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 LazyAGI/LazyMind --skill sciverse-paper-searchgit clone --depth 1 https://github.com/LazyAGI/LazyMindWrote 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/lazyagi/lazymind/sciverse-paper-search)<a href="https://agentmods.dev/skills/lazyagi/lazymind/sciverse-paper-search"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/sciverse-paper-search/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/lazyagi/lazymind/sciverse-paper-search"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/sciverse-paper-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01465 |
| Opus 5 | $0.00034 | $0.00732 |
| Sonnet 5 | $0.00014 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
sciverse-paper-search 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sciverse Paper Search Skill
Overview
Use this skill when the user needs scientific literature retrieval, paper metadata screening, citation-ready evidence, or a research synthesis grounded in Sciverse search results.
This skill is adapted to the current LazyLLM SciverseSearch implementation. It must only rely on the currently supported tool capabilities:
sciverse_search.searchsciverse_search.meta_searchsciverse_search.meta_catalogsciverse_search.get_content
Do not assume Sciverse MCP tools, resource APIs, binary attachment downloads, figure/table downloads, DianShi, or SeqStudio capabilities are available unless the runtime explicitly exposes those tools.
When To Use
Use this skill for:
- Finding scientific papers on a research topic.
- Retrieving citable evidence snippets for a scientific question.
- Screening papers by year, venue, DOI, author, title, or metadata fields.
- Building paper lists for literature reviews.
- Reading fuller text for selected Sciverse results when
doc_idis available. - Producing cited summaries, comparisons, or evidence tables from Sciverse results.
Do not use this skill for:
- Downloading paper images, figures, tables, PDFs, or binary resources.
- Chemical retrosynthesis, molecule/reaction search, or DianShi workflows.
- Protein sequence/structure annotation or SeqStudio workflows.
- Claims that require full-text access when only abstracts or snippets are available.
Available Tool Capabilities
sciverse_search.search
Use this for normal Agent retrieval.
Recommended defaults:
query=<research question or paper topic>
topk=5
search_type="agentic"
include_content=true
Use search_type="agentic" when the user asks a natural-language scientific question and needs evidence passages.
Use search_type="meta" when the user mainly needs paper metadata. You may pass year_from and year_to for year constraints.
Current implementation notes:
topkis capped at 10.- Results are normalized to title, url, snippet, source, and
extra. extramay includedoc_id,doi,year,venue,authors,score,chunk_id,page_no,offset, andcontent.
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 · 217 lines · 68 tokens per session scan A 0e3ed67f67a5
sciverse-paper-search is a skill published in the GitHub repository LazyAGI/LazyMind (77 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 1,465 once invoked, about $0.0003 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
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via deriveoutlineprompt (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → render each panel with paneltask (loading figure-style), one at a time or…
paper-narrative
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. paperbriefprompt(abstract, captions) hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and…
figure-style
Publication-grade figure correctness and legibility rules. Load before drawing any plot and call applyfigurestyle() — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded…
fair-esm2
Embed proteins with Meta AI's ESM-2 (fair-esm package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.
borzoi
Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritising non-coding variants by predicted track delta.
esmfold2
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…