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

1.6 KiB

Raw Permalink Blame History

Excel (.xlsx) Generation Template

Fill every [fill: ...] marker with content from the data model, then generate the .xlsx (openpyxl, or raw OPC for tiny workbooks). Delete this instruction block after filling.

Workbook metadata

Workbook title: [fill: workbook name]
Owner / source: [fill: team and data source]
Date generated: [fill: YYYY-MM-DD]
Version: [fill: 1.0]

Scope contract

Purpose: [fill: what decisions this workbook supports]
Sheet list: [fill: one line per sheet: name and content]
Source of truth: [fill: path to the source data (CSV/JSON/etc.)]

Sheet layout — [fill: sheet name]

Columns

Column	Header text	Type (number/date/text/currency)	Notes
A	[fill: header]	[fill: type]	[fill: notes]
B	[fill: header]	[fill: type]	[fill: notes]

Rows

Row 1 header row: [fill: yes]
Data rows: [fill: source path or inline rows]
Formulas: [fill: which cells hold formulas and what they compute; every formula cell must carry a cached value]

Styling

Number formats: [fill: currency/date formats per column]
Column widths: [fill: widths so data is not clipped]
Freeze panes: [fill: header row frozen?]

Validation gate

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

Structure passed: [fill: script exit code and status]
Render check: [fill: ok or unavailable, with renderer used]
Spot check: [fill: 2-3 cells compared against source data, confirmed]

1.6 KiB Raw Permalink Blame History