Skip to content

moonlight-lupin/agent-skills / research/news-monitoring

news-monitoring

Verified

Use when a topic or news stream needs recurring monitoring — cover it with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Covers search strategy, source selection, Chinese-language platforms, and digest templates.

evals/routing-fixtures.json

View on GitHub
{
  "skill_name": "news-monitoring",
  "purpose": "Lightweight routing + output-contract fixtures for news-monitoring. Specs, not executed live in CI; validated by tests/test_routing_fixtures.py. They capture when recurring/monitoring requests belong here vs. one-off research, and what a digest must contain.",
  "fixtures": [
    {
      "id": "nm-01-recurring-digest",
      "request": "Set up a digest of AI-policy news and send it to me every Monday morning.",
      "expected_routing": {
        "skill": "news-monitoring",
        "reason": "Recurring, scheduled monitoring with delivery — the core of news-monitoring (cron + digest).",
        "not": ["deep-research"]
      },
      "required_output_fields": ["dated items", "direct source links", "per-item summary", "dedup against previous digests"],
      "forbidden_patterns": ["(?i)as an ai language model", "(?i)google news proxy url", "(?i)bing apiclick"]
    },
    {
      "id": "nm-02-multilang-monitor",
      "request": "Track Hong Kong student-housing news in both English and Chinese and give me the top items each fortnight.",
      "expected_routing": {
        "skill": "news-monitoring",
        "reason": "Ongoing multi-language topic monitoring with periodic delivery.",
        "not": ["deep-research", "website-scraping"]
      },
      "required_output_fields": ["dated items", "direct source links", "language coverage note"],
      "forbidden_patterns": ["(?i)as an ai language model"]
    },
    {
      "id": "nm-03-boundary-oneoff-report",
      "request": "Give me a one-off, in-depth report on how AI regulation has evolved globally, with citations.",
      "expected_routing": {
        "skill": "deep-research",
        "reason": "A single comprehensive cited report (not recurring) is deep-research, not monitoring.",
        "not": ["news-monitoring"]
      },
      "required_output_fields": ["inline citations", "sources/references list", "research stats"],
      "forbidden_patterns": ["(?i)as an ai language model"]
    }
  ]
}
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall