agentleFS
arch3rProarch3rPro/ark-space/skills/monitor/SKILL.md

monitor

Skill1 starsChanged 32 days agoMITView on GitHub

Create and manage recurring Exa searches or Firecrawl page, crawl, and web-search monitors through ArkSpace. Use when the user wants scheduled change checks, webhook delivery, a monitor paused or resumed, an immediate check triggered, history inspected, or a persistent monitor deleted.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use spec and debug.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the installed arks CLI or ArkSpace MCP tools.

    line 9
  2. Distinctive:

    Do not present Firecrawl Monitor as an interchangeable Exa Provider:

    line 13
  3. Very specific:

    Use monitor.* for Exa recurring search results.

    line 15
  4. Very specific:

    Use monitor.site.* for Firecrawl page, crawl, or web-search change checks.

    line 16
  5. Distinctive:

    Ask one focused question if the intended contract is unclear.

    line 18
  6. Very specific:

    Run arks --version. If unavailable, explain that ArkSpace CLI is required and ask before changing the user's environment.

    line 22
  7. Very specific:

    Run arks doctor --json when Provider readiness is unknown.

    line 23
  8. Distinctive:

    Ask before changing configuration or the user's environment.

    line 24
  9. Very specific:

    Before creation, present the monitor name, exact query, result count, cadence, public HTTPS webhook, new secret-file path, and continuing …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Monitor

Use the installed arks CLI or ArkSpace MCP tools. Use web.search for one-time discovery and research.run for one attached report.

Choose the contract

Do not present Firecrawl Monitor as an interchangeable Exa Provider:

  • Use monitor.* for Exa recurring search results. Its contract is a query, result count, interval, webhook, run history, and one-time signing secret.
  • Use monitor.site.* for Firecrawl page, crawl, or web-search change checks. Its contract includes typed targets, a cron or natural-language schedule, retention, optional goal-based judging, page-level diffs, Firecrawl credit estimates, and optional webhook events.

Ask one focused question if the intended contract is unclear.

Readiness and ownership

  1. Run arks --version. If unavailable, explain that ArkSpace CLI is required and ask before changing the user's environment.
  2. Run arks doctor --json when Provider readiness is unknown. If credentials are missing, direct the human to run arks setup in a trusted local terminal. Never ask for an API key in conversation or place one in a command argument.
  3. Ask before changing configuration or the user's environment. Use only ArkSpace-owned monitor IDs; every resource is bound to the anonymous key ID that created it.

Create an Exa recurring search

Before creation, present the monitor name, exact query, result count, cadence, public HTTPS webhook, new secret-file path, and continuing charges. Obtain explicit approval, then call monitor.create with confirmed: true.

The secret path must not already exist. ArkSpace creates it with restrictive permissions and never returns the secret. Configure the receiver to verify Exa-Signature. Do not copy the secret into chat.

Create a Firecrawl site monitor

Before creation, present:

  • the exact scrape, crawl, or search targets;
  • the five-field cron or natural-language schedule and IANA timezone;
  • retention from 1–365 days;
  • the judging goal and whether judging is enabled;
  • the public HTTPS webhook and selected monitor.page or monitor.check.completed events, if any;
  • Firecrawl's estimate when available, and that each check bills underlying scrape, crawl, search, and optional judging work.

Obtain explicit approval, then call monitor.site.create with confirmed: true. Search targets require a non-empty goal unless judging is explicitly disabled. ArkSpace bounds targets and outputs, forces fresh monitored fetches, and does not expose arbitrary scrape code, webhook headers, or secret values.

For the CLI, place create fields in a JSON object and run:

arks monitor site create --input ./site-monitor.json --confirm --json

Operate

Exa operations:

  • monitor.list, monitor.status, monitor.runs, monitor.run.get
  • confirmed mutations: monitor.update, monitor.pause, monitor.resume, monitor.trigger, monitor.delete

Firecrawl operations:

  • monitor.site.list, monitor.site.status, monitor.site.checks, monitor.site.check.get
  • confirmed mutations: monitor.site.update, monitor.site.pause, monitor.site.resume, monitor.site.trigger, monitor.site.delete

State the exact resource ID and effect before every mutation. Pausing retains configuration and history. Resuming restores scheduled work. Triggering queues paid work immediately. Deletion is irreversible at the Provider resource level.

Failure and deletion

ArkSpace never rotates credentials or Providers for an owned monitor. Restore a missing owning environment-variable credential rather than creating a duplicate.

If create reports acceptance-unknown, check the correct Provider dashboard before retrying. If a mutation reports safeToRetry: false, refresh status or history before acting again. A successful delete confirms removal of the API resource only; do not claim physical erasure of retained artifacts, delivery records, logs, or backups.

Report the monitor ID, Provider, target or query, schedule, current state, and mutation outcome. Summarize run or check history instead of pasting raw Provider payloads, while preserving warnings and uncertain effects.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.