Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to publish, deploy, or share a presentation or HTML file via GitHub Pages.
.claude/skills/publish-to-pages/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-19 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
Publish any presentation or web content to GitHub Pages in one shot.
Run these silently. Only surface errors:
bashcommand -v gh >/dev/null || echo "MISSING: gh CLI — install from https://cli.github.com" gh auth status &>/dev/null || echo "MISSING: gh not authenticated — run 'gh auth login'" command -v python3 >/dev/null || echo "MISSING: python3 (needed for PPTX conversion)"
poppler-utils is optional (PDF conversion via pdftoppm). Don't block on it.
Determine input type from what the user provides:
| Input | Detection | |-------|-----------| | HTML file | Extension .html or .htm | | PPTX file | Extension .pptx | | PDF file | Extension .pdf | | Google Slides URL | URL contains docs.google.com/presentation |
Ask the user for a repo name if not provided. Default: filename without extension.
Both conversion scripts automatically detect large files and switch to external assets mode:
assets/assets/This keeps individual files well under GitHub's 100MB limit. Small files still produce a single self-contained HTML.
You can force the behavior with --external-assets or --no-external-assets.
No conversion needed. Use the file directly as index.html.
Run the conversion script:
bashpython3 SKILL_DIR/scripts/convert-pptx.py INPUT_FILE /tmp/output.html # For large files, force external assets: python3 SKILL_DIR/scripts/convert-pptx.py INPUT_FILE /tmp/output.html --external-assets
If python-pptx is missing, tell the user: pip install python-pptx
Convert with the included script (requires poppler-utils for pdftoppm):
bashpython3 SKILL_DIR/scripts/convert-pdf.py INPUT_FILE /tmp/output.html # For large files, force external assets: python3 SKILL_DIR/scripts/convert-pdf.py INPUT_FILE /tmp/output.html --external-assets
Each page is rendered as a PNG and embedded into HTML with slide navigation. If pdftoppm is missing, tell the user: apt install poppler-utils (or brew install poppler on macOS).
/d/ and /)bashcurl -L "https://docs.google.com/presentation/d/PRESENTATION_ID/export/pptx" -o /tmp/slides.pptx
Repos are created public by default. If the user specifies private (or wants a private repo), use --private — but note that GitHub Pages on private repos requires a Pro, Team, or Enterprise plan.
bashbash SKILL_DIR/scripts/publish.sh /path/to/index.html REPO_NAME public "Description"
Pass private instead of public if the user requests it.
The script creates the repo, pushes index.html (plus assets/ if present), and enables GitHub Pages.
Note: When external assets mode is used, the output HTML references files in assets/. The publish script automatically detects and copies the assets/ directory alongside the HTML file. Make sure the HTML file and its assets/ directory are in the same parent directory.
Tell the user:
https://github.com/USERNAME/REPO_NAMEhttps://USERNAME.github.io/REPO_NAME/my-slides-2) or a date (my-slides-2026).pip install python-pptx.poppler-utils (apt install poppler-utils or brew install poppler).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. 22 cases were attempted, and 14 counted toward the lift figure. The other 8 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 +23 percentage points is the difference between those two pass rates over the 14 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.