科研 Skill
最高法院案件材料整理
case-prep
Gathers the full document set for a US Supreme Court case and loads it onto the user’s reMarkable in a per-case folder. Use when prepping a SCOTUS case for a podcast, class, or article.
SKILL.md
SCOTUS case prep → reMarkable
Given a case name (and optionally a docket number), collect the canonical
reading set and upload it to the tablet under <Project>/<Case>/.
Hard rules
- Every uploaded document is a real PDF you actually downloaded. Verify
each file begins with
%PDFbefore uploading. Never hand-construct a document URL and assume it worked — fetch it and check. - Web-confirm the caption and docket number first. If the name is ambiguous (multiple granted cases, consolidated cases, common party names), confirm with the user before downloading the wrong case's briefs.
- Report gaps honestly. If a document isn't filed yet, isn't public, or can't be found, say so in the final manifest. Never substitute a look-alike document.
Step 1 — Resolve the case
- Web-search the case name to confirm the exact caption and Supreme Court
docket number (format
NN-NNN, e.g.24-316). Good confirming sources: supremecourt.gov, SCOTUSblog's case page, Oyez. - Note whether the case is consolidated with others (grab the lead docket; mention companions in the manifest).
- Note argument status: not yet argued / argued (transcript available) / decided.
Step 2 — Download documents (to the scratchpad, via curl)
Docket page (index of every filing, with PDF links):
https://www.supremecourt.gov/search.aspx?filename=/docket/docketfiles/html/public/<DOCKET>.html
Fetch it and extract the DocketPDF links. Entry text identifies each
filing ("Petition for a writ of certiorari filed", "Brief of petitioner",
"Brief amicus curiae of United States", etc.).
Default document set (in reading order — skip whatever doesn't exist yet; note it in the manifest):
| # | Document | Source |
|---|---|---|
| 00 | Questions presented | https://www.supremecourt.gov/qp/<TERM>-<5-digit-zero-padded-number>qp.pdf (e.g. docket 24-316 → 24-00316qp.pdf) |
| 01 | Lower-court opinion | CourtListener (below) |
| 02 | Cert petition | docket page |
| 03 | Brief in opposition | docket page |
| 04 | Cert-stage reply | docket page |
| 05 | Petitioner's merits brief | docket page |
| 06 | Respondent's merits brief | docket page |
| 07 | Merits reply brief | docket page |
| 08 | U.S. / SG amicus brief (if any, either stage) | docket page |
| 09 | Oral-argument transcript (if argued) | https://www.supremecourt.gov/oral_arguments/argument_transcripts/ — links follow .../argument_transcripts/<TERM>/<docket>_<suffix>.pdf; find the real link on the term's transcript index page |
Other amicus briefs: don't download them all by default (there can be dozens). Tell the user how many were filed and offer to add specific ones.
Lower-court opinion via CourtListener: search
https://www.courtlistener.com/api/rest/v4/search/?q=<case name>&court=<lower court id>
or the website search, matching the docket number / caption from the cert
petition (the petition's first pages identify the opinion below precisely).
Then resolve and download the PDF deterministically with the legal-research
skill's helper (prefers CourtListener's stored copy, falls back to the
court's own file, verifies %PDF magic before saving):
python3 ../legal-legal-research/cl_case_tools.py pdf cluster:<cluster_id> --out "01 Lower-court opinion.pdf"
(cluster_id comes from the search result; a reporter cite works too once
one exists). If no PDF is on CourtListener or the court's site, the cert
petition's appendix contains the opinion below — flag that as the fallback
rather than uploading something unverified.
Use a browser-plausible User-Agent for supremecourt.gov (it 403s bare
curl): curl -sL -A "Mozilla/5.0" -o <file> <url>.
Step 3 — Upload to the reMarkable
Tools: the remarkable_* MCP tools (if not loaded:
ToolSearch "select:mcp__remarkable__remarkable_upload,mcp__remarkable__remarkable_mkdir,mcp__remarkable__remarkable_browse"
— adjust prefix to whatever the connected server exposes).
