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 XWang20/semanticscholar-MCP-Server --skill scholarqa-researchgit clone --depth 1 https://github.com/XWang20/semanticscholar-MCP-ServerWrote 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/xwang20/semanticscholar-mcp-server/scholarqa-research)<a href="https://agentmods.dev/skills/xwang20/semanticscholar-mcp-server/scholarqa-research"><img src="https://agentmods.dev/badge/skills/xwang20/semanticscholar-mcp-server/scholarqa-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/xwang20/semanticscholar-mcp-server/scholarqa-research"><img src="https://agentmods.dev/badge/skills/xwang20/semanticscholar-mcp-server/scholarqa-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 | $0.00122 | $0.02110 |
| Opus 5.5 | $0.00049 | $0.00844 |
| Sonnet 5.5 | $0.00024 | $0.00422 |
| Haiku 4.5 | $0.00012 | $0.00211 |
Grade A, and why
scholarqa-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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScholarQA Research
Goal
Produce a concise, evidence-grounded answer before writing a broad narrative. Retrieve scholarly evidence with Semantic Scholar, map each material claim to verified papers, expose disagreements and evidence limits, and never invent citations.
For literature questions, treat this as a Semantic Scholar MCP/CLI adaptation of the ScholarQA workflow, not as a wrapper around or behavioral replica of ai2-scholarqa-lib. For research ideation, preserve Scideator's shared faceted representation and human-directed loop; do not reduce it to generic brainstorming.
Provenance boundary
Read references/provenance.md before modifying or redistributing this skill, and whenever the user asks how its workflow was derived.
- Treat this skill as an independent Semantic Scholar MCP/CLI adaptation, not an official Ai2 Scholar QA release or an Allen Institute for AI product.
- Credit the Ai2 Scholar QA paper and official
allenai/ai2-scholarqa-librepository when describing the evidence-QA design. No upstream ScholarQA code is bundled or imported. - Credit the Scideator paper for the facet-ideation workflow and published prompt pseudocode. Keep published specifications distinct from adapter decisions.
- Do not add these methodology citations mechanically to ordinary literature answers; cite the papers that support the user's requested claims. Include methodology citations when discussing, comparing, publishing, or redistributing the workflow itself.
Select mode
- Evidence QA: Answer, review, compare, trace, or audit the literature. Follow the main workflow below.
- Facet ideation: Generate research directions from seed papers, explore analogies, or iteratively refine an idea. Read references/scideator-workflow.md, references/scideator-prompts.md, and references/retrieval.md completely before acting.
- Novelty check: Assess a supplied idea against retrieved literature. Read the novelty sections of both Scideator references, load references/scideator-novelty-examples.md, and follow references/retrieval.md. Judge only relative to the retrieved evidence; never certify global novelty.
- Hybrid: Use Evidence QA to establish the literature first, then enter Facet ideation. Keep evidence claims and generated proposals visibly separate.
What ships with it
7 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.
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.
- 1mo ago First seen · 133 lines · 122 tokens per session scan A 02505afa02e3
scholarqa-research is a skill published in the GitHub repository XWang20/semanticscholar-MCP-Server (3 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 2,110 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
deep-research
Conduct evidence-grounded literature reviews and technical field investigations with Scholar MCP. Use for iterative academic search, multi-paper claim verification, frontier mapping, benchmark comparison, or citation lineage tracing. Route ordinary paper lookup directly to Scholar MCP.
mitiq-error-mitigation
A local experiment runner for testing four ways to reduce errors in sampled quantum circuits: zero-noise extrapolation, readout correction, probabilistic error cancellation, and Clifford data regression. It compares noisy and mitigated results under the same sampling budget.
quantum-ground-state
A narrowly defined quantum solver for the ground-state energy of a two-quantum-bit Pauli Hamiltonian in a specified one-excitation sector. It uses a noiseless statevector VQE and checks the result against an exact calculation; VQE is a method that searches for a low-energy quantum state.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-amplitude-amplification
A local Qiskit workflow for amplitude amplification, a quantum method that increases the chance of measuring selected answers. It can explain the method, build a circuit, or run calculations on a simulator.
quantum-heat-1d
A runnable open-source implementation of the one-dimensional heat equation, which describes how temperature spreads along a line over time. It uses a quantum-circuit method that rewrites the heat problem into a form suitable for simulation.