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 MiaoQichuan/new-litigation-visualization --skill mqc-legal-courseware-mastergit clone --depth 1 https://github.com/MiaoQichuan/new-litigation-visualizationWrote 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/miaoqichuan/new-litigation-visualization/mqc-legal-courseware-master)<a href="https://agentmods.dev/skills/miaoqichuan/new-litigation-visualization/mqc-legal-courseware-master"><img src="https://agentmods.dev/badge/skills/miaoqichuan/new-litigation-visualization/mqc-legal-courseware-master/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/miaoqichuan/new-litigation-visualization/mqc-legal-courseware-master"><img src="https://agentmods.dev/badge/skills/miaoqichuan/new-litigation-visualization/mqc-legal-courseware-master.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 | $0.00414 | $0.05892 |
| Opus 5.5 | $0.00166 | $0.02357 |
| Sonnet 5.5 | $0.00083 | $0.01178 |
| Haiku 4.5 | $0.00041 | $0.00589 |
Grade A, and why
mqc-legal-courseware-master 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 yesterday.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
法律课件大师（V7）
我们不跟 PowerPoint 比编辑能力。 比的是：法律人从一堆材料到一套像样的课件有多快，内容靠不靠得住。
做法是「骨架定死、内容交给 AI」：网格、风格、卡片样子、核对规则是固定的；用户说一句想法，AI 按法律场景 生成模块和页面，用户在磁吸界面上拖一拖、改一改，再导出。自由度在想法上，不在像素上。
和其他模块一样：模型只写 JSON（deck.json），几何由脚本算，导出后回读审计。 V7 只读 V1–V6，不改它们。
〇、用户怎么开口
句式：用法律课件大师，把【材料 / 想法】做成【几页】课件，在【场合】讲给【谁】，用【奇川风 / 歸藏风】。
| 用户要的 | 怎么做 |
|---|---|
| 「打开编辑器，我自己排」 | 第三节：开编辑器，并在后台等编辑器里的 AI 请求 |
| 一套类案课件 | 先用 V6 出图表说明放进 assets/，再写 deck.json（「类案研究」组合） |
| 案情汇报 / 庭前准备 | 用 V2 / V3 / V5 出 SVG 放进 assets/（V3 加 --shape wide 出横版，竖版放进课件页字太小），配争议焦点卡、风险提示卡 |
| 法条解读 / 普法讲座 | 法条卡（照录原文）+ 要点 + 风险提示；案例复盘用案例卡 + 裁判要旨卡 |
| 律所推介 / 律师介绍 | 先填律所名片（第五节），一键生成介绍页，再按场合润色 |
〇之二、运行与交付须知
- 命令从哪里跑。 本文件里写的
scripts/…、examples/…、references/…都在本技能目录下（这份 SKILL.md 所在的文件夹）。 请在用户的工作目录里运行，命令写成python3 <本技能目录>/scripts/…，不要先cd进本技能目录；脚本自己找得到依赖，在哪里调用都一样。 - 产物放哪里。 用户的材料、JSON 与产物一律放在用户的工作目录，不要写进本技能目录：插件更新时那里会被整个替换，用户也找不到。
build.py 课件名 --new在当前目录建课件文件夹；课件文件夹放在用户的工作目录。 - 照实交付。 脚本打印的核对清单照原样转告用户；没有真的打开看过图片，就不要说「看过了、效果没问题」。
一、课件目录
my-deck/
deck.json 课件说明（编辑器自动保存；AI 与模型也直接写它）
assets/ 素材：V6 图表说明 *.json、V1–V5 的图 *.svg
brand/ （可选）这套课件专用的律所名片；没有就用本机公共名片 ~/.mqc-nlv/brand/
ai/ 编辑器发给 AI 的请求（requests.json）
exports/ 导出的 PPTX
目录名与文件名用 ASCII：Windows 解压 ZIP 时中文文件名会失败。内容、标题用中文没问题。
新建：python3 scripts/build.py my-deck --new --title "民间借贷类案研究"
二、磁吸网格与卡片
一页 1280×720，12 栏 × 6 行，页边距左右 48、上下 56，模块之间一律留 16px。每个模块写它占哪几格：
x（第几栏，0 起）、y（第几行）、w、h，都是整数。不写像素、颜色、字号——由网格和风格决定。
法律内容卡
| type | 卡片 | 字段 | 最小 |
|---|---|---|---|
| statute | 法条 | law 法律名称、article 条款、text 条文原文 |
4×2 |
| holding | 裁判要旨 | text 要旨原文、court 法院、case_no 案号（至少写一个出处） |
4×2 |
| case | 案例 | case_no（必填）、court、cause 案由、heading、result 裁判结果、point 要点 |
3×2 |
| issue | 争议焦点 | heading、text；按阅读顺序自动标「争议焦点一、二、三」 |
3×2 |
| risk | 风险提示 | heading、text |
3×2 |
| evidence | 证据 | heading、items（一行一份：「名称——证明目的」，自动标证据 1、2、3） |
5×2 |
What ships with it
38 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.
