agentleFS
Lesile-YinLesile-Yin/agent-skills/skills/slide-smith/SKILL.md

slide-smith

Skill2 starsChanged 3 months agoMITView on GitHub

Batch PowerPoint automation with python-pptx. Audits deck structure, standardizes typography/colors/spacing against design tokens, and performs safe bulk text operations across many decks. Use when processing courseware or training material at scale, unifying inconsistent decks to a house style, or preparing accessibility-friendly (large-type, high-contrast) variants.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never modify originals in place.

    line 18
  2. Distinctive:

    Keep replacements at run level to preserve formatting.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Slide Smith

Batch-forging decks: audit → standardize → verify. Built for courseware pipelines where dozens of .pptx files must share one visual system.

Safety rule (non-negotiable)

Never modify originals in place. Every script reads a source path and writes a new file (*_standardized.pptx or an explicit --out). If the user asks to overwrite originals, produce the outputs first, then let them swap.

Capabilities

1. Inventory — know what you're dealing with

python3 scripts/inventory.py deck.pptx [more.pptx ...] [--json]

Reports per deck: slide count, layouts used, distinct fonts, distinct font sizes, image count, text boxes overflowing slide bounds. Run this first on any batch — the inventory decides which standardize presets are needed.

2. Standardize — apply design tokens

python3 scripts/standardize.py deck.pptx --preset house [--out out.pptx]

Applies a named preset from references/design-tokens.md:

  • Title/body font families and size floors (titles never below the preset's minimum; body text scaled up, never down).
  • Theme colors for titles, body, and accents.
  • Consistent margins for text placeholders.

Presets included: house (neutral corporate), access-large (accessibility/elder-friendly: 40pt+ titles, 24pt+ body, high contrast), sans-minimal. Add your own by editing the PRESETS dict in the script.

3. Bulk text ops — replace/append across decks

For find-replace or boilerplate insertion across a batch, drive python-pptx directly with a short inline script; pattern:

from pptx import Presentation
prs = Presentation(src)
for slide in prs.slides:
    for shape in slide.shapes:
        if shape.has_text_frame:
            for para in shape.text_frame.paragraphs:
                for run in para.runs:
                    run.text = run.text.replace(OLD, NEW)
prs.save(dst)

Keep replacements at run level to preserve formatting; only rebuild paragraphs when structure must change.

Workflow for a batch job

  1. inventory.py over the whole folder → note font chaos / overflow counts.
  2. Pick or define a preset; run standardize.py on one representative deck; open and eyeball it (script output says what changed).
  3. Loop over the batch; collect the per-deck change summaries.
  4. Deliver: standardized files + one Markdown summary (deck, slides, changes applied, warnings like "images may overlap enlarged text").

Known limits

  • Charts, SmartArt and grouped shapes are not restyled (python-pptx access is limited); inventory flags them so a human can check.
  • Font availability: standardize sets font names; if the target machine lacks the font, PowerPoint substitutes. Prefer widely installed families.
  • Overflow detection is geometric (box bounds vs slide), not optical.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.