Communitygithub.com

sheet-review

Preflight and review an exported presentation sheet (PDF) and its InDesign source before calling it done — page size, embedded fonts, image PPI, small and placeholder text, scale notations, hairlines, off-palette and legend-only colors, a change diff against the previous export, InDesign overset / links / placed-drawing scale / missing fonts, then a tile-by-tile visual pass for stray linework and legend-to-symbol mismatches. Use when the user says "check the sheet", "review the PDF", "is the board ready", "preflight", "before I print / plot / submit", after any InDesign export, or before reporting a layout as verified.

Qu'est-ce que sheet-review ?

sheet-review is a Codex agent skill that preflight and review an exported presentation sheet (PDF) and its InDesign source before calling it done — page size, embedded fonts, image PPI, small and placeholder text, scale notations, hairlines, off-palette and legend-only colors, a change diff against the previous export, InDesign overset / links / placed-drawing scale / missing fonts, then a tile-by-tile visual pass for stray linework and legend-to-symbol mismatches. Use when the user says "check the sheet", "review the PDF", "is the board ready", "preflight", "before I print / plot / submit", after any InDesign export, or before reporting a layout as verified.

Compatible avec~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/zohartito/arch-skills/tree/HEAD/skills/sheet-review

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

sheet-review — export → evidence → verdict

A fit-to-screen look cannot see a 0.3 pt stray line on a 36×24 sheet. In one studio project, "PDF reviewed" was claimed while stray bed linework and a colored legend over uncolored symbols went through, and that miss is logged 30 times. This skill makes the review cover every tile, and it keeps what a script proved separate from what the visual pass saw.

Scripts live in this skill's scripts/ folder; run commands from the skill folder.

Order

  1. Pin the artifact. Record the PDF path and its INDD, with the sha256 and mtime of both. Review the exported PDF, not a description of it.
  2. InDesign audit (when the INDD is open). It only reads and never launches InDesign. Limit: both routes below need an execute_extend_script tool from a fork of the adb-mcp Adobe connector. That tool is not in upstream adb-mcp yet. If it isn't available, say the audit was not run and list it under not checked. The PDF preflight (step 3) does not need it.
    • MCP: read indesign_audit.jsx, set TARGET_DOC_NAME to the document name, and pass the text to an InDesign MCP tool named execute_extend_script (see the repository README). Pass app_name when both the release and Beta InDesign are running.
    • Without MCP (Codex, shell): <adb-mcp venv>/bin/python scripts/run_indesign_audit.py --doc NAME.indd --out <checks>/indesign-audit.json It audits whichever InDesign is running. Add --app "<name>" only when the release and the Beta are both running; the error lists the running names. Don't write a year from memory: Creative Cloud replaces the apps on upgrade (2026 became 2027 in November 2026).
    • If unsavedChanges is true, the PDF does not represent the live layout. Say so.
  3. PDF preflight:
    python3 scripts/pdf_preflight.py SHEET.pdf --out <checks>/sheet-review-<date> \
      --expect-size 36x24 --palette <project>/standards/linework.md --compare PREVIOUS.pdf
    
    Dependencies are PyMuPDF, numpy, Pillow and scipy (all in requirements-arch-tools.txt). Exit 1 means a FAIL. Outputs are report.md, report.json, p<N>-overview.png with the tile grid labeled, tiles/p<N>-r<row>c<col>.png at 150 dpi (--tile-dpi 300 for fine linework) and p<N>-diff.png. Always pass --compare when a previous export exists: the changed-region list is the cheapest way to catch a stray line or an accidental move.
  4. Visual pass on every tile, in order. For each tile write clean or the issue with its tile id. Look at the overview first for composition at fit-page distance. Then, per tile:
    • Stray linework: construction lines, duplicates, lines crossing furniture, beds or text, lines outside a drawing frame, broken hatch boundaries.
    • Legend ↔ symbol: every legend swatch appears on the drawing it keys, and every colored category on the drawing is in the legend. A colored legend over uncolored symbols is a fail. swatch-only-color findings point at suspects.
    • Line hierarchy: cut/poché heaviest, then medium, then light, per the project's linework standard.
    • Scale: each stated scale (the preflight lists every notation) matches the placed size. A placed drawing that isn't at 100% in the audit makes its stated scale wrong unless the label was changed to match. Scale bars and north arrows are where the standard asks for them. NTS appears only where intended.
    • Text: readable at print size, nothing clipped, no placeholders, consistent titles.
    • Images: pixelation or banding. Section cut marks match the section titles.
  5. Report in three columns: verified by script / seen in visual pass / not checked. Keep status words exact: exported ≠ printed ≠ submitted. Never call a sheet ready with an open FAIL, an unreviewed tile, or unsaved INDD changes.

Reading the automated findings

CheckMeaningWatch for
page-size FAILwrong size or orientation—
font-not-embedded FAILthe plotter may substitute—
low-ppi-imageeffective PPI at placed sizebbox can extend past the page on cropped images
small-textspans below --min-text-pt (6)sizes are listed, the smallest is located
placeholder-textlorem / TODO / TBD / XXX / TK—
hairline-strokesstrokes < 0.1 pt may vanish in printMake2D linework weights
swatch-only-colora non-neutral fill used only in ≤ 6 small shapes, never strokedraster images aren't scanned; if the keyed items are in a placed image, confirm by eye
off-palette-fillsfills > 0.5 in² not near any palette hex (grays and near-black ignored)pass the palette the project actually uses
changed-region (INFO)pixels changed vs. the previous exportevery region should map to an intended edit
INDD notAt100a placed drawing is scaledthe stated drawing scale must be recomputed

Eval

tests/seeded_eval.py SHEET.pdf --work <scratch> --palette … copies a real sheet and plants five defects: a stray line, a legend swatch with no symbols, an off-palette fill, 3 pt text and "TBD". It then runs the preflight with --compare and scores detection against that answer key. The last run, on a real 36x24 review sheet (2026-10-05), caught 5/5. Re-run it after any change to the script. Stray linework that existed before the first export is invisible to --compare, so the visual pass stays mandatory.

Design critique (conventions, argument, composition) is a separate step, not covered here. This skill is the evidence pass, and it runs before that critique.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

physical-model-prep

Prepare physical architecture studio models for fabrication - 3D-print STLs and laser-cut .3dm files generated from the saved Rhino model, with the scales, materials, layer colours, fit clearances, measured laser burn, laser settings per material (basswood, plywood, MDF engrave, mat board) and USB hand-off that one real studio project's models (Oct 2026) actually used, plus the rules the user's corrections set. Use when asked for a "laser file", to "laser cut" or "score" or "engrave" parts, "laser settings", square or round "post holes", "kerf", to "3D print the model", to build a "massing model" or "chunk model", for a "cut list", for anything at the "fab lab" or the "plotter USB", or when making a "model base" or "lot insert". Not for image-editing effects such as an engraved look in Photoshop, which involve no laser or printer.

precedent-dossier

Research architectural precedents into a cited dossier with a source ledger, so no claim (architect, year, client, program, dimension, intent) reaches a crit without a source id. Sets up the folder, assigns stable S### ids at time of access, ranks sources by class (architect, permit/public record, publication, builder, listing/marketing, social), separates architect-stated intent from inference, records contradictions instead of resolving them silently, tracks drawings and saved images with provenance, and validates the ledger with scripts/check_ledger.py. Use for "precedent research", "find precedents", "case studies", "research this building", "sources for", "who designed", "dossier", or any request to find drawings, intent, or facts about an existing building.

Skills associés