xuzhougeng/wisp-science is a local-first desktop workbench for scientific research that combines AI assistants with Python and R computing, literature search, scientific databases, and remote runtimes. Researchers use it to run analyses, manage project artifacts, and preserve evidence and decisions on their own machines. Its catalogue skills and instruction extend the workbench’s reusable agent workflows.
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 xuzhougeng/wisp-science --skill word-zotero-citationsgit clone --depth 1 https://github.com/xuzhougeng/wisp-scienceWrote 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/xuzhougeng/wisp-science/word-zotero-citations)<a href="https://agentmods.dev/skills/xuzhougeng/wisp-science/word-zotero-citations"><img src="https://agentmods.dev/badge/skills/xuzhougeng/wisp-science/word-zotero-citations/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/xuzhougeng/wisp-science/word-zotero-citations"><img src="https://agentmods.dev/badge/skills/xuzhougeng/wisp-science/word-zotero-citations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 16 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 145 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00090 | $0.03198 |
| Opus 5.5 | $0.00036 | $0.01279 |
| Sonnet 5.5 | $0.00018 | $0.00640 |
| Haiku 4.5 | $0.00009 | $0.00320 |
Grade A, and why
word-zotero-citations 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 2mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
14 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.
- assets/templates/offline-run-summary.md 1.3 KB
- evals/task-cases.json 3.8 KB
- evals/trigger-cases.json 2.8 KB
- references/contracts.md 5.6 KB
- references/implementation-map.md 4.2 KB
- references/live-refresh-protocol.md 3.4 KB
- references/live-run-recipe.md 6.6 KB
- references/recovery-and-rollback.md 3.3 KB
- references/verification-matrix.md 3.9 KB
- references/zotero-mcp-configuration.md 3.5 KB
- scripts/refresh_word_zotero.ps1 13 KB runs code
- scripts/run_live_workflow.py 22 KB runs code
- scripts/validate_word_zotero_ui.ps1 17 KB runs code
- scripts/verify_skill.py 8.1 KB runs code
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.
- 2mo ago First seen · 262 lines · 90 tokens per session scan A 495d3538f076
word-zotero-citations is a skill published in the GitHub repository xuzhougeng/wisp-science (1,058 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 90 tokens to every session and 3,198 once invoked, about $0.0004 per session on Opus 5.5. 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
docx-generation
Use when creating a Word DOCX report from Markdown, converting Markdown tables and lists to DOCX, or choosing a workflow for editing an existing DOCX while preserving its structure and styles. Use this workflow before running Markdown-to-DOCX shell commands. Includes report typography, table layout, a reusable…
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
paper-narrative
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.
scvi-tools
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…
self-awareness
Inspect Open-Science's JavaScript control REPL, discover managed Project files, Sessions, and Agent Frames, and safely feature-gate host. calls with host.capabilities(). Use when an Agent needs to discover available host APIs, locate an Artifact or Upload Version, diagnose a Session, or read a Frame transcript in the…