⚠️ USE VARIED LAYOUTS — monotonous presentations are a common failure mode. Don't default to basic title + bullet slides. Actively seek out:

Multi-column layouts (2-column, 3-column)
Image + text combinations
Full-bleed images with text overlay
Quote or callout slides
Section dividers
Stat/number callouts
Icon grids or icon + text rows

Avoid: Repeating the same text-heavy layout for every slide.

Match content type to layout style (e.g., key points → bullet slide, team info → multi-column, testimonials → quote slide).

Unpack
Build presentation (do this yourself, not with subagents):
- Delete unwanted slides (remove from <p:sldIdLst>)
- Duplicate slides you want to reuse (add_slide.py)
- Reorder slides in <p:sldIdLst>
- Complete all structural changes before step 5
Edit content: Update text in each slide{N}.xml. Use subagents here if available — slides are separate XML files, so subagents can edit in parallel.
Clean
Pack

Output Structure

Copy the user-provided file to template.pptx in cwd. This preserves the original and gives a predictable name for all downstream scripts.

cp /path/to/user-provided.pptx template.pptx

./
├── template.pptx               # Copy of user-provided file (never modified)
├── template.md                 # markitdown extraction
├── unpacked/                   # Editable XML tree
└── edited.pptx                 # Final repacked deck

Minimum expected deliverable: edited.pptx.

Scripts

Script	Purpose
`unpack.py`	Extract and pretty-print PPTX
`add_slide.py`	Duplicate slide or create from layout
`clean.py`	Remove orphaned files
`pack.py`	Repack with validation

Removes slides not in <p:sldIdLst>, unreferenced media, orphaned rels.

Always write to /tmp/ first, then copy to the final path. Python's zipfile module uses seek internally, which fails on some volume mounts (e.g. Docker bind mounts). Writing to a local temp path avoids this.

Validates, repairs, condenses XML, re-encodes smart quotes.

Slide Operations

Slide order is in ppt/presentation.xml → <p:sldIdLst>.

Reorder: Rearrange <p:sldId> elements.

Delete: Remove <p:sldId>, then run clean.py.

Add: Use add_slide.py. Never manually copy slide files—the script handles notes references, Content_Types.xml, and relationship IDs that manual copying misses.

Editing Content

Subagents: If available, use them here (after completing step 4). Each slide is a separate XML file, so subagents can edit in parallel. In your prompt to subagents, include:

The slide file path(s) to edit
"Use the Edit tool for all changes"
The formatting rules and common pitfalls below

For each slide:

Read the slide's XML
Identify ALL placeholder content—text, images, charts, icons, captions
Replace each placeholder with final content

Use the Edit tool, not sed or Python scripts. The Edit tool forces specificity about what to replace and where, yielding better reliability.

Formatting Rules

Bold all headers, subheadings, and inline labels: Use b="1" on <a:rPr>. This includes:
- Slide titles
- Section headers within a slide
- Inline labels like (e.g.: "Status:", "Description:") at the start of a line
Never use unicode bullets (•): Use proper list formatting with <a:buChar> or <a:buAutoNum>
Bullet consistency: Let bullets inherit from the layout. Only specify <a:buChar> or <a:buNone>.

Common Pitfalls

Template Adaptation

When source content has fewer items than the template:

Remove excess elements entirely (images, shapes, text boxes), don't just clear text
Check for orphaned visuals after clearing text content
Run content QA with markitdown to catch mismatched counts

When replacing text with different length content:

Shorter replacements: Usually safe
Longer replacements: May overflow or wrap unexpectedly
Verify with markitdown after text changes
Consider truncating or splitting content to fit the template's design constraints

Template slots ≠ Source items: If template has 4 team members but source has 3 users, delete the 4th member's entire group (image + text boxes), not just the text.

Multi-Item Content

If source has multiple items (numbered lists, multiple sections), create separate <a:p> elements for each — never concatenate into one string.

❌ WRONG — all items in one paragraph:

<a:p>
  <a:r><a:rPr .../><a:t>Step 1: Do the first thing. Step 2: Do the second thing.</a:t></a:r>
</a:p>

✅ CORRECT — separate paragraphs with bold headers:

<a:p>
  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
  <a:r><a:rPr lang="en-US" sz="2799" b="1" .../><a:t>Step 1</a:t></a:r>
</a:p>
<a:p>
  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
  <a:r><a:rPr lang="en-US" sz="2799" .../><a:t>Do the first thing.</a:t></a:r>
</a:p>
<a:p>
  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
  <a:r><a:rPr lang="en-US" sz="2799" b="1" .../><a:t>Step 2</a:t></a:r>
</a:p>
<!-- continue pattern -->

Copy <a:pPr> from the original paragraph to preserve line spacing. Use b="1" on headers.

Smart Quotes

Handled automatically by unpack/pack. But the Edit tool converts smart quotes to ASCII.

When adding new text with quotes, use XML entities:

<a:t>the &#x201C;Agreement&#x201D;</a:t>

Character	Name	Unicode	XML Entity
`"`	Left double quote	U+201C	`“`
`"`	Right double quote	U+201D	`”`
`'`	Left single quote	U+2018	`‘`
`'`	Right single quote	U+2019	`’`

Other

Whitespace: Use xml:space="preserve" on <a:t> with leading/trailing spaces
XML parsing: Use defusedxml.minidom, not xml.etree.ElementTree (corrupts namespaces)

ppt-editing-skill

Editing Presentations

Template-Based Workflow