Tasks

Skill 5 of 6

Tavily Monitor

Build a Tavily search or extraction that runs on a cadence, with a saved baseline.

3 minutes · 584 words · 4 sections

Install

$ npx skills add tavily-ai/skills --skill tavily-monitor

$ npx skills add tavily-ai/skills

» /plugin marketplace add tavily-ai/skills

The first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.

Turn a watch into a search or an extraction that can run again unchanged, then run it once and save the baseline. The monitor file is the result.

Use tavily-search to run the check. If it isn’t installed, run npx skills add tavily-ai/skills --skill tavily-search and read its SKILL.md before continuing.

When this is the wrong skill

The user wants a deep comprehensive report. Use tavily-research. If it isn’t installed, run npx skills add tavily-ai/skills --skill tavily-research and read its SKILL.md before continuing.
The user wants every current match, once. Use tavily-list. If it isn’t installed, run npx skills add tavily-ai/skills --skill tavily-list and read its SKILL.md before continuing.

Pick the kind

You have	Kind	What “changed” means
A topic, and the pages are not known yet	search	A result URL that was not in the previous snapshot
One or more known URLs	extract	The hash of that page’s extracted content changed

Use search for mentions, news, jobs, and anything where new pages appear. Use extract for a pricing page, a changelog, a docs page, or a status page.

Steps

Write the query or the URL list so the next run can reuse it verbatim. Follow tavily-search for how to shape it. Leave dates and “latest” out of the query. The snapshot, not the wording, decides what is new.
Write the change rule in one sentence. For a search, a new URL is the alert. A URL from the last snapshot that is missing this run is not an alert: a page that could not be fetched live is left out. For an extract, a changed hash is the alert, and the alert quotes the part the user cares about (the price, the version), not the whole page.
Name a cadence. Use the one the user asked for. If they did not, use daily for news and changelogs, and weekly for a page that changes slowly, and say which you chose. On a search, set max_age_hours to that interval in hours, so a cached copy older than the cadence is not returned. Daily is 24, weekly is 168. Use 0 when the interval is under an hour, and 720 when it is longer than 30 days. Read how the parameter works in the search reference of tavily-search. Write the number in the monitor file and send it on every run, including the first. Extract does not take max_age_hours.
Run it once. If the results are the wrong kind of thing, fix the query or the URLs and run again before you save anything. If the search is refused with 434, the run did not complete. Say so, and leave snapshot.json as it was.
Save the monitor and the snapshot. The next run reads the monitor, runs the same search or extract, reports only what the change rule flags, and replaces snapshot.json.

Create monitors/{name}/ in the working directory. The name is sentence case, 3 to 6 words, letters, numbers, and single spaces. Quote it in shell commands.

Do not start a scheduler unless the user asks for one. When they do, and the environment has a way to run on that cadence, point it at this folder.

A later change to the query or the URL list is a new monitor. It gets a new folder and a new baseline. Editing them in place makes the next diff meaningless.

Output

monitors/{name}/monitor.md:

# {Name}

- Cadence: {daily | weekly on Monday | the schedule the user asked for}
- Kind: search | extract
- Query: {the query, for a search}
- URLs: {one per line, for an extract}
- max_age_hours: {the cadence in hours, search only}
- Alert when: {the change rule}
- Snapshot: snapshot.json

## Run again

Read this file. Use `tavily-search` to run the same search or extract. On a
search, pass `max_age_hours` from this file. Compare the result to
snapshot.json using the alert rule above. Report only the changes. Then
replace snapshot.json with this run. If the search is refused with `434`,
report that and keep the snapshot.

monitors/{name}/snapshot.json:

{
  "ran_at": "YYYY-MM-DD",
  "kind": "search",
  "query": "",
  "items": [{ "url": "", "title": "", "snippet": "" }]
}

For an extract, store pages instead of items: url, sha256 of the extracted content, and a short excerpt of the part being watched.

In the reply, give the cadence, max_age_hours for a search, the query or the URLs, the alert rule, and the folder path, plus what the baseline already shows.

About this skill

Trigger

Build a Tavily search or extraction that runs on a cadence, with a saved baseline. Search monitors set max_age_hours to the interval so a cached copy from before it is not returned. Use when the user wants to monitor, track, watch, or be alerted when something changes, or asks for a recurring check of a query or a page. For a deep comprehensive report use tavily-research. For a one-time lookup use tavily-search. For a one-time table use tavily-list.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Allowed tools: Bash(tvly*)
Source: skills/tasks/tavily-monitor/SKILL.md

Colophon for this issue

Colophon

How this issue was made

Source

github.com/tavily-ai/skills, branch main, last pushed 6 November 2026.