- CHANGELOG.md 24 KB
- docs/adr/0001-magnetic-slots-and-editable-pptx.md 2.0 KB
- docs/adr/0002-magnetic-grid-learned-from-m3e-canvas.md 3.5 KB
- docs/adr/0003-legal-vertical-and-ai-through-conversation.md 2.2 KB
- docs/adr/0004-firm-style-from-template.md 2.2 KB
- docs/adr/0005-several-writers-one-deck.md 3.0 KB
- examples/demo/assets/bar-filings.json 894 B
- examples/demo/assets/ribbon-funds.json 1.7 KB
- examples/demo/assets/sankey-appeals.json 1.3 KB
- examples/demo/assets/v3-relation.svg 6.8 KB
- examples/demo/assets/waffle-outcomes.json 579 B
- examples/demo/brand/brand.json 1.2 KB
- examples/demo/brand/logo.png 4.2 KB
- examples/demo/deck.json 8.5 KB
- README.md 1.4 KB
- references/deck-format.md 9.7 KB
- scripts/adapt.py 5.5 KB runs code
- scripts/ai.py 17 KB runs code
- scripts/brand.py 14 KB runs code
- scripts/build.py 4.7 KB runs code
- scripts/deck.py 62 KB runs code
- scripts/export.py 28 KB runs code
- scripts/firm_style.py 12 KB runs code
- scripts/frame.py 11 KB runs code
- scripts/grid.py 28 KB runs code
- scripts/notes.py 8.9 KB runs code
- scripts/paths.py 2.1 KB runs code
- scripts/prov.py 4.1 KB runs code
- scripts/safewrite.py 3.4 KB runs code
- scripts/studio.py 31 KB runs code
- scripts/svgimport.py 44 KB runs code
- scripts/template_read.py 29 KB runs code
- tests/fixtures/v2-numbered.svg 13 KB
- tests/fixtures/v4-brief.svg 12 KB
- tests/golden/slides.json 972 B
- tests/run_checks.py 134 KB runs code
- web/grid.js 6.7 KB runs code
- web/studio.html 139 KB
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.
- yesterday First seen · 214 lines · 414 tokens per session scan A 6e46eba292aa
mqc-legal-courseware-master is a skill published in the GitHub repository MiaoQichuan/new-litigation-visualization (133 stars, last pushed yesterday), licensed MIT. It adds 414 tokens to every session and 5,892 once invoked, about $0.0017 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 2026-10-15.
Other skills, from other repositories
bar-prep-questions-bossmann007
Questões de preparação para o Exame de Ordem (OAB) — 1ª fase (objetiva) ou 2ª fase (peça/discursiva), com foco nas matérias fracas do aluno. Rastreia erros e volta aos padrões. Use quando o usuário disser "prova da OAB", "questões de 1ª fase", "peça prática", ou "me teste pra Ordem".
irac-practice-bossmann007
Corrige uma peça/parecer no método IRAC (ou estrutura equivalente) quanto a estrutura, identificação de teses, precisão de fundamentação, profundidade de análise e organização. NÃO reescreve o texto nem mostra resposta-modelo; rastreia padrões entre sessões. Use quando o usuário disser "corrige meu IRAC", "avalia meu…
case-brief
Resume um julgado/acórdão no seu formato preferido. Em modo sabatina, faz o aluno afirmar a tese/ementa primeiro. Use quando o usuário disser "resume [julgado]", "qual a tese de", "resumo de acórdão", ou colar o inteiro teor de uma decisão.
common-law-contract-formation-consideration
Anwalt oder Mandant will Vertragsschluss-Grundlagen des Common Law verstehen: offer acceptance consideration deed promissory estoppel UCC. Anwendungsfall Transaktionsvertrag oder NDA mit UK/US-Gegenpartei. Prüfraster Consideration-Prüfung Deed-Anforderungen Estoppel-Risiko UCC-Varianten. Output Erklärung…
common-law-simulation-negotiation
Anwalt oder Mandant will UK/US-Vertragsverhandlung oder Mandantengespraech simulieren und False-Friends-Lernkurve absolvieren. Prüfraster Verhandlungs-Simulation Issue-List-Erstellung Mandanten-Erklärung. Output Simulations-Szenario Verhandlungs-Script Lern-Feedback. Abgrenzung zu common-law-quality-gate (Qualitaet)…
common-law-interpretation-precedent
Deutscher Anwalt liest UK oder US-Gerichtsentscheidung und versteht Praezedenzfall-Logik nicht: ratio decidendi obiter dictum stare decisis Vertragsauslegung. Normen UK Supreme Court Rules US Federal Rules. Prüfraster Ratio-obiter-Unterscheidung Binding-Persuasive-Abgrenzung Auslegungs-Methode. Output…