- Crop margins first — run this skill's
crop_pdf.pyon every PDF so documents open margin-free on the tablet (the user shouldn't have to adjust borders by hand):uv run <this skill's directory>/crop_pdf.py <file.pdf>A nonzero exit means no plausible content box was found — upload that file uncropped rather than failing. remarkable_mkdir→<Project>/<Short Caption>(e.g.SCOTUS Prep/Smith v. Arizona).- Upload each PDF named
NN Title.pdfper the table (keep the numbers so they sort in reading order), e.g.02 Cert Petition.pdf,06 Respondent Merits Brief.pdf. remarkable_browsethe folder afterward to confirm everything landed.
Step 4 — Report
Give the user a manifest: caption, docket number, argument date/status, each document uploaded (with filing date where the docket shows it), each document not available and why, companion cases, and the amicus count with an offer to pull specific ones.
Prerequisites
- A reMarkable tablet and a reMarkable MCP server connected to the current agent,
exposing
remarkable_upload/remarkable_mkdir/remarkable_browse-style tools (names may differ by connector). Without one, Step 3 cannot run — the downloaded, cropped PDFs can still be handed to the user as files instead. ToolSearch(Step 3) is a Claude Code built-in for discovering MCP tools dynamically; on another agent, just use whatever the connected reMarkable MCP server actually exposes (check its tool list directly).uv(foruv run crop_pdf.py) or a plainpython3with the same dependencies installed.
Limitations
- US Supreme Court only. Every source (supremecourt.gov, SCOTUSblog, Oyez, CourtListener) and the whole document set (cert petition, merits briefs, SCOTUS oral- argument transcript) is specific to US Supreme Court practice; this skill has no state-court, lower-federal-court, or non-US equivalent.
- Assumes the user owns a reMarkable device specifically — no fallback is defined for a different e-reader/tablet brand beyond "hand the user the files instead."
示例提示词
帮我收集这个案件的诉状、简报和庭审记录并导入reMarkable。
所属插件
安装该插件会一并获得同领域的 13 个 Skill / MCP。
同插件的其他科研 Skill
- Zotero文献库构建Builds or extends a Zotero collection for a project: finds sources, adds metadata via the Zotero Web API, and runs an anti-hallucination check. Use to populate a Zotero library with verified sources.
- 裁判文书实证研究Guides empirical research on a sample of Chinese court judgments: sampling frame, coding scheme, inter-coder reliability, and descriptive statistics on rulings. Use for a quantitative case-law study.
- 文稿引注核查Verifies every citation/quotation in a legal draft against CourtListener, official reporters, and Zotero/the open web, returning a graded Bluebook footnote report. Use to cite-check a US law draft.
- 代码专利特征扫描Scans a codebase for distinctive, potentially patentable design patterns with structured scoring and evidence. Use before a patent consultation, not as legal advice.
- 代码专利检索验证Turns code-scan findings into patent-database search queries for researching existing implementations before consulting an attorney. Not legal advice.
- 快速引注查找Finds 2-4 verified US case-law or scholarly citations with a pincite for a single proposition, footnote-ready with Bluebook form. Use for a quick cite-finding request, not a full memo.
- 中国法律全领域检索China-focused systematic legal research across statutes, regulations, judicial interpretations, and guiding cases, tailored by user role. Use to judge legality or find a legal basis/damages standard.
- 深度法律研究备忘录Fans out multiple agents across free US legal sources, verifies every authority against CourtListener/Justia/Google Scholar, and returns a polished memo. Use for US case-law research.
- 专利构思特征分析Analyzes a described concept to surface what makes it distinctive, with structured scoring for a patent consultation. Not legal advice.
- 专利构思检索验证Turns a concept analysis into patent-database search queries for researching the prior-art landscape before consulting an attorney. Not legal advice.
- 文稿校对润色Proofreads a legal draft’s prose for typos, grammar, and internal consistency (hyphenation, defined terms, cross-references). Use for a proofing pass; not a cite-checker or editor.
- 法律研究插件初始化配置One-time, conversational setup for the legal-research plugin: saves and tests a CourtListener token and checks Zotero credential availability. Use to set up this plugin’s CourtListener access.
常见问题
最高法院案件材料整理能做什么?
Gathers the full document set for a US Supreme Court case and loads it onto the user’s reMarkable in a per-case folder. Use when prepping a SCOTUS case for a podcast, class, or article。
如何安装最高法院案件材料整理?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「最高法院案件材料整理」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
最高法院案件材料整理需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
最高法院案件材料整理经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。