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 Nehra-Amaterasu/zotero-mcp --skill annotate-papergit clone --depth 1 https://github.com/Nehra-Amaterasu/zotero-mcpWrote 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/nehra-amaterasu/zotero-mcp/annotate-paper)<a href="https://agentmods.dev/skills/nehra-amaterasu/zotero-mcp/annotate-paper"><img src="https://agentmods.dev/badge/skills/nehra-amaterasu/zotero-mcp/annotate-paper/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/nehra-amaterasu/zotero-mcp/annotate-paper"><img src="https://agentmods.dev/badge/skills/nehra-amaterasu/zotero-mcp/annotate-paper.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 | $0.00082 | $0.01559 |
| Opus 5.5 | $0.00033 | $0.00624 |
| Sonnet 5.5 | $0.00016 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
annotate-paper 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 5d 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.
This is a copy
100% identical to annotate-paper — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotate a paper for understanding
The goal is a PDF someone can study from cold: the background, the argument and every figure explained in place.
Colour scheme (change it here)
Use exactly these colours so every paper reads the same way. Edit the table to make the scheme your own; the rest of the skill refers to the roles, not the colours.
| Annotation | Where | Colour | Content |
|---|---|---|---|
| Context box | around the title and authors, page 1 | orange | What a newcomer needs first: the field, key terms defined plainly, the problem's history, why this approach. Start with CONTEXT. |
| Four-part summary | around the abstract | magenta | THE WHOLE PAPER IN FOUR PARTS. then // PROBLEM:, // METHOD: (with the real numbers), // RESULTS: (numbered), // TAKEAWAY: and the limits. |
| Abstract highlights | sentences in the abstract | by role | Prefix each comment with its role: PROBLEM. / GOAL. / CONCLUSION. (yellow), METHOD. (blue), DISCOVERY. (green). |
| Figure boxes | one per sub-panel | purple | See "Figure boxes" below. |
| Body highlights | key sentences throughout | yellow / blue / green / red | yellow = claim or big idea; blue = method, data or design choice; green = finding or evidence; red = limitation, caveat or critique. |
This skill sits on top of the zotero-cli skill. Run zotero-cli config once first; writing annotations needs local
write access.
1. Find the paper and its PDF
Use the paper that is open in the reader, or the one the user names:
zotero-cli --json search "title words" --limit 5
zotero-cli --json get children ITEM_KEY # the PDF attachment's key; supplementary PDFs are attachments too
Annotate the main PDF, not the supplement, unless asked.
2. Read the whole paper, then look at every figure
zotero-cli read ITEM_KEY --start-page 1 --end-page 99
Read all of it, including Methods and figure captions. Extracted text is unreliable for figures, tables and math, so render every figure page and look at it yourself:
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.
- 5d ago First seen · 119 lines · 82 tokens per session scan A 2bd12a3e63f2
annotate-paper is a skill published in the GitHub repository Nehra-Amaterasu/zotero-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 82 tokens to every session and 1,559 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to annotate-paper, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.