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-timeline-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-timeline-master)<a href="https://agentmods.dev/skills/miaoqichuan/new-litigation-visualization/mqc-timeline-master"><img src="https://agentmods.dev/badge/skills/miaoqichuan/new-litigation-visualization/mqc-timeline-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-timeline-master"><img src="https://agentmods.dev/badge/skills/miaoqichuan/new-litigation-visualization/mqc-timeline-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00269 | $0.06703 |
| Opus 5 | $0.00134 | $0.03351 |
| Sonnet 5 | $0.00054 | $0.01341 |
| Haiku 4.5 | $0.00027 | $0.00670 |
Grade A, and why
mqc-timeline-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 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新诉讼可视化 · 时间轴大师
时间轴大师,用数学,画准一张时间轴。
它替你解决的那件事
律师手上的材料是散的。一份判决书、几份合同、一叠证据目录、一段微信记录、 几张手机拍的照片,时间散落在其中。要把这些变成一张能交出去的图,难的从来不是画, 是两件事:该上图的事有没有抽全,抽全了排不排得下。
这个模块把这两件事分开做。前半段读材料,判断哪一句写的是已经发生的事实,把它们 归成事项;后半段接过这份清单,用纸张的物理尺寸算出每一个模块该摆在哪里、能有多宽、 能写多少字。两段之间只交接一个数,交接完就互不干涉。
材料怎么顺手怎么给:判决书、起诉状、答辩状、代理意见、合同、证据目录、银行与 支付宝流水、微信聊天记录、扫描件、手机照片,甚至一段口述。不必先整理,不必改格式, 也不必自己先画一张。没有文字层的扫描件与照片同样读得出来,做法是先逐页探测可读 字符数,再按 150 DPI 栅格化,然后逐页看图;交付时会声明哪几份出自读图,那几项请你 自己回原件复核一遍。
为什么能画准:位置、尺寸、容量全部是算出来的
一张 A4 有多宽是定死的。绘图宽 958 px,来自 A4 横版的 1070 减去两侧各 56 的留白。 这个数不由人改,后面所有的数都从它推出来。
推的顺序是一环扣一环的。时间轴上有几个时点,轴就被分成几段,每一段的长度决定了模块 落在哪里;位置定住,才知道相邻两个模块之间还剩多少空;剩多少空,决定一个模块能有 多宽;宽度定了,才知道这个模块能写几个字。所以先定位置,再定尺寸,最后才定能写 多少字,不能倒过来。
这些数不是查表得来的,换一份材料就换一组。编号型的卡宽由事项数压出来:八个事项时 189 px、十二个时 121 px、十六个时 96 px,卡片跟着变矮变窄,列距也从 110 收到 58。 日期型不一样,它的卡宽固定 214 px,因为时点多了是轴上挤、不是卡片变窄,正文至多 六行、约 84 字。期间型更特别,它的容量不是一个数而是每段各一个,条身长度由那一段的 真实天数决定,同一张图上各段差别可以从一个字到三十九个字。
放得下几个模块,同样是算的。第一道是一条不等式:
模块宽 × n ≤ 绘图宽 × 层数
全部模块的横向总宽不许超过绘图宽乘层数。它抓的是逐字段比对抓不住的那一类错,也就是 每个数看着都对、合起来却自相矛盾。
参数交出来之后还有第二道,用一组恒成立的关系把它验算一遍:
图宽 = 2 · 边距 + (n−1) · 列距 + 最小模块宽
等式两边只要差 0.5 像素就当场报错,并指名是哪一处尺寸算漏了。四项、八项、十二项、 十六项、二十项五档实测,差全部是 0.00。这一列不是差不多,是精确相等。
交接的顺序也是定死的:前端交出事项清单,后端按这一档的几何算出每个模块能写多少字, 把这个数交回去,前端再按这个数把字写到位。反过来先写好再排,就只剩两条路, 把字截掉或者把版面挤坏。
抽事实那一段没有公式可用。哪一句是事实、哪几句属于同一件事,是读懂内容之后的判断, 正则拿不到(试过一版按日期与文书名切分的正则切割器,在真材料上切出三组同名、一组 吞掉六成句子)。所以那一段交给模型做,代价是每一条判断都要能对回原句去核。
图上的字,回得去原句
卡片上每一段文字,都必须是原句删掉一些字之后剩下的样子。以原句「2021年3月5日, 双方签订设备采购合同」为例:写成「双方签订设备采购合同」通过;写成「双方签署」 换了词,拦住;写成「设备采购合同由双方签订」调了词序,拦住;补一个原句没有的字, 同样拦住。所以图上的每一句都指得回材料里的哪一句。
不进主轴的有三类:合同条款是约定,诉请是主张,付款计划是承诺。要画到期未付, 材料里得另有记载,比如一笔付款回单、一份催告函、一次对账。它不评价证据, 不认定事实,不给法律意见。
三种形态,由材料的性质定
编号型(numbered_point_timeline)的轴上距离只表先后,等距排开。时点密集、或者
没有精确日期时用它。它是阶梯的底,永远画得出。
日期型(dated_point_timeline)的轴按等长单位格铺开,距离本身在说话。时效届满与
起诉之间隔了多久、催告之后沉默了多久,这一类论点不在事情本身、在事情之间的距离上。
只有日期型能让空白成为证据。
期间型(proportional_gantt)把几段有长度的期间画成条,条长与重叠位置就是主张。
诉讼时效、保证期间、借款与计息起止、工期顺延与停工、租赁期、代持期,都属于这一档。
它还能同时承载时点,落在轴上画成虚线竖线加标注,所以不必另造一种混合型。
形态不由人选。判定顺序是期间型、日期型、编号型,材料的性质满足哪一档的硬条件就走 哪一档。
What ships with it
60 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.
