I Had 11 AI Subagents Test Every PPTX Skill for Claude Code. Here's What Actually Works.
Serge’s Substack
SubscribeSign in
I Had 11 AI Subagents Test Every PPTX Skill for Claude Code. Here's What Actually Works.<br>The same 5-slide pitch deck brief, eleven presentation skills, eleven parallel Claude subagents, zero mercy. Screenshots included.
Serge Bulaev<br>Jul 22, 2026
Share
Claude Code skills went from a curiosity to an ecosystem in about six months. Search GitHub for "pptx skill" today, and you'll find everything from Anthropic's official document skills to a McKinsey-cosplay design system with Harvey balls to a pipeline that clones the look of your old decks with an image model.<br>The question nobody answers: Which of them produce a deck you'd actually present — and then edit in PowerPoint on the flight to the meeting?<br>So I ran an experiment.
The setup
I write about AI tooling a lot, and my publishing pipeline is itself agent-run — so testing agent skills with agents felt right. The method:<br>One brief for everyone. A 5-slide investor pitch for Publora (a real product: social publishing API, 10 platforms, $2.99/account). Fixed facts, fixed slide structure, one hard trap: Slide 4 must contain a real table or chart — not a picture of one.
Eleven skills, eleven isolated subagents. Each agent cloned one repo, read its SKILL.md, and followed the skill's own documented methodology — no freelancing. Each wrote a report: what broke (with exact errors), what it worked around, scores 1–10 on ease of use, output quality, editability, and docs.
Independent rendering. Every resulting deck went through the same LibreOffice → PNG pipeline, and I reviewed the slides visually myself.
Total: ~1.3M agent tokens, about an hour of wall-clock time, and eleven decks on disk.<br>One number that sets the scene: a single skill's instruction file can now run to 82,000 tokens (slides_maker's SKILL.md) — longer than most novellas — and the agents read all of it before touching the brief.<br>The scoreboard
The asterisk: claude-office-skills turned out to be a verbatim snapshot of Anthropic's pre-release pptx skill. Its own README tells you to use the upstream. Treat rows 1–2 as one entry.
claude-office-skills: a pre-release snapshot of the official skill — the family resemblance shows.<br>The one finding that matters most
Before the individual reviews, here's the pattern that cuts across the whole field:<br>Almost every third-party skill paints tables instead of building them.<br>The brief demanded a real comparison table on slide 4. Out of eleven skills, exactly two produced native OOXML table/chart objects through their own pipeline: the official Anthropic skill and slides_maker. Everyone else — including the two prettiest generators — draws "tables" out of text boxes and rectangles. It looks identical in a screenshot. Then your CFO opens the file, tries to add a row, and finds sixty-two loose shapes where a table should be.<br>My subagents patched real tables in via python-pptx to satisfy the brief, and every report flagged the same thing: beauty and editability are currently a trade-off, and most skilled authors chose beauty.
A native, editable table — the official skill.
Gorgeous — and made of loose shapes. mckinsey-pptx.<br>Tier 1: use these
1. anthropics/skills — the boring, correct answer (6/9/9/9)
The official document-skills bundle is the only entry that treats a .pptx as a document format rather than a rendering target. Real tables, real charts, a design rulebook, an XSD validator, and a mandatory render-and-look QA loop that caught every layout defect in our run.<br>The catch: its primary create path assumes pptxgenjs is preinstalled (it is in Anthropic's own sandbox; it wasn’t in ours — npm ENOTCACHED). The agent fell back to python-pptx and the skill's tool-agnostic rulebook carried it to a clean slate anyway. That's the sign of a well-designed skill: the methodology survives the tooling.<br>Use it when: you need decks people will edit. Which is most decks.<br>What the reports surfaced beneath the surface: the SKILL.md is ~240 lines of hard-won scar tissue — twenty-odd documented gotchas like "hex colors without #" and "negative shadow offsets corrupt files." The render-QA wrapper goes as far as compiling a small C shim on the fly with GCC and LD_PRELOADing it so LibreOffice's sockets work inside sandboxes. The design section explicitly bans the classic AI-slide tells — accent lines under titles, decorative color bars, and cream backgrounds. One human moment: its placeholder check greps for TODO and flagged our deck — the match was "Mastodo n," an actual platform in the brief.<br>2. slides_maker — the dark horse (6/9/9/7)
The only third-party skill that shipped both a native table and a native editable chart through its own engine. Its build → strict-lint → render → render-lint → critic loop caught 30+ real defects in our run before a human ever saw the file. The output (dark_tech preset) looks like a real startup deck, not a python-pptx...