Licence

MIT — the text of every skill is reproduced unmodified, frontmatter included, under the upstream licence.

Discovery

6 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. 3 distinct layouts observed: skills/core/*/SKILL.md, skills/developers/*/SKILL.md, skills/tasks/*/SKILL.md.

Issue colours

Resolved from a deterministic hash of the owner name. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this skill so the document has one h1 and no skipped levels:

Removed “Tavily monitor”, a leading h1 that duplicated the skill title.

Spec compliance

Every skill satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Marketplace

A plugin manifest is published at .claude-plugin/marketplace.json by Tavily, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /tavily-ai/skills.md, and each skill at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

When this is the wrong skill

The user wants a deep comprehensive report. Use tavily-research. If it isn’t installed, run npx skills add tavily-ai/skills --skill tavily-research and read its SKILL.md before continuing.

The user wants every current match, once. Use tavily-list. If it isn’t installed, run npx skills add tavily-ai/skills --skill tavily-list and read its SKILL.md before continuing.

Pick the kind

You have	Kind	What “changed” means
A topic, and the pages are not known yet	search	A result URL that was not in the previous snapshot
One or more known URLs	extract	The hash of that page’s extracted content changed

Use search for mentions, news, jobs, and anything where new pages appear. Use extract for a pricing page, a changelog, a docs page, or a status page.

Steps

Write the query or the URL list so the next run can reuse it verbatim. Follow tavily-search for how to shape it. Leave dates and “latest” out of the query. The snapshot, not the wording, decides what is new.

Write the change rule in one sentence. For a search, a new URL is the alert. A URL from the last snapshot that is missing this run is not an alert: a page that could not be fetched live is left out. For an extract, a changed hash is the alert, and the alert quotes the part the user cares about (the price, the version), not the whole page.

Name a cadence. Use the one the user asked for. If they did not, use daily for news and changelogs, and weekly for a page that changes slowly, and say which you chose. On a search, set max_age_hours to that interval in hours, so a cached copy older than the cadence is not returned. Daily is 24, weekly is 168. Use 0 when the interval is under an hour, and 720 when it is longer than 30 days. Read how the parameter works in the search reference of tavily-search. Write the number in the monitor file and send it on every run, including the first. Extract does not take max_age_hours.

Run it once. If the results are the wrong kind of thing, fix the query or the URLs and run again before you save anything. If the search is refused with 434, the run did not complete. Say so, and leave snapshot.json as it was.

Save the monitor and the snapshot. The next run reads the monitor, runs the same search or extract, reports only what the change rule flags, and replaces snapshot.json.

Create monitors/{name}/ in the working directory. The name is sentence case, 3 to 6 words, letters, numbers, and single spaces. Quote it in shell commands.

Do not start a scheduler unless the user asks for one. When they do, and the environment has a way to run on that cadence, point it at this folder.

A later change to the query or the URL list is a new monitor. It gets a new folder and a new baseline. Editing them in place makes the next diff meaningless.

Output

monitors/{name}/monitor.md:

# {Name}

- Cadence: {daily | weekly on Monday | the schedule the user asked for}
- Kind: search | extract
- Query: {the query, for a search}
- URLs: {one per line, for an extract}
- max_age_hours: {the cadence in hours, search only}
- Alert when: {the change rule}
- Snapshot: snapshot.json

## Run again

Read this file. Use `tavily-search` to run the same search or extract. On a
search, pass `max_age_hours` from this file. Compare the result to
snapshot.json using the alert rule above. Report only the changes. Then
replace snapshot.json with this run. If the search is refused with `434`,
report that and keep the snapshot.

monitors/{name}/snapshot.json:

{
  "ran_at": "YYYY-MM-DD",
  "kind": "search",
  "query": "",
  "items": [{ "url": "", "title": "", "snippet": "" }]
}

For an extract, store pages instead of items: url, sha256 of the extracted content, and a short excerpt of the part being watched.

In the reply, give the cadence, max_age_hours for a search, the query or the URLs, the alert rule, and the folder path, plus what the baseline already shows.