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 zfy465914233/scholar-agent --skill paper-analysisgit clone --depth 1 https://github.com/zfy465914233/scholar-agentWrote 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/zfy465914233/scholar-agent/paper-analysis)<a href="https://agentmods.dev/skills/zfy465914233/scholar-agent/paper-analysis"><img src="https://agentmods.dev/badge/skills/zfy465914233/scholar-agent/paper-analysis/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/zfy465914233/scholar-agent/paper-analysis"><img src="https://agentmods.dev/badge/skills/zfy465914233/scholar-agent/paper-analysis.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 | $0.00029 | $0.00618 |
| Opus 5 | $0.00015 | $0.00309 |
| Sonnet 5 | $0.00006 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
paper-analysis 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 11d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Analysis Skill
Generate a comprehensive analysis note for a single paper.
Step 1: Download the paper
download_paper(paper_id="2510.24701", title="Paper Title", domain="LLM")
This caches the PDF locally under paper-notes/<title>/.
Step 2: Extract figures
extract_paper_images(paper_id="2510.24701")
Auto-detects the local PDF. Images go to paper-notes/<title>/images/.
Step 3: Generate the analysis note
analyze_paper(paper_json='{"title": "...", "authors": [...], "arxiv_id": "..."}', language="zh")
Returns:
note_path: path to the generated markdown notequality_check: whether the note has unfilled placeholderspdf_text: full text extracted from the PDF (if available)instructions: if placeholders exist, instructions to fill them
Step 4: Fill placeholders
The generated note contains <!-- LLM: describe method --> style placeholders. When instructions is non-null, you MUST fill all placeholders using the pdf_text field:
Filling rules
- Read the note at
note_path. - For each
<!-- LLM: ... -->placeholder, replace it with substantive content drawn frompdf_text. - Be specific: cite numbers, dataset names, architecture details, formula descriptions.
- Do NOT leave any placeholder unfilled.
- Write the complete filled note back using the Write tool.
Section guide
| Section | What to write |
|---|---|
| Core information | One-sentence contribution, key result, paper type |
| Abstract translation | Translate or paraphrase the abstract with domain context |
| Research background | What problem existed, why it matters |
| Research questions | List the explicit or implicit questions the paper addresses |
| Method overview | Architecture, algorithm, pipeline — with specifics |
| Experimental results | Datasets, metrics, comparisons, ablation findings |
| Deep analysis | Strengths, weaknesses, assumptions, limitations |
| Comparison with related work | Position vs. prior art |
| Technical roadmap | Where this fits in the broader research trajectory |
| Future work | Open questions the paper raises |
| Comprehensive evaluation | Your own 1-5 rating with justification |
| My notes | Leave empty for user to fill |
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.
- 11d ago First seen · 81 lines · 29 tokens per session scan A e53ddaf3eafe
paper-analysis is a skill published in the GitHub repository zfy465914233/scholar-agent (9 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 618 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 2026-08-31.
Other skills, from other repositories
proposal-import
Import an existing proposal (usually PDF) into the standard single-file format — extract text and references, strip personal data, mark gaps. Use when the user has a draft from Word, LaTeX, Overleaf or another tool, pastes the text of an older proposal, or wants to carry existing work over and continue it here.
proposal-publish
Build a PDF (or docx fallback) from a proposal file via pandoc — compact layout, typst-first, with install guidance when tools are missing. Also offers a stripped hand-in export, and hands over to a workspace build script where one exists. Use when the user wants a PDF or something to email, print or hand to their…
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.