Paper Three Pass Extraction
Domain-neutral methodology for autonomously extracting structured notes from a single academic paper via three escalating passes. Pass 1 (inspectional, ~10-15 min) reads title, abstract, intro, section headings, conclusion, references at a glance, then applies the Five Cs framework (Category, Context, Correctness, Contributions, Clarity). Pass 2 (content grasp, ~30-60 min) reads the full paper skipping proofs, answers main-argument / Big-Question / hypotheses / figure-by-figure / references / confusions. Pass 3 (deep understanding, ~1-4 hours, reserved for important papers) virtually re-implem
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill paper-three-pass-extractiongit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/paper-three-pass-extraction ~/.claude/skills/paper-three-pass-extractionPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# paper-three-pass-extraction
Three-pass methodology for extracting structured notes from a single academic paper. Each pass escalates from cheap-and-shallow to expensive-and-deep; downstream agents trigger Pass 2 only for relevant papers and Pass 3 only on explicit operator request.
The **central principle**: every question in this methodology is answered *by the agent reading the paper*, against the paper's content. Never ask the operator the questions. Never have a Socratic dialogue. The questions are an internal extraction checklist whose purpose is to produce structured output — not user-facing prompts.
## Workflow
```
- [ ] Pass 1: Inspectional reading (always run)
- Read title, abstract, intro paragraphs, section headings, conclusion, references at a glance
- Apply the Five Cs framework
- Produce Pass 1 extraction output
- [ ] Pass 2: Content grasp (run when escalated, e.g., paper passed relevance filter)
- Acquire full text (PDF or HTML); flag if unavailable
- Read linearly, skipping proofs and heavy derivations
- Answer the Pass 2 question set
- Append Pass 2 extraction output
- [ ] Pass 3: Deep understanding (run only on operator request)
- Re-read methods + proofs that Pass 2 skipped
- Virtually re-implement the core idea
- Answer the Pass 3 question set
- Append Pass 3 extraction output
```
## Pass 1 — Inspectional ReadingDetails
- Skill name
paper-three-pass-extraction- Repository
- lyndonkl/claude
- Path
skills/paper-three-pass-extraction/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Paper Three Pass Extraction skill do?
Domain-neutral methodology for autonomously extracting structured notes from a single academic paper via three escalating passes. Pass 1 (inspectional, ~10-15 min) reads title, abstract, intro, section headings, conclusion, references at a glance, then applies the Five Cs framework (Category, Context, Correctness, Contributions, Clarity). Pass 2 (content grasp, ~30-60 min) reads the full paper skipping proofs, answers main-argument / Big-Question / hypotheses / figure-by-figure / references / confusions. Pass 3 (deep understanding, ~1-4 hours, reserved for important papers) virtually re-implem
How do I install the Paper Three Pass Extraction skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Paper Three Pass Extraction popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
Academic Letter Architect
200lyndonkl/claude
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
Adr Architecture
200lyndonkl/claude
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
Research Claim Map
200lyndonkl/claude
Systematically evaluates claims by triangulating sources, rating evidence quality (primary/secondary/tertiary), assessing source credibility, and reaching confidence-rated conclusions to prevent confirmation bias and reliance on unreliable sources. Use when verifying claims before decisions, fact-checking statements, conducting due diligence, evaluating conflicting evidence, or when user mentions "fact-check", "verify this", "is this true", "evaluate sources", "conflicting evidence", or "due diligence".
Paper Relevance Filter
200lyndonkl/claude
Scores a candidate paper against a keyword watchlist and a relevance-criteria document, returning KEEP/DROP/REVIEW with a one-line rationale and a 0-100 relevance score. Combines keyword-match strength, criteria-fit, and a historical-context check (was this paper or its preprint already covered in a recent digest). Domain-neutral - usable for any literature-scan workflow. Use after fetching candidate papers from bioRxiv, medRxiv, or PubMed and before clustering or synthesis. Trigger keywords - paper relevance, filter papers, keep or drop, score papers, relevance rationale.
Retrieval Search Orchestration
200lyndonkl/claude
Designs retrieval strategies for querying knowledge graphs in RAG systems, covering pattern selection (global-first, local-first, U-shaped hybrid), query decomposition for multi-hop reasoning, ranking and constraint configuration, and provenance tracking for citation. Use when designing retrieval pipelines, orchestrating search over knowledge graphs, or when user mentions retrieval strategy, search orchestration, query decomposition, multi-hop reasoning, provenance tracking, or citation in GraphRAG.
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.