Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/decocms/studio/pptxnpx skills add decocms/studio --skill pptxgit clone --depth 1 https://github.com/decocms/studioWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.00826 |
| Opus 5 | $0.00020 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
pptx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pptx — PowerPoint presentations
Reading and inspection of .pptx files. Editing and creation are not yet
supported.
Making a presentation, slide deck, or "slides"? This is NOT the skill — use the
slidesskill (org/public/core/slides/SKILL.md), which authors HTML decks with a live, editable preview. Reach forpptxONLY when the user explicitly works with a PowerPoint.pptxfile — reading one they uploaded, or when they specifically ask for.pptxoutput (not yet supported here).
Quick reference
| Task | Command |
|---|---|
| Plain-text dump | pptx-extract <file.pptx> |
| Plain-text + speaker notes | pptx-extract --notes <file.pptx> |
| Visual overview (grid image) | pptx-thumbnail <file.pptx> |
| One slide at full resolution | pptx-rasterize --pages 3 <file.pptx> |
| Several slides | pptx-rasterize --pages 1,3-5 <file.pptx> |
| Raw XML inspection | pptx-unpack <file.pptx> |
Every command writes its output next to the input file and prints the output path(s) on stdout.
Reading text
pptx-extract prints each slide as a ## Slide N section followed by the
visible text. Speaker notes are excluded by default; pass --notes to
include them under a ### Notes subsection per slide.
Visual overview
pptx-thumbnail produces two artifacts:
- A composite grid image at
<input-stem>.thumbnail.jpg— 4-column grid with a small slide-number overlay on each cell. Suitable for a single multimodal read to get the shape of the deck. - A directory
<input-stem>.slides/containing per-slide JPGs at the same resolution. When a slide in the grid looks interesting, readslide-NNN.jpgdirectly instead of re-runningpptx-thumbnail.
To actually see the rendered image, call the read tool on the path
pptx-thumbnail printed:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 89 lines · 41 tokens per session scan A 5d5c6bb03f77
pptx is a skill published in the GitHub repository decocms/studio (402 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 826 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcp-assistant
Use when a task needs connected MCP servers, external services, dynamic MCP tool discovery, schema inspection, sandboxed MCP execution, or routing across many possible MCP tools.
pr-finish-pass
Final-polish pass on the current PR or feature branch before it lands. Rebases on origin/main, force-pushes, drives CI to green, then reviews the diff for correctness/perf/security/reliability bugs, flaky test patterns banned by make lint-test-patterns, sloppy comments a senior engineer would not write, cross-crate…
mcp-cli
Use when running, automating, integrating, or troubleshooting the MCP CLI (mcpa | mcp-ts), including local or remote discovery, authentication, schema inspection, tool calls, and gateway lifecycle errors.
harn-release
Use for Harn release prep, version bumps, publishing, tags, and release notes.
harn-apps
Keep app behavior in Harn while shared hosts draw the view and provide files, network, and browser features.
harn-mcp
Use for MCP client connections, server definitions, inbound roots/sampling/elicitation, and deterministic MCP fixtures.