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.
npx skills add Stars-Shen/Paper-insight-skill --skill paper-insightgit clone --depth 1 https://github.com/Stars-Shen/Paper-insight-skillWrote 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.
[](https://agentmods.dev/skills/stars-shen/paper-insight-skill/paper-insight)<a href="https://agentmods.dev/skills/stars-shen/paper-insight-skill/paper-insight"><img src="https://agentmods.dev/badge/skills/stars-shen/paper-insight-skill/paper-insight/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.
<a href="https://agentmods.dev/skills/stars-shen/paper-insight-skill/paper-insight"><img src="https://agentmods.dev/badge/skills/stars-shen/paper-insight-skill/paper-insight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.01928 |
| Opus 5 | $0.00054 | $0.00964 |
| Sonnet 5 | $0.00022 | $0.00386 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
paper-insight 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.
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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Insight
Overview
Use this skill to turn one paper or a small paper set into citation-grounded research insight: structured reading notes, innovation judgment, paper scorecards, strategic citation chaining, related-work expansion and drafting, idea incubation, future directions, paper-to-project transfer plans, reproducibility checks, a general domain checklist, and literature maps. Prefer primary sources, official paper pages, PDFs, project pages, official repositories, and authoritative indexes over secondary summaries.
Operating Principles
- Separate paper claims, evidence-supported conclusions, and your own inferences.
- Do not fabricate citations, venues, DOIs, arXiv IDs, datasets, results, page numbers, or related papers.
- If only the abstract is available, say that the assessment is abstract-only.
- Prefer fewer well-read papers over long unvetted lists.
- Stop expansion when new papers no longer change the interpretation or the user's requested scope is reached.
Workflow
- Clarify scope only when needed: paper(s), domain, output mode, venue/year constraints, whether preprints are acceptable, and whether code reuse matters.
- Collect source material:
- For local PDFs, use
pdfinfo,pdftotext -layout, and visual inspection when figures/tables matter. - For web sources, use primary paper pages, arXiv, OpenReview, ACL Anthology, ACM/IEEE/publisher pages, PubMed, Semantic Scholar, Crossref, Papers with Code, and official repositories.
- For recent or "latest" work, browse and record exact dates.
- For local PDFs, use
- Read in layers:
- Pass 1: title, abstract, introduction, conclusion.
- Pass 2: method, experiments, limitations, appendix, key tables/figures.
- Pass 3: related work and citations only if expansion is needed.
- Produce the lightest useful output:
structured_reading: detailed paper notes.innovation_check: contribution and novelty assessment.paper_scorecard: quality, evidence, reproducibility, transferability, and reading-priority scoring.citation_chaining: backward, forward, lateral, benchmark, and negative/critique literature expansion.related_work_expansion: nearby papers and relationship types.related_work_draft: cohesive related-work paragraphs organized by timeline, method family, problem evolution, or motivation gap.future_directions: limitations converted into feasible research plans.idea_incubator: research hypotheses, minimal experiments, expected outcomes, risks, and possible paper angles.paper_to_project: reusable units, target files/modules, integration risks, and minimal project validation.reproducibility_check: code/data/checkpoint/experiment reuse assessment.domain_checklist: field-specific validity, evidence, and risk checks.literature_map: graph or table of paper relationships.
What ships with it
7 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.
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.
- 12d ago First seen · 157 lines · 108 tokens per session scan A 58f0a5afe667
paper-insight is a skill published in the GitHub repository Stars-Shen/Paper-insight-skill (55 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 1,928 once invoked, about $0.0005 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.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.