paper-triage

paper-triage is a skill for Claude Code from zongmin-yu/semantic-scholar-skills. It costs 24 tokens per session (456 once invoked), scanned A, original, MIT.

A tool for narrowing down an unclear research-paper request into possible meanings and a ranked list of likely papers. It helps when a title is incomplete, vague, or could refer to several papers.

In plain words
What is it for?
Use it to investigate remembered title fragments, ambiguous terms, or vague paper descriptions and produce a shortlist for follow-up.
Why use it?
It reduces time spent searching the wrong paper when the initial query is uncertain. It also suggests what research workflow to use after identifying the right paper.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the semantic-scholar plugin — 3 skills shipped together

Good fit Use it to investigate remembered title fragments, ambiguous terms, or vague paper descriptions and produce a shortlist for follow-up.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zongmin-yu/semantic-scholar-skills/paper-triage
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zongmin-yu/semantic-scholar-skills --skill paper-triage
Clone the repo
git clone --depth 1 https://github.com/zongmin-yu/semantic-scholar-skills

Made for: Claude Code.

Or install semantic-scholar, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/zongmin-yu/semantic-scholar-skills/paper-triage/github.svg)](https://agentmods.dev/skills/zongmin-yu/semantic-scholar-skills/paper-triage)
Your own site
<a href="https://agentmods.dev/skills/zongmin-yu/semantic-scholar-skills/paper-triage"><img src="https://agentmods.dev/badge/skills/zongmin-yu/semantic-scholar-skills/paper-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for paper-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/zongmin-yu/semantic-scholar-skills/paper-triage"><img src="https://agentmods.dev/badge/skills/zongmin-yu/semantic-scholar-skills/paper-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00456
Opus 5 $0.00012 $0.00228
Sonnet 5 $0.00005 $0.00091
Haiku 4.5 $0.00002 $0.00046

Measured 12d ago against content hash 8688e5649760, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills-src/paper-triage/SKILL.md · 45 lines

What it actually says

Paper Triage

Turn an ambiguous paper query into a ranked shortlist and clear next steps. Use this when the human starts with a fuzzy title fragment, overloaded term, or vague memory of a paper.

Arguments

  • The positional argument is the paper query. Quote multi-word titles when running from a shell.
  • --shortlist-size <n> controls the final shortlist size returned to the human.
  • --relevance-limit <n> controls the first relevance-search pass.
  • --bulk-candidate-limit <n> controls the wider recall pass.
  • --snippet-candidate-limit <n> controls how many preliminary candidates get snippet search.
  • --snippet-limit-per-paper <n> caps snippet evidence gathered for each snippet target.

Workflow

  1. Run python scripts/run.py ....
  2. Read result.possible_interpretations to see how the query was resolved.
  3. Read result.shortlist for the ranked candidate papers.
  4. Read result.follow_up_actions to know which workflow to run next once the right paper is identified.
  5. If the shortlist still looks wrong, rerun with a more specific query string.

Output

  • The script prints the unified JSON envelope described in output_contract.md.
  • The underlying workflow result is TriageResult.to_dict().
  • result.notes captures extra execution notes, and result.considered_candidates shows the rerank breadth.

When To Escalate

  • The query is too vague to resolve into a useful shortlist.
  • The top interpretation is clearly wrong even after adding specificity.
  • The human really wants author lookup or direct paper details instead of title disambiguation.
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 45 lines · 24 tokens per session scan A 8688e5649760

Subscribe to this mod's changes

paper-triage is a skill published in the GitHub repository zongmin-yu/semantic-scholar-skills (21 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 456 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

academic-research

Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…

Lingtai-AI/lingtai · 180 tokens

research-architect

Use when a user needs the end-to-end Research Architect workflow to turn a raw idea, user-designated accessible target reference paper, partial research materials, results, or an existing draft into an auditable research plan, draft, or revision path.

mmTheBest/Research-Architect · 53 tokens

research-architect-draft

Use when a Research Architect project has an evidence-ready spine, evidence and claim trail, citation support, terminology/object identities, and display logic that need to become an evidence-first, promise-aware first draft or audited revision.

mmTheBest/Research-Architect · 49 tokens

research-architect-evidence

Use when executed research materials, results, observations, analyses, or draft claims need to become a Research Architect evidence bank, claim register, manuscript-wide display sequence, panel-level evidence map, and bounded interpretation trail.

mmTheBest/Research-Architect · 48 tokens

research-architect-literature

Use when a Research Architect project needs accessible target-reference papers analyzed for transferable research logic, or candidate questions positioned against literature, gaps, evidence standards, and independent study options—not generic bibliography collection.

mmTheBest/Research-Architect · 44 tokens

research-architect-audit

Use when reviewing, revising, or deciding whether to complete a Research Architect draft, especially when its reference adaptation, design, evidence, citations, claim boundaries, copying risk, or missing upstream artifacts need an auditable diagnosis.

mmTheBest/Research-Architect · 51 tokens