Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Processes PowerPoint presentation files (.pptx). Creates slides, rewrites templates, converts HTML to presentations, validates thumbnails, swaps layouts, and performs deep OOXML editing. Use when working with presentation files or slide decks. Do NOT use for Word documents, spreadsheets, or PDF files.
.claude/skills/telagod-creating-presentations/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -16% | 0% |
.pptx is a ZIP archive of XML and resources. Choose workflow by intent.
| Intent | Workflow | Reference | |--------|----------|-----------| | Read text | markitdown → markdown | thumbnails-and-conversion.md | | Analyze layout / comments / theme | unpack → raw XML | thumbnails-and-conversion.md | | Create new from scratch | html2pptx | html2pptx.md + design-patterns.md | | Create using template | rearrange + inventory + replace | template-workflow.md | | Edit existing slides | unpack → OOXML → pack | ooxml.md | | Visual review | thumbnail grids | thumbnails-and-conversion.md |
html2pptx.md. NEVER set range limits.<p>, <h1>–<h6>, <ul>, <ol>class="placeholder" for chart/table areas (gray bg for visibility)scripts/html2pptx.js to converthtml2pptx() per HTML filepptx.writeFile() to savepython scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4See template-workflow.md for full 7-step workflow (extract → inventory → outline → rearrange → inventory text → generate replacements → apply).
ooxml.md (~500 lines). NEVER set range limits.python ooxml/scripts/unpack.py <file> <dir>ppt/slides/slide{N}.xml)python ooxml/scripts/validate.py <dir> --original <file>python ooxml/scripts/pack.py <dir> <file>Concise code, no verbose names, no unnecessary print statements.
| Package | Install | Purpose | |---------|---------|---------| | markitdown | pip install "markitdown[pptx]" | Text extraction | | pptxgenjs | npm i -g pptxgenjs | Create via html2pptx | | playwright | npm i -g playwright | HTML rendering | | react-icons | npm i -g react-icons react react-dom | Icons | | sharp | npm i -g sharp | SVG rasterization | | LibreOffice | apt install libreoffice | PDF conversion | | Poppler | apt install poppler-utils | pdftoppm | | defusedxml | pip install defusedxml | Secure XML |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 29,065 | 6,483 | -78% | 1 | 1 | 0% | 6,218 | 1,353 | -78% | 0 | 0 | — |
case-02 | fail→fail | 13,351 | 6,230 | -53% | 1 | 1 | 0% | 2,458 | 1,336 | -46% | 0 | 0 | — |
case-03 | fail→fail | 7,452 | 5,974 | -20% | 1 | 1 | 0% | 1,255 | 1,200 | -4% | 0 | 0 | — |
case-04 | fail→fail | 15,689 | 11,301 | -28% | 1 | 1 | 0% | 2,774 | 2,464 | -11% | 0 | 0 | — |
case-05 | pass→pass | 9,498 | 7,205 | -24% | 1 | 1 | 0% | 1,489 | 2,102 | +41% | 0 | 0 | — |
case-06 | fail→pass | 14,165 | 6,057 | -57% | 1 | 1 | 0% | 2,017 | 1,944 | -4% | 0 | 0 | — |
case-07 | pass→pass | 9,840 | 2,359 | -76% | 1 | 1 | 0% | 1,453 | 1,337 | -8% | 0 | 0 | — |
case-08 | fail→pass | 9,699 | 4,554 | -53% | 1 | 1 | 0% | 1,561 | 1,547 | -1% | 0 | 0 | — |
case-09 | pass→pass | 4,066 | 1,548 | -62% | 1 | 1 | 0% | 678 | 1,165 | +72% | 0 | 0 | — |
case-10 | pass→pass | 6,362 | 1,780 | -72% | 1 | 1 | 0% | 1,069 | 1,215 | +14% | 0 | 0 | — |
case-11 | pass→pass | 8,782 | 2,556 | -71% | 1 | 1 | 0% | 1,432 | 1,354 | -5% | 0 | 0 | — |
case-12 | fail→pass | 12,954 | 1,925 | -85% | 1 | 1 | 0% | 2,273 | 1,283 | -44% | 0 | 0 | — |
case-13 | fail→pass | 14,156 | 3,609 | -75% | 1 | 1 | 0% | 2,254 | 1,556 | -31% | 0 | 0 | — |
case-14 | pass→pass | 14,512 | 1,720 | -88% | 1 | 1 | 0% | 2,214 | 1,221 | -45% | 0 | 0 | — |
case-15 | fail→pass | 8,807 | 1,640 | -81% | 1 | 1 | 0% | 1,449 | 1,210 | -16% | 0 | 0 | — |
case-16 | pass→pass | 2,506 | 1,146 | -54% | 1 | 1 | 0% | 339 | 1,105 | +226% | 0 | 0 | — |
case-17 | pass→pass | 6,616 | 2,641 | -60% | 1 | 1 | 0% | 989 | 1,200 | +21% | 0 | 0 | — |
case-18 | pass→pass | 7,899 | 3,419 | -57% | 1 | 1 | 0% | 1,250 | 1,541 | +23% | 0 | 0 | — |
case-19 | fail→pass | 14,133 | 7,370 | -48% | 1 | 1 | 0% | 2,465 | 2,119 | -14% | 0 | 0 | — |
case-20 | pass→pass | 15,702 | 2,725 | -83% | 1 | 1 | 0% | 2,348 | 1,331 | -43% | 0 | 0 | — |
case-21 | pass→pass | 14,085 | 8,409 | -40% | 1 | 1 | 0% | 2,780 | 2,581 | -7% | 0 | 0 | — |
case-22 | fail→pass | 18,303 | 20,626 | +13% | 1 | 1 | 0% | 3,435 | 4,940 | +44% | 0 | 0 | — |
case-23 | fail→pass | 12,466 | 5,579 | -55% | 1 | 1 | 0% | 1,919 | 2,024 | +5% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 20 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +35 percentage points is the difference between those two pass rates over the 20 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.