- assets/longform/01-mathematics.png 1115 KB
- assets/longform/01-mathematics.svg 30 KB
- assets/longform/02-exact.png 1022 KB
- assets/longform/02-exact.svg 25 KB
- assets/longform/03-the-figure.png 1861 KB
- assets/longform/03-the-figure.svg 130 KB
- assets/screenshots/timeline-example.png 124 KB
- assets/screenshots/timeline-example.svg 5.5 KB
- AUTHOR.md 2.9 KB
- CHANGELOG.md 9.6 KB
- docs/adr/0001-rasterise-not-ocr.md 3.1 KB
- docs/adr/0002-transcript-as-material.md 3.4 KB
- docs/adr/0003-lane-labels-certain-only.md 2.9 KB
- docs/adr/0004-promises-are-not-facts.md 2.7 KB
- docs/adr/0005-lane-relation-field.md 3.2 KB
- docs/adr/0006-no-a11y-contract.md 3.0 KB
- docs/adr/0007-guards-for-errs-only.md 3.2 KB
- docs/adr/0008-drawio-no-lane-labels.md 3.7 KB
- docs/adr/README.md 3.3 KB
- examples/dated-limitation.json 5.0 KB
- examples/dated-proportional.json 13 KB
- examples/gantt-periods.json 3.2 KB
- examples/numbered-multiband.json 13 KB
- examples/stress-two-sides.json 25 KB
- examples/two-sides-actors.json 15 KB
- examples/two-sides-numbered.json 14 KB
- examples/vertical-single-column.json 14 KB
- HANDOVER.md 61 KB
- README.md 11 KB
- references/front-end.md 26 KB
- references/layout-constraints.md 51 KB
- references/model-steps.md 6.4 KB
- references/troubleshooting.md 6.6 KB
- RELAY-1-overview.md 7.7 KB
- RELAY-2-mapping.md 20 KB
- RELAY-3-retrospective.md 14 KB
- schemas/semantic-map.schema.json 20 KB
- scripts/capacity.py 24 KB runs code
- scripts/check_model_output.py 48 KB runs code
- scripts/export_formats.py 8.8 KB runs code
- scripts/feasible.py 23 KB runs code
- scripts/geom.py 19 KB runs code
- scripts/ingest.py 5.4 KB runs code
- scripts/paginate.py 8.3 KB runs code
- scripts/paper.py 11 KB runs code
- scripts/pick.py 12 KB runs code
- scripts/pipeline.py 74 KB runs code
- scripts/propose_layout.py 11 KB runs code
- scripts/read_image.py 8.0 KB runs code
- scripts/read_source.py 20 KB runs code
- scripts/render_dated_v2.py 26 KB runs code
- scripts/render_figure.py 9.5 KB runs code
- scripts/render_multiband.py 50 KB runs code
- scripts/render_spans_v2.py 37 KB runs code
- scripts/render_vcolumns.py 22 KB runs code
- scripts/render_vertical.py 11 KB runs code
- scripts/trace_index.js 6.8 KB runs code
- scripts/validate_map.py 17 KB runs code
- tests/check_anonymised.py 9.2 KB runs code
- tests/fixtures/judgment-no-heading.txt 1.0 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.
- 11d ago First seen · 384 lines · 269 tokens per session scan A 76d8c38e6ef9
mqc-timeline-master is a skill published in the GitHub repository MiaoQichuan/new-litigation-visualization (55 stars, last pushed 19d ago), licensed MIT. It adds 269 tokens to every session and 6,703 once invoked, about $0.0013 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
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
fill-icmje-coi
Batch-generate per-author ICMJE Conflict of Interest Disclosure Forms (coidisclosure.docx) for manuscript submission. Pre-fills all 13 disclosure items as "☒ None" + final certification ☒ using a synthetic seed template shipped with the skill, then clones the seed per author with Date, Name, and Manuscript Title…
law-to-markdown
A legal-document conversion skill for turning PDF, Word, or plain-text regulations into structured Markdown. Markdown is a text format that uses simple symbols for headings and lists.
cowork-data-room-builder
Prepare YOUR data room for a fundraise, acquisition, or bank diligence -- builds the checklist for your deal stage, sweeps your folders for what you already have, produces a gap report, and organizes everything into the structure buyers and investors expect. The sell-side complement to cowork-deal-room.
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
kr-patent-full-workflow
A coordinator for writing a Korean patent specification from start to finish. It guides the work through invention interviews, claim preparation, technical details, consistency checks, and final DOCX output.