observe

Use this skill when the user asks to "check observations", "what did Crawlio see", "show crawl timeline", "query the observation log", or wants to review what happened during a crawl session. Queries the append-only observation log with filtering by host, source, operation, and time range.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "observe" with this command: npx skills add crawlio-app/crawlio-plugin/crawlio-app-crawlio-plugin-observe

observe

Query Crawlio's observation log — the append-only timeline of everything Crawlio observed during a crawl session.

When to Use

Use this skill when the user wants to:

  • See what happened during a crawl
  • Review extension captures (framework detection, network requests, console logs)
  • Reconstruct a timeline of events
  • Find specific observations by host, source, or time range

Quick Reference

Get Recent Observations

get_observations({ limit: 20 })

Filter by Host

get_observations({ host: "example.com", limit: 50 })

Filter by Source

SourceWhat It Captures
extensionChrome extension enrichment (framework, network, console, DOM)
engineCrawl lifecycle events (crawl_start, crawl_done)
webkitWebKit runtime capture
agentAI-created findings
get_observations({ source: "extension", limit: 30 })

Filter by Operation

OpMeaning
observeRaw data capture
findingAgent-created insight
crawl_startCrawl began
crawl_doneCrawl completed
pageSingle page observation
get_observations({ op: "crawl_done" })

Time-Based Query

Use Unix timestamps to query a time range:

get_observations({ since: 1708444200, limit: 100 })

Combine Filters

get_observations({
  host: "example.com",
  source: "extension",
  op: "observe",
  limit: 50
})

Single Observation Lookup

Look up a specific observation or finding by ID:

get_observation({ id: "obs_a1b2c3d4" })

Use this to verify evidence referenced by findings, or to inspect the full payload of an evidenceId returned by analyze_page. Works with both obs_xxx (observation) and fnd_xxx (finding) IDs.

Reading Observations

Each observation entry contains:

  • id — unique identifier (obs_ prefix for observations, fnd_ for findings)
  • op — what type of event this is
  • ts — ISO 8601 timestamp
  • url — the URL this relates to
  • source — what produced this entry
  • data — composite payload (framework detection, network requests, console logs, progress, etc.)

Common Patterns

Timeline Reconstruction

Query by host with no limit to see the full story of a crawl:

get_observations({ host: "example.com" })

Crawl Summary

Get start and end events to see crawl performance:

get_observations({ op: "crawl_start" })
get_observations({ op: "crawl_done" })

The crawl_done entry includes progress data (totalDiscovered, downloaded, failed).

Extension Audit

See everything the Chrome extension captured:

get_observations({ source: "extension", limit: 200 })

Evidence Chain Verification

Verify evidence referenced by a finding:

get_observation({ id: "obs_a1b2c3d4" })

This returns the full observation entry. Use it to confirm that evidence IDs in findings actually support the claimed insight.

After Observation — Create Findings

Once you've identified patterns in observations, use the finding skill to record insights with evidence chains.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

crawl-site

No summary provided by upstream source.

Repository SourceNeeds Review
General

finding

No summary provided by upstream source.

Repository SourceNeeds Review
Security

audit-site

No summary provided by upstream source.

Repository SourceNeeds Review