Back to Cookbook
KiloClaw

Literature Triage Queue

Turn an overwhelming reading backlog into a prioritized plan

Too many papers, too little time, no reliable way to decide what to read next. This recipe builds a time-boxed, prioritized reading queue for any topic, project, or thesis chapter — with a built-in "rabbit-hole safe" capture channel for questions to research later.

House RecipeWork3 min

INGREDIENTS

🔎Web Search📄Google DocsTodoist📅Calendar

PROMPT

Create a skill called "Literature Triage Queue". Goal: - Convert an overwhelming body of literature into a prioritized, time-boxed plan and a synthesis-ready notes system, without endless rabbit holes. When I run this skill, ask for: - Research question/topic + 5-15 keywords - Field/subfield (if known; if unknown, mark as unspecified) - Any seed papers (DOIs/titles/links) and/or an exported library (RIS/BibTeX) if available - Deadline and weekly reading hours - Output format preference: Google Doc / Markdown / plain text - Whether this is a systematic review, dissertation chapter, grant background, or general orientation Output: 1) A ranked queue: NOW (top 10), NEXT (20), LATER (rest), each with one-sentence rationale. 2) A reading plan for the next 2 weeks (time-boxed blocks). 3) A reusable note template per paper (purpose, methods, results, limitations, how I might cite it). 4) A "Questions to Park" list: questions that came up but are deferred. 5) A short synthesis snapshot: emerging themes, contradictions, and gaps. Rules: - Don't invent citations or claims about papers I haven't provided. - If a detail is missing, mark it as "unspecified" and continue with best-effort structure.

How It Works

You have a pile of papers and no idea where to start. This recipe runs a

"seed → expand → prioritize" workflow: start from review papers, key authors,

or an advisor-provided list, then rank everything into a reading queue with

clear next actions.

What You Get

  • A ranked reading queue (NOW / NEXT / LATER), where every paper has:
  • Why it matters to *your* question
  • What to extract (methods, dataset, claims, limitations)
  • A decision state: skim / deep read / cite-only / drop
  • A weekly time-boxed reading plan
  • A reusable note template that feeds directly into writing and synthesis
  • A running "Questions to Park" list so you don't spiral mid-read

Setup Steps

  1. Provide your topic, constraints, and any seed papers (titles/DOIs/links)
  2. Provide your deadline (if any) and weekly available reading hours
  3. Optionally export your reference library (RIS/BibTeX) — if you have one
  4. The Claw generates the queue + note template + weekly schedule
  5. Each week, re-run to update priorities and synthesize emerging themes

Tips

  • Time-box searches: add questions to the "park list" and keep reading
  • Keep an explicit "drop" state — not everything deserves deep reading
  • If systematic review: split queue into "screen" vs "extract" phases
  • Works best when you re-run weekly to reflect new priorities
Tags:#academics#literature-review#reading#synthesis#productivity