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 virtualarchitectures/Local-Zotero-MCP --skill analyzing-zotero-researchgit clone --depth 1 https://github.com/virtualarchitectures/Local-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/virtualarchitectures/local-zotero-mcp/analyzing-zotero-research)<a href="https://agentmods.dev/skills/virtualarchitectures/local-zotero-mcp/analyzing-zotero-research"><img src="https://agentmods.dev/badge/skills/virtualarchitectures/local-zotero-mcp/analyzing-zotero-research/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/virtualarchitectures/local-zotero-mcp/analyzing-zotero-research"><img src="https://agentmods.dev/badge/skills/virtualarchitectures/local-zotero-mcp/analyzing-zotero-research.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 | $0.00092 | $0.01045 |
| Opus 5 | $0.00046 | $0.00522 |
| Sonnet 5 | $0.00018 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
analyzing-zotero-research 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Zotero research
Requires the Zotero desktop app running locally with the Local API enabled (see the
searching-zotero-library skill for the setting). This skill works entirely from what's already
in the user's Zotero library — there is no external literature index (no Semantic Scholar or
citation-graph integration) to cross-reference against.
Hard constraint: don't reach outside the zotero MCP server to compensate. Do not call
WebSearch, WebFetch, or any other tool to look up papers, verify existence/citation details,
or check "what's out there" on the open web, and don't answer from general/trained knowledge of
the literature presented as verified fact. Doing that is exactly the Semantic Scholar-style
cross-referencing this MCP doesn't have, just done through a side door instead of the front door.
If a Zotero search or citation-count lookup looks unreliable, say so — don't quietly substitute a
web search to compensate (same rule searching-zotero-library applies to qmode="everything").
Never claim to find papers "missing from the field" — only ever "missing from your library" or "thin in your library." If the user explicitly asks what's missing from the field at large, not just their library, tell them plainly that this skill only sees their Zotero library and has no external index to check against. If they then want an actual open-web check, that's a distinct, explicit request outside this skill's scope — confirm with them before doing it, since it's a materially different kind of answer (unverified web results vs. their own library data), not a silent fallback for this skill to reach for on its own.
Start every analysis with a search_items or get_collection_items call to gather the working
set (see searching-zotero-library), then apply one of the patterns in
reference/patterns.md:
- Thematic clustering — group 10+ papers into themes with representative examples.
- Gap analysis — map what's well-covered vs. sparse (time periods, methods, regions, perspectives) within the library.
- Trajectory analysis — sort by date and trace how the user's reading on a topic evolved.
- Reading-list prioritization — tier a large result set into essential/important/ supplementary reading.
What ships with it
1 file 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.
- 11d ago First seen · 67 lines · 92 tokens per session scan A 2ceb3405db9b
analyzing-zotero-research is a skill published in the GitHub repository virtualarchitectures/Local-Zotero-MCP (0 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 1,045 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…