Documents skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

vision

Query images with a local Ollama vision model without loading the image into the main agent context. Use when you need to describe a screenshot, check whether rendered content is present, detect overlapping elements, or ask any visual question about a PNG/JPEG/WebP file. Requires Ollama running locally with the Gemma 4 multimodal model (`gemma4` on Ollama). Script: .agents/skills/vision/scripts/ask.py. Trigger phrases: "describe image", "what does this screenshot show", "does the canvas contain content", "check screenshot visually", "look at this image", "any overlapping elements", "vision query".

2.56k repo starsObserved in 1 repos
Documents

download-attachment

Download files from URLs to the Obsidian attachments folder and organize them with descriptive names. Use when the user provides URLs to download, asks to save files from the web, or wants to add web content as attachments.

2.54k repo starsObserved in 1 repos
Documents

brain-to-docs

Use when the user wants to extract project vision, decisions, and preferences from his head into clear documentation (README + ADRs) through a back-and-forth Q&A loop. Triggers on "brain-to-docs", "build out the docs", "extract the vision", "let's document this project".

2.54k repo starsObserved in 1 repos
Documents

learnprompt-single-mdx

Create or rewrite exactly one LearnPrompt Starlight MDX tutorial to the repository's golden-sample standard, with bottom-of-page auditable sources instead of SourceCard, a research pack, evidence ledger, reproducible showcase, independent review, quality score, and successful site build. Use for one LearnPrompt article, tutorial, chapter, or MDX page; in batch goals, invoke once per topic in an isolated task.

2.53k repo starsObserved in 1 repos
Documents

make-latex-model

当用户明确要求“LaTeX 模板优化”“样式参数对齐”“像素级比对”“make-latex-model”或旧写法“make_latex_model”,或要把 ChineseResearchLaTeX 里的某个项目做成高质量模板时使用。适配 NSFC / paper / thesis / cv 四条产品线;先依据 packages/ 与 projects/ 的真实分层判断改项目层还是公共包,再用各产品线官方构建入口验收。若必须修改 packages 下公共包,需先生成受影响模板回归计划并完成相关回归;NSFC 专项工具仅在明确属于 NSFC 参数对齐场景时按需使用。

2.52k repo starsObserved in 1 repos
Documents

nsfc-code

根据 NSFC 标书正文内容,结合申请代码推荐库,为你给出 5 组申请代码1/2(主/次)推荐与理由;输出到 NSFC-CODE-vYYYYMMDDHHmm.md(只读,不修改标书)

2.52k repo starsObserved in 1 repos
Documents

nsfc-qc

当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制:并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等,最终输出标准化 QC 报告;中间文件默认归档到 `project_root/.bensz-api/skills/nsfc-qc/{yyyy-mm-dd-hh-mm}/`,并兼容 legacy `.nsfc-qc/` 读取/清理。

2.52k repo starsObserved in 1 repos
Documents

nsfc-ref-alignment

检查 NSFC 标书正文引用与参考文献的一致性与真实性风险(只读):核查 bibkey 是否存在、BibTeX 字段与 DOI 等格式问题,并生成结构化输入供宿主 AI 逐条评估“正文表述是否真的在引用该文献”;默认仅输出审核报告,不直接修改标书或 .bib(除非用户明确要求)。

2.52k repo starsObserved in 1 repos
Documents

nsfc-reviewers

当用户明确要求"评审国自然标书"、"模拟专家评审"、"审阅 NSFC 申请书"时使用。模拟领域专家视角对 NSFC 标书进行多维度评审,输出分级问题与可执行修改建议。⚠️ 不适用:用户只是想写/改标书某个章节(应使用 nsfc-*-writer 系列技能)、只是想了解评审标准(应直接回答)、没有明确"评审/审阅"意图。

2.52k repo starsObserved in 1 repos
Documents

paper-explain-figures

解读论文 Figure 的含义并输出一份“教会人类如何读图”的高可读性 Markdown 报告;支持输入 1 个或多个 figure 文件绝对路径与人工解读,自动尝试从图附近检索生成该图的源代码,并采用类似 parallel-vibe 的方式通过 `codex exec`/`claude -p` 以进程级隔离解读每张图(并发上限默认 3,可在 config.yaml 调整)。⚠️ 不适用:用户只是想改图尺寸/裁剪/改格式;或要求直接修改图片/源代码(本 skill 对图片与源代码全程只读,严禁修改)。

2.52k repo starsObserved in 1 repos
Documents