research-scout

Name: research-scout
Author: yusuke124358

Codex skill research-scout

by yusuke124358(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from yusuke124358/keiba (.codex/skills/research-scout/SKILL.md). Install upstream with npx skills add yusuke124358/keiba --skill research-scout. Copyright stays with the author.

--- name: research-scout description: Perform web-search-based research to build a reading list and experiment ideas backlog.

Research Scout

Steps

Use web search with cached results first.
If cached results are insufficient, ask before using live search.
Populate docs/research/reading_list.md with:
- Title, brief summary, reason to include
- Reproduction difficulty and license note
- Source URL
Extract ideas into docs/research/ideas/backlog.yml.
For horse-racing topics, add a leakage/forward-looking data review note.

Output

Updated reading list and ideas backlog.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install research-scout and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

yusuke124358-keiba-research-scout.ocm.jsonjson

{
  "ocm": "1",
  "id": "yusuke124358-keiba-research-scout",
  "kind": "skill",
  "name": "research-scout",
  "description": "Codex skill research-scout",
  "publisher": "yusuke124358",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Codex skill research-scout"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/yusuke124358/keiba",
      "path": ".codex/skills/research-scout/SKILL.md",
      "ref": "f32329cea80fecafd44588e72cfcc6ced5a0717c",
      "url": "https://github.com/yusuke124358/keiba/blob/f32329cea80fecafd44588e72cfcc6ced5a0717c/.codex/skills/research-scout/SKILL.md",
      "key": "yusuke124358/keiba/.codex/skills/research-scout/SKILL.md"
    }
  },
  "instructions": "---\nname: research-scout\ndescription: Perform web-search-based research to build a reading list and experiment ideas backlog.\n---\n\n# Research Scout\n\n## Steps\n1) Use web search with cached results first.\n2) If cached results are insufficient, ask before using live search.\n3) Populate `docs/research/reading_list.md` with:\n   - Title, brief summary, reason to include\n   - Reproduction difficulty and license note\n   - Source URL\n4) Extract ideas into `docs/research/ideas/backlog.yml`.\n5) For horse-racing topics, add a leakage/forward-looking data review note.\n\n## Output\n- Updated reading list and",
  "cost": {
    "context_tokens": 153
  }
}

Fetch it by URL: GET /api/v1/registry/yusuke124358-keiba-research-scout/manifest?version=1.0.0