Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Deploy Slides to GitHub Pages — measured AI agent skill | DecimalAI

pedrohcgs/deploy

NewSkillScoreMaintained

Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly for that.

DevOpsby pedrohcgs

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull pedrohcgs-deploy

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/pedrohcgs-deploy/SKILL.md

Raw file: /s/pedrohcgs-deploy/SKILL.md ↗ · machine-readable summary at /s/pedrohcgs-deploy.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

Yes — +48% lift-32% tokens0% turns83% of whole cases pass with skill (19/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-50%	0%
case-05	✗→✓	▲ Improved	-55%	0%
case-07	✗→✓	▲ Improved	-52%	0%
case-08	✗→✓	▲ Improved	-4%	0%
case-09	✗→✓	▲ Improved	-36%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

pedrohcgs / claude-code-my-workflow

.claude/skills/deploy/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Deploy Slides to GitHub Pages

Render Quarto slides and sync all files to docs/ for GitHub Pages deployment.

Steps

Run the sync script:

If $ARGUMENTS is provided (e.g., "Lecture4"): ./scripts/sync_to_docs.sh $ARGUMENTS
If no argument: ./scripts/sync_to_docs.sh (syncs all lectures)

Verify deployment:

Check that HTML files exist in docs/slides/
Check that _files/ directories were copied (RevealJS assets)
Check that docs/Figures/ was synced from Figures/

Verify interactive charts (if applicable):

Grep rendered HTML for interactive widget count
Confirm count matches expected

Verify TikZ SVGs (if applicable):

Check that all referenced SVG files exist in docs/Figures/LectureN/

Open in browser for visual verification:

open docs/slides/LectureX_Name.html # macOS
# xdg-open docs/slides/LectureX_Name.html # Linux
Confirm slides render, images display, navigation works

Report results to the user

What the sync script does:

Renders all .qmd files in Quarto/ (skips *_backup* files)
Copies HTML and _files/ directories to docs/slides/
Copies Beamer PDFs from Slides/ to docs/slides/
Syncs Figures/ to docs/Figures/ using rsync

Want to see if pedrohcgs/deploy would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.