitor / alert me when X"create
"What am I monitoring?" / "List monitors"list
"What changed?" / "Show me events for monitor X"events
"Show monitor X" / "Get details for X"get
"Change cadence / query / webhook for X"update
"Test the webhook" / "Fire a test event"simulate (requires a webhook on the monitor)
"Show me the full payload for event group X"event-group
"Stop / delete monitor X"delete (always confirm before deleting)

Create a monitor

parallel-cli monitor create "<query>" --cadence daily --json

Cadence options: hourly, daily (default), weekly, every_two_weeks. Match cadence to how often the source actually changes — hourly for prices/news, weekly for filings/staffing.

Optional flags:

  • --webhook https://example.com/hook — POST events to a URL as they happen
  • --metadata '{"team":"competitive-intel"}' — attach JSON metadata for your own bookkeeping
  • --output-schema '<json>' — structure the event payload (advanced)

Parse the JSON to extract the monitor_id. Tell the user:

  • The monitor has been created with its ID
  • The cadence (so they know when to expect first event)
  • That events accumulate server-side — they can run parallel-cli monitor events $MONITOR_ID later to see what changed

If they configured a webhook, suggest testing it:

parallel-cli monitor simulate "$MONITOR_ID"

simulate requires a webhook to be configured on the monitor. Without one it errors with Webhook not configured for this monitor — do not run it on monitors created without --webhook.

List monitors

parallel-cli monitor list -n 10 --json

Default to -n 10 — accounts with many historical monitors can return megabytes of JSON otherwise. Raise the limit only if the user explicitly asks for "all" or a larger set. Present as a table: ID, query (truncated), cadence, created.

Note: monitor list is not guaranteed to be sorted newest-first, so a monitor you just created may not appear in the first page of results. If a user is verifying creation, prefer monitor get $MONITOR_ID (using the ID returned by create) over scanning the list.

View events for a monitor

parallel-cli monitor events "$MONITOR_ID" --lookback 10d --json

Lookback format: Nd (days) or Nw (weeks). Default 10d.

For deeper detail on a specific event group:

parallel-cli monitor event-group "$MONITOR_ID" "$EVENT_GROUP_ID" --json

Summarize for the user: count of events in the period, then a bulleted list of what changed with timestamps. Cite source URLs from the event payload.

Get / update / delete

parallel-cli monitor get "$MONITOR_ID" --json
parallel-cli monitor update "$MONITOR_ID" --cadence weekly --json
parallel-cli monitor delete "$MONITOR_ID" --json

Always confirm before deleting — deletion is permanent.

Setup

Requires parallel-cli (installed and authenticated). If parallel-cli --version fails, or if a later command fails with an authentication error, tell the user to see https://docs.parallel.ai/integrations/cli and stop.

parallel-web의 다른 스킬

parallel-cli-setup
parallel-web
Set up and maintain the Parallel CLI (install, auth, balance, skills install)
official
parallel-data-enrichment
parallel-web
회사, 인물 또는 제품 데이터를 CEO 이름, 자금 정보, 연락처 정보 등 웹에서 수집한 필드로 대량 보강합니다. 인라인 JSON 데이터 또는 CSV 파일을 입력받아 보강된 결과를 CSV로 출력합니다. 모니터링 URL 및 폴링 명령어를 통한 진행 상황 추적과 함께 비동기적으로 실행됩니다. parallel-cli 도구와 인터넷 접속이 필요하며, 구성 가능한 타임아웃으로 대규모 데이터셋을 처리합니다. 자연어 의도 설명(예: "CEO 이름 및 설립 연도")을 통해 유연한 필드 요청을 지원합니다.
official
parallel-deep-research
parallel-web
복잡한 주제에 대해 구성 가능한 깊이, 지연 시간, 비용 트레이드오프를 제공하는 철저한 연구. 30초에서 25분까지의 세 가지 프로세서 계층(pro-fast, ultra-fast, ultra)과 1배에서 3배까지의 기본 비용 스케일링. 폴링을 통한 비동기 실행: 연구를 즉시 시작하고, URL을 통해 진행 상황을 모니터링하며, 준비 완료 시 차단 없이 결과를 검색. 출력은 포맷된 마크다운 보고서와 JSON 메타데이터로 제공되며, 빠른 개요를 위해 실행 요약이 stdout에 출력됨. 명시적...
official
parallel-findall
parallel-web
자연어 설명과 일치하는 엔터티(회사, 인물, 제품 등)를 발견합니다. 사용자가 '모든 X를 찾아줘' 또는 '…하는 모든 Y를 나열해줘'라고 요청할 때 사용하세요.
official
parallel-web-extract
parallel-web
Extract content from multiple URLs in parallel, token-efficiently. Handles webpages, articles, PDFs, and JavaScript-heavy sites with a single command Runs in a forked context to minimize token overhead compared to built-in WebFetch Supports batch extraction of multiple URLs with optional focus objectives Requires parallel-cli installation and authentication; outputs extracted content as markdown to a local file for follow-up queries
official
parallel-web-search
parallel-web
인터넷 전반에 걸쳐 최신 정보, 연구, 사실 확인을 위한 빠른 웹 검색. 단일 목표 기반 쿼리 또는 여러 키워드 검색을 병렬로 실행하여 최대 10개의 결과를 발췌문 및 메타데이터와 함께 반환합니다. --after-date를 통한 시간 기반 필터링과 --include-domains를 통한 도메인별 검색을 지원합니다. 제목, URL, 게시 날짜, 발췌문이 포함된 구조화된 JSON을 출력하여 쉽게 구문 분석하고 후속 쿼리를 수행할 수 있습니다. 모든 주장에 대해 마크다운을 사용한 인라인 인용이 필요합니다...
official
result
parallel-web
실행 ID로 완료된 연구 작업 결과를 가져옵니다.
official
setup
parallel-web
Set up the Parallel plugin (install CLI)
official