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 skills add XMZF-vAI/clerkbox --skill pptxgit clone --depth 1 https://github.com/XMZF-vAI/clerkboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xmzf-vai/clerkbox/pptx)<a href="https://agentmods.dev/skills/xmzf-vai/clerkbox/pptx"><img src="https://agentmods.dev/badge/skills/xmzf-vai/clerkbox/pptx/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xmzf-vai/clerkbox/pptx"><img src="https://agentmods.dev/badge/skills/xmzf-vai/clerkbox/pptx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00152 | $0.02445 |
| Opus 5.5 | $0.00061 | $0.00978 |
| Sonnet 5.5 | $0.00030 | $0.00489 |
| Haiku 4.5 | $0.00015 | $0.00245 |
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 1mo 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX Pro 2.0 — Fast Path
Core principle
Generate a polished, professional .pptx in 6–10 minutes by following a single five-step fast path:
- Gather material — collect the topic, audience, deck length, and any user-supplied source content.
- Ensure environment — verify Python +
python-pptx; install if missing. - Write generator — produce a single
generate.pyscript with inline overflow safeguards. - Execute & self-correct — run, fix any P0 issues in place, rerun.
- Deliver — output the
.pptxto the current working directory with a one-paragraph QA note.
This skill uses Python + python-pptx as the unified engine for all PPTX operations. Quality bars stay the same; the delivery path is faster and more predictable.
When to use
Use this skill for any task involving .pptx files:
- From scratch generation — follow the five-step fast path in this file.
- Editing an existing .pptx — follow the three-step path in
references/editing.md(read structure → write modify script → markitdown verify). Same python-pptx engine, no XML unpacking. - Read-only inspection / text extraction — run
python -m markitdown deck.pptxdirectly, or use the structured-read snippet at the top ofreferences/editing.md.
Step 1 — Gather material
Ask only what is genuinely missing. Do not run mandatory multi-round clarification. The minimum context needed is:
- Topic — what the deck is about.
- Audience and tone — executive, technical, sales, training, internal review.
- Length — slide count target, default 6–8.
- Source content — paste, file path, or "use public knowledge."
If the user already gave clear instructions, skip the question round and proceed.
Step 2 — Ensure environment
Run probes. If they succeed, skip install:
python -c "import pptx; print