nestbrowse-info-seeking

{
  "ocm": "1",
  "id": "adu2021-skillxiv-nestbrowse-info-seeking",
  "kind": "skill",
  "name": "nestbrowse-info-seeking",
  "description": "Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner loop filters content before context injection, multi-task learning trains outer/inner jointly—enabling 4B models to match larger competitors.",
  "publisher": "ADu2021",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "information-seeking",
      "web-agents",
      "nested-architecture",
      "efficiency",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner loop filters content before context injection, multi-task learning trains outer/inner jointly—enabling 4B models to match larger competitors."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/ADu2021/skillXiv",
      "path": "skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md",
      "ref": "10b9e2ab98d22d657cdca33fadb35feaf4a2e26b",
      "url": "https://github.com/ADu2021/skillXiv/blob/10b9e2ab98d22d657cdca33fadb35feaf4a2e26b/skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md",
      "key": "ADu2021/skillXiv/skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md"
    },
    "license": "MIT"
  },
  "instructions": "## Overview\n\nNested architecture decouples reasoning from page content extraction.\n\n## Core Technique\n\n**Nested Loop Structure:**\n\n```python\n# Outer loop: reasoning\nreasoning = outer_agent.think(state)\ntool_call = outer_agent.select_tool()\n\n# Inner loop: extract relevant content\nrelevant_content = inner_agent.extract(page, goal)\n\n# Return minimal content to reasoning\n```\n\n## When to Use\n\nUse when: Information-seeking agents, large-scale web interaction, efficiency critical.\n\n## References\n\n- Nested outer/inner loop architecture\n- Minimal browser toolkit\n- Content filtering before context injec",
  "cost": {
    "context_tokens": 151
  }
}