MidnightDarling/collate

给历史研究者的中文文献 OCR 校对与阅读 pipeline · Agent-native OCR, collation & reading workflow for historical Chinese scholarship — works with Claude Code, Codex, Gemini CLI, Cursor & Hermes agents

6Stars on the repository
24Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

chunqiu

01

MidnightDarling/collate

Skill Claude CodeCodex

Use when reading a single historical paper or final draft and you need to surface taboo, judgment, rhetorical silence, repetition, or the contemporary reality the author approaches indirectly.

6 3mo ago A 38 tokens original Apache-2.0

constellatio

02

MidnightDarling/collate

Skill Claude CodeCodex

Skill "constellatio" from MidnightDarling/collate, covering constellatio, 这个 skill 做什么, 输入, 方法 and 输出.

6 3mo ago A 45 tokens original Apache-2.0

diff-review

03

MidnightDarling/collate

Skill Claude CodeCodex

A review tool that compares the original OCR Markdown with the corrected final Markdown and shows the changes in an HTML page.

6 3mo ago A 153 tokens original Apache-2.0

kaozheng

04

MidnightDarling/collate

Skill Claude CodeCodex

Use when a historical paper or final draft needs evidential scrutiny: warrants, citations, source rank, truncation risk, or argument structure must be audited rather than stylistically interpreted.

6 3mo ago A 40 tokens original Apache-2.0

mp-format

05

MidnightDarling/collate

Skill Claude CodeCodex

A converter that turns finished Markdown or Word manuscripts into HTML for WeChat public-account posts, plus Markdown for Xiami-style editing.

6 3mo ago A 215 tokens original Apache-2.0

ocr-run

06

MidnightDarling/collate

Skill Claude CodeCodex

A workflow for converting cleaned historical-document PDFs into searchable Markdown using optical character recognition, or OCR. It supports scanned pages, including traditional Chinese, vertical text, older characters, and modern simplified Chinese.

6 3mo ago A 214 tokens original Apache-2.0

paper-summary

07

MidnightDarling/collate

Skill Claude CodeCodex

Map a corpus of historical research papers — archival basis, school lineage, temporal-spatial coverage, methodological distribution, conceptual contention, theoretical borrowings, open questions, and a newcomer's reading route. Emits Obsidian-friendly Markdown with ASCII and SVG visualizations. Use for 5–30 history…

6 3mo ago B 157 tokens original Apache-2.0

prep-scan

08

MidnightDarling/collate

Skill Claude CodeCodex

A Mac tool that cleans unwanted marks from scanned PDF papers and historical documents before text recognition. It removes items such as library stamps, database watermarks, scan dates, headers, and footers, then creates a cleaned PDF and page images.

6 3mo ago A 228 tokens original Apache-2.0

prometheus

09

MidnightDarling/collate

Skill Claude CodeCodex

Use when a historical paper or final draft contains a concept, institution, or proper noun that needs a sharply defined public-facing gloss and an ATTRIBUTION-style SVG card.

6 3mo ago A 37 tokens original Apache-2.0

proofread

10

MidnightDarling/collate

Skill Claude CodeCodex

A proofreading workflow for OCR text, meaning text produced by recognizing words from scanned pages. It checks historical documents against their page images and creates a review list without changing the original text.

6 3mo ago A 185 tokens original Apache-2.0

real-thesis

11

MidnightDarling/collate

Skill Claude CodeCodex

Use when a historical paper appears to orbit a deeper claim than the one it states directly, and you need to excavate the thesis it repeatedly approaches but does not quite write.

6 3mo ago A 39 tokens original Apache-2.0

setup

12

MidnightDarling/collate

Skill Claude CodeCodex

A first-time setup guide for a Mac document-OCR workflow. OCR, or optical character recognition, turns scanned pages into text that can be searched and edited.

6 3mo ago A 156 tokens original Apache-2.0

to-docx

13

MidnightDarling/collate

Skill Claude CodeCodex

A document converter that turns corrected Markdown into a Word .docx file. Markdown is plain text with simple formatting marks, while .docx is the editable Microsoft Word format commonly used for submissions and editorial work.

6 3mo ago A 217 tokens original Apache-2.0

visual-preview

14

MidnightDarling/collate

Skill Claude CodeCodex

A visual comparison page for checking document-image cleanup. It shows the original page, the cleaned page, and a difference view that highlights removed marks such as watermarks and collection stamps.

6 3mo ago A 214 tokens original Apache-2.0

xray-paper

15

MidnightDarling/collate

Skill Claude CodeCodex

X-ray a single historical research paper — recover what the author was chasing, situate the paper in the historiographical tradition it joins, and render the encounter as Obsidian-friendly Markdown with ASCII chronicles, SVG positioning cards, and cognitive collision cards. Use when reading one post-OCR history paper…

6 3mo ago A 150 tokens original Apache-2.0