hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-report
hyper-report
VerifiedUse this skill when the user asks for a report as a finished document rather than a chat answer: a briefing, business or research report, proposal, status or analysis write-up, or one-page summary. It fixes audience and decision up front, keeps every number and claim traceable to a source, and renders one authored Markdown source into HTML, print PDF, per-page PNG/JPG images, DOCX, or Markdown, with tables and figures where they carry the reader. Do not use it for slide decks, spreadsheet workbooks, single generated images, or reports that only need to live in chat.
rules/format-routes.md
View on GitHub# Format routes
One source, many formats, one direction: the Markdown source is authored, the HTML is rendered from it, and everything else is derived from the HTML.
## 1. Why HTML is canonical
The HTML is the only artifact that is both the source of every other format and inspectable on its own. A PDF is a printed HTML; a page image is a screenshot of one page of that HTML; a DOCX is a conversion of that HTML. Fix the HTML, and every format inherits the fix. Hand-edit a PDF and the next render silently discards the edit.
```
report.md --(markdown.awk)--> body.html
body.html + report.css + theme + report.js --(assemble.awk)--> report.html <- canonical
report.html --(headless print)--> report.pdf
report.html --(headless screenshot)--> report-01.png ... report-NN.png
report-NN.png --(sips / magick)--> report-NN.jpg
report.html --(textutil)--> report.docx
report.md --(copy)--> report.md
```
## 2. What each format carries
| Format | Carries | Loses | Use when |
|---|---|---|---|
| HTML | Everything: pagination, theme, tables, figures, the table of contents | Nothing, but it needs a browser to open | The reader will read on screen, or you need one file that prints correctly |
| PDF | Exactly the paginated pages, fonts embedded, fixed geometry | Text reflow, live links beyond what the browser wrote | The reader will print it, email it, or sign it |
| PNG | One file per page, at 1–3× device scale | Text selection, links, search | A slide, a chat message, a message board, a preview |
| JPG | Same as PNG, smaller | Slightly more compression artifacts on text | The destination caps file size or rejects PNG |
| DOCX | Editable text, the reader can revise | Exact pagination, the theme's typography, the footer numbering | The reader must edit or comment in Word |
| Markdown | The authored source, portable | Any layout the pipeline applied | The reader wants the text, or will re-render elsewhere |
DOCX is a courtesy export, not a layout-faithful one. Say so when delivering it: pagination in Word will not match the PDF, because Word lays out the text again with its own engine and fonts.
## 3. Format selection
Pick the smallest set that serves the stated reader.
- No format named, on-screen reader: `html,pdf`.
- No format named, print or email: `html,pdf`.
- A chat or slide destination: `png` alone, or `pdf` plus `png` for the pages that matter.
- A reader who must edit: add `docx`, and warn about pagination.
- A page-limited task ("one page"): the page count is the deliverable constraint, so check it before adding formats.
Do not add a format the user did not ask for just because the pipeline can. Five files where the user wanted one is a worse delivery than one file.
## 4. When a renderer is missing
Formats degrade in this order, and the degradation is reported, never hidden:
| Missing | Still works | Reported as |
|---|---|---|
| Any Chromium-family browser | `md` only | `BROWSER_MISSING` — the browser is the whole rendering path |
| `textutil` (non-macOS) | `html`, `pdf`, `png` | `DOCX_UNAVAILABLE` |
| `sips` and ImageMagick | `html`, `pdf`, `png` | `RASTERIZER_MISSING` for the `jpg` request only |
Never install a renderer mid-run to make a format appear. Report which format is unavailable and why, deliver the rest, and let the user decide.
## 5. The page is the unit
Every format except Markdown is page-addressed, so the page count is decided once, in the HTML, and every derived format agrees with it.
- The layout pass in `report.js` decides how many pages the content takes.
- The PDF must print exactly that many pages; a mismatch is a blocking finding.
- The image export is per page, numbered from 1, zero-padded to two digits.
- The page number in the footer is `current / total`, resolved after pagination.
This is why the source cannot contain a manual page break in the middle of flowing text except through the explicit `:::pagebreak` marker, which the paginator honors as a hard boundary.
## Sources
> Checked 2026-11-13.
| Claim | Source |
|---|---|
| Headless print-to-pdf, screenshot, and DOM dump as the rendering primitives | <https://developer.chrome.com/docs/chromium/headless> |
| `@page` size and margin, and the fixed-geometry print model | <https://developer.mozilla.org/en-US/docs/Web/CSS/@page> |
| `sips` as the macOS image converter and `textutil` as the macOS document converter | <https://ss64.com/mac/sips.html>, <https://ss64.com/mac/textutil.html> |
| DOCX re-layout in Word differing from browser pagination | This package's measurement on macOS 26.2 with Word's own layout engine, not a documented guarantee |Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |