Paper Relevance Filter

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.

200 stars 25 forksResearch & Science Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill paper-relevance-filter
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/paper-relevance-filter ~/.claude/skills/paper-relevance-filter

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# paper-relevance-filter

Decide whether a fetched paper belongs in this week's digest. Output is a per-paper decision (KEEP / DROP / REVIEW), a 0-100 score, and a one-line rationale that the user can audit.

## Workflow

```
- [ ] Step 1: Load relevance criteria + the watchlist + last-4-weeks kept-paper IDs
- [ ] Step 2: Score each paper on three axes (match, criteria, novelty)
- [ ] Step 3: Combine to a 0-100 score; map to KEEP / REVIEW / DROP via thresholds
- [ ] Step 4: Apply tie-breakers (cap output at requested max kept count)
- [ ] Step 5: Return decisions + a calibration summary
```

**Step 1 — Inputs**

The caller hands the skill:
- `papers`: list of normalized paper records (output of `fetch-preprint-recent` or `fetch-pubmed-recent`)
- `watchlist`: list of keywords/phrases (with optional weights — default weight 1.0)
- `criteria`: text from `relevance-criteria.md` describing what fits and what doesn't
- `prior_ids`: set of `id` values that appeared as KEEP in any of the last 4 digests (used for novelty)
- `max_kept`: target ceiling, e.g. 25 (the digest will not exceed this)

**Step 2 — Three-axis scoring**

For each paper, compute three sub-scores in [0, 1]:

**Axis 1 — Match strength (0-1)**
- 0.0 if no watchlist keyword appears in title or abstract
- 0.5 if a keyword appears once in the abstract only
- 0.7 if a keyword appears in the abstract more than once OR in title once
- 1.0 if a keyword appears in the title AND abstract, or multiple distinct keywords match
Read the full skill on GitHub

Details

Skill name
paper-relevance-filter
Path
skills/paper-relevance-filter/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Paper Relevance Filter skill do?

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.

How do I install the Paper Relevance Filter 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 Relevance Filter popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/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.

Testing & QA25

Academic Letter Architect

200

lyndonkl/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.

Research & Science25

Adr Architecture

200

lyndonkl/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.

Software Development25

Paper Three Pass Extraction

200

lyndonkl/claude

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

Research & Science25

Paper From Zero Guide

84

mkaremm80/My-Skills-on-Claude

Turn any research paper or technical document (PDF or LaTeX) into a colorful PDF guide that explains it from zero: background, every equation with labels, full proofs, examples, results, and simulation checks. Use when someone wants to understand a hard paper, thesis, report or standard from the ground up.

Research & Science19

Research Claim Map

200

lyndonkl/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".

Research & Science25

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.