Update to A-Z Links: Easily view sources

{
  "description": "Triage a Links reading backlog when the user asks which resources matter most for a goal, what to read before a deadline, or how to reduce an overwhelming list. Choose a focused subset and explain deferrals using supplied summaries or inspected sources. Use for prioritization, not a beginner-to-advanced curriculum, invented reading times, or completion tracking.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 243
    }
  ],
  "name": "triage-reading-list",
  "skill_md_contents": "---\nname: triage-reading-list\ndescription: \"Triage a Links reading backlog when the user asks which resources matter most for a goal, what to read before a deadline, or how to reduce an overwhelming list. Choose a focused subset and explain deferrals using supplied summaries or inspected sources. Use for prioritization, not a beginner-to-advanced curriculum, invented reading times, or completion tracking.\"\n---\n\n# Triage Reading List\n\nChoose the smallest useful reading subset for the user's immediate goal and\nretain a clear record of what was deferred.\n\n## Inputs\n\n- Obtain the immediate goal and any deadline, available time, required sources,\n  or constraints on format and access.\n- Use supplied links or the latest model-visible `modelContent.links`. Request\n  updated links when the user refers to unavailable widget edits.\n- Use supplied summaries, excerpts, and durations or inspect pages through\n  available browsing tools when content assessment requires it.\n\n## Workflow\n\n1. Establish the decision or outcome the reading must enable. Ask for a missing\n   goal when it would change the selection. Treat an unstated time budget as\n   unknown rather than inventing one.\n2. Assess each resource's direct relevance, unique contribution, prerequisite\n   value, and any known effort or access constraint. Distinguish verified\n   information, user-supplied summaries, and uncertain judgments. Do not rank\n   unseen pages by unsupported assumptions about their contents.\n3. Group the resources conceptually into essential now, useful if time remains,\n   and deferred. Preserve mandatory items and explain overlap or low relevance\n   without calling unread material low quality.\n4. Select a focused essential subset and put the most useful starting resource\n   first. Prefer coverage of the immediate goal over a fixed item count. Flag\n   prerequisites or missing information that may change the priorities.\n5. Use only supplied or verified durations when assessing fit to a time budget.\n   If durations are unknown, prioritize qualitatively and say the schedule fit\n   is uncertain. Do not infer read status, completion, or deadlines from private\n   widget state.\n6. Preserve accurate titles. Put priority, the reason to read, and a suggested\n   focus in each selected description. Keep these annotations grounded in\n   available source information.\n7. Deliver one focused collection and a short companion list of deferred\n   resources with reasons. Include optional reading only when it helps the\n   user; publish a second collection only if requested. Identify assumptions\n   and unknown durations that materially affect the plan.\n\n## Publish with Links\n\nCall `links` with the selected ordered HTTP(S) entries, each containing string\n`url`, `title`, and `description` fields, and an optional brief `reason`. Keep\npriority labels in descriptions; no priority, deadline, or read-status tool\narguments exist. Treat the returned `{ links }` as an echo.\n\nExplain that this publishes a new subset without removing entries from the\nearlier widget. Leave pinning, editing, undo, and Share to the user. Do not\nclaim to schedule reminders, operate the clipboard, or track reading progress.\n\nHonor text-only requests and tool prohibitions with a textual shortlist. If no\nresource fits the goal or no usable URLs are available, explain the gap instead\nof inventing resources or publishing an empty collection.\n"
}