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 agentmods add skills/zju-real/easel/paper-explainernpx skills add ZJU-REAL/Easel --skill paper-explainergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/paper-explainer)<a href="https://agentmods.dev/skills/zju-real/easel/paper-explainer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/paper-explainer.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.02830 |
| Opus 5 | $0.00057 | $0.01415 |
| Sonnet 5 | $0.00023 | $0.00566 |
| Haiku 4.5 | $0.00011 | $0.00283 |
Grade A, and why
paper-explainer 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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
科研论文解读（论文 → 视频 / 图文）
把一篇论文讲成普通人/同行都爱看的视频号视频或图文。核心中间产物是一份 结构化 asset library（一次解析+提炼，视频与图文两条产线共用，不重复调 LLM）。 确定性 IO（拉论文/解析 PDF/骨架）走
scripts/paper_ingest.py；提炼与分镜脚本由你 LLM 完成——这是本 SKILL 的核心价值。
视频转图文（反向）见 video-to-article；纯格式转换见 doc-convert； 只做图表见 chart-visualization / infographic；发视频号见 skill-channels-upload。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 论文 | 是 | arxiv id（2401.12345）/ arxiv 链接 / 本地 PDF 路径（没给就问） |
| 目标形态 | 否 | 视频（默认，视频号/B站）/ 图文（知乎/公众号）/ 两者都要 |
| 视频画幅 | 视频时必填 | 用户或上游任务未明确横版/竖版（或 16:9/9:16/具体分辨率）时，进入视频制作前必须追问并等确认；不得按平台、Profile 或默认值静默推断，已明确则不重复问 |
| 受众深度 | 否 | 大众科普（默认）/ 同行向（更专业） |
| 时长 | 否 | 视频默认 2–4 分钟（视频号中视频） |
产物结构（outputs/论文简称/）
article.md 图文版（知乎/公众号）
final.mp4 成片
assets/ paper.pdf / parsed/ / asset-library.json / script.md
slide-plan.json 结构化分页（页面唯一输入，口播与屏幕文字分离）
slides/ 稳定渲染的逐页 PNG + HTML + audit report
slides-contact-sheet.jpg 整套视觉复核图
脚本（相对项目根）：paper_ingest.py（解析）+ render_slides.py（分页校验/渲染/审计）。
执行步骤
1. 取原文 + 解析
- 环境自检：
python skills/openclaw/paper-explainer/scripts/paper_ingest.py check（看 pdfplumber / MinerU token / 代理；缺 pdfplumber 则pip install pdfplumber）。 - 拉论文：
paper_ingest.py fetch --paper <id/url/本地pdf> -o outputs/论文简称/assets/paper.pdf。 - 解析：
paper_ingest.py parse -i outputs/论文简称/assets/paper.pdf -o outputs/论文简称/assets/parsed/（有MINERU_API_TOKEN走 MinerU 含公式/图表结构化，否则 pdfplumber 纯文本 + 尽力抽图）。
2. 结构化提炼（你来做，核心）
- 生成骨架：
paper_ingest.py skeleton -o outputs/论文简称/assets/asset-library.json。 - 读
assets/parsed/content.*，按references/paper-distill-schema.md填满assets/asset-library.json：one_liner（一句话讲清干了啥）、problem/prior_gap、contributions（≤3 条）、method（含通俗类比 analogy）、key_figures（挑 2–4 张关键图，每张写plain大白话解释）、results（含关键数字）、limitations、takeaway、terms（术语通俗表）。 通俗化方法见references/explain-methodology.md（公式/图表→大白话、类比法、避免堆术语）。 - 忠于原文：不夸大、不编造结论；拿不准的地方标注，别臆测（学术内容错了会被同行抓）。
What ships with it
10 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.
- EASEL-META.md 2.1 KB
- references/explain-methodology.md 3.2 KB
- references/paper-distill-schema.md 2.7 KB
- references/platform-adapt.md 2.3 KB
- references/slide-design.md 12 KB
- references/slide-plan.example.json 2.9 KB
- references/slide-plan.style-transfer.example.json 1.8 KB
- references/video-storyboard.md 3.1 KB
- scripts/paper_ingest.py 19 KB runs code
- scripts/render_slides.py 49 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.
- 6d ago First seen · 102 lines · 114 tokens per session scan A 5ccf7747707e
paper-explainer is a skill published in the GitHub repository ZJU-REAL/Easel (352 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 2,830 once invoked, about $0.0006 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
interactive-explainer
Use when someone wants an educational explainer with a host and characters — history or science shorts with dialogue, not voiceover-only B-roll.
hidden-talents
Interview you in depth to surface overlooked or suppressed talents and write your Personal Talent Manual.
socratic
Diagnose a confusion Socratically, one question at a time, until the question actually worth answering surfaces — then answer that one.
two-layer-explain
Explain a concept twice — for a newcomer and for an expert — then bridge the two layers, flag the likely misunderstandings, and set three check questions.
deconstruct
Reverse-engineer why a finished piece of work succeeds and extract what transfers to your own — rules, a checklist, and a first exercise.
project-scaffolder
Use when a learning plan requires runnable chapter files, a multi-lesson coding course, a project-based route, or a workspace the learner will open in an editor.