mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-12 12:06:29 +03:00

Files

T

c49666e29a feat(skill): add documents family skill (PDF / Word / Excel / PowerPoint) (#262 )

* feat(skill): add documents family skill (PDF / Word / Excel / PowerPoint)

One family skill for PDF, Word (.docx), Excel (.xlsx), and PowerPoint
(.pptx) per the family-skill rule (epub precedent): shared workflow in
SKILL.md (scope, content model, template, render, validate, deliver) with
per-format load-on-demand references, generation templates per format, a
stdlib validation script (--json, structural sanity + render check with
graceful degradation), one fixture per format, a unittest suite, six
output-quality eval cases spanning all four formats, a human README, the
README.md index entry, and regenerated catalogs.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* fix(skill): dispatch PDF renderer args per binary in documents validation

The render check passed pdftoppm-only flags (-png/-r/-f/-l) to mutool and
ghostscript, which reject them, so a machine with only mutool or gs would
false-FAIL valid PDFs. Dispatch per-renderer argument sets (pdftoppm -png;
mutool draw -o; gs -sDEVICE=png16m) and cover the dispatch with a unit test.
Also: count PDF pages via the /Count page-tree fallback (page objects can
hide in compressed ObjStm streams), drop the stale "unsupported input" exit-2
claim from the docstring, and stop labeling skipped files with a FAIL check.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* style(skill): drop redundant local tempfile import in renderer dispatch test

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

---------

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

2026-08-03 17:36:00 -04:00

1.7 KiB

Raw Permalink Blame History

PDF Generation Template

Fill every [fill: ...] marker with content from the content model, then render to PDF (print-ready HTML/CSS or LaTeX). Delete this instruction block after filling.

Document metadata

Title: [fill: document title]
Author / owner: [fill: author or team]
Audience: [fill: who reads this and what decision it supports]
Date: [fill: YYYY-MM-DD]
Version: [fill: 1.0]

Scope contract

Purpose: [fill: one sentence on what this PDF is for]
Page budget: [fill: expected page count / upper bound]
Layout engine: [fill: print HTML/CSS (WeasyPrint or headless Chromium), LaTeX, or direct PDF]
Source of truth: [fill: path to the content model this is generated from]

Content outline

Section 1 — [fill: section title]

Body: [fill: paragraph or bullet content]
Layout notes: [fill: fonts, spacing, page-break constraints]

Section 2 — [fill: section title]

Body: [fill: paragraph or bullet content]
Layout notes: [fill: fonts, spacing, page-break constraints]

Section N — [fill: section title]

Body: [fill: paragraph or bullet content]
Layout notes: [fill: fonts, spacing, page-break constraints]

Assets

Images/figures: [fill: image paths and placement]
Fonts: [fill: font names; confirm they will be embedded]

Validation gate

python3 scripts/validate-documents.py --render-check --json output.pdf

Structure passed: [fill: script exit code and status]
Render check: [fill: ok or unavailable, with renderer used]
Page count observed: [fill: matches scope?]

1.7 KiB Raw Permalink Blame History