Borrowing it
Nothing to install: this file belongs to gjjisadog/scipdf-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gjjisadog/scipdf-mcp/main/.grok/skills/scipdf/SKILL.mdgit clone --depth 1 https://github.com/gjjisadog/scipdf-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/gjjisadog/scipdf-mcp/scipdf)<a href="https://agentmods.dev/skills/gjjisadog/scipdf-mcp/scipdf"><img src="https://agentmods.dev/badge/skills/gjjisadog/scipdf-mcp/scipdf/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/gjjisadog/scipdf-mcp/scipdf"><img src="https://agentmods.dev/badge/skills/gjjisadog/scipdf-mcp/scipdf.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 | $0.00075 | $0.01229 |
| Opus 5 | $0.00037 | $0.00615 |
| Sonnet 5 | $0.00015 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
scipdf 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scipdf — 论文 PDF 本地下载工作流
配套:MCP scipdf + 可选 CLI node …/scipdf-mcp/dist/index.js。
目标:用户要论文 → DOI → 本地下载 → 返回 path(+ 可选引用格式)。
下载顺序(MCP 内部):
- 可选 Unpaywall OA:仅当用户同时配置了
SCIPDF_UNPAYWALL_EMAIL且SCIPDF_PREFER_OA=true时,才在 Sci-Hub 之前尝试合法 OA - 默认:pdfHosts → Sci-Hub 镜像(始终主路径,无需额外配置)
- pdfHosts 默认:
https://sci.bban.top/pdf/ - 镜像默认约 15 个(含 ren/red/ee/st/ru/box/se、sidesgame、vg、usualwant、hkvisa、al、mksa.top、pismin、sci-hub.in 等)
- 完整列表见仓库
src/config.ts/config.example.json/ README
- pdfHosts 默认:
未配置邮箱 / 未开 PREFER_OA → 行为与纯 Sci-Hub 一致。不要要求用户必须配邮箱。
镜像异常时用 check_mirrors(可 force_refresh: true);可用 SCIPDF_MIRRORS / SCIPDF_PDF_HOSTS 覆盖。
前置条件 / 诊断
- 工具列表应有
download_paper(MCP 名scipdf)。 - 若没有 MCP 工具:
- 提示用户:重启客户端;或运行
cd <repo> && bash install.sh/bash install.sh --update - 不要假装已下载。
- 若用户本机有仓库,可退路执行 CLI:
node /path/to/scipdf-mcp/dist/index.js download "<query>"
- 提示用户:重启客户端;或运行
完整工作流
用户:标题 / DOI / 链接 / 文献列表 / bib
→ ① 收集查询
→ ② resolve_doi(必要时)
→ ③ download_paper / download_papers
→ ④ 汇报 path + DOI + 引用;失败报 code
① 收集
优先级:DOI → URL → 标题 → 引用串 → bib/ris 整段(用 parse_references)。
② 解析 DOI
| 输入 | 动作 |
|---|---|
| DOI | 直接 download_paper |
| 标题 | resolve_doi 或直接 download_paper(内部会解析) |
失败 DOI_NOT_FOUND |
看 candidates;或 web 检索后用明确 DOI 再下 |
AMBIGUOUS_DOI |
列出 candidates 让用户选,不要静默下错篇 |
③ 下载
download_paper:
query: "..."
query_type: auto|doi|title|url|citation
force: false
批量:
download_papers:
queries: ["10.a/b", "title...", "@article{...}"]
- 已存在文件会返回
cached: true+ path(不必当错误)。 - 镜像异常:
check_mirrors(可force_refresh: true)。
④ 汇报(必填字段)
成功:
- 标题、DOI、path、bytes、
cached、可选citation.apa/gbt/bibtex
失败:
code(如DOI_NOT_FOUND/MIRROR_BLOCKED/ALL_SOURCES_FAILED/PDF_NOT_IN_DB)error原文candidates(若有)
禁止编造 path。
失败重试(固定策略)
- 标题 →
download_paper失败且DOI_NOT_FOUND - 用
resolve_doi或 candidates / 公开网页确认 DOI download_paper+query_type: "doi"- 仍失败 →
check_mirrors,把 code 给用户,不无限重试
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 · 124 lines · 75 tokens per session scan A 53d2ded0c93a
scipdf is a skill published in the GitHub repository gjjisadog/scipdf-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,229 once invoked, about $0.0004 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
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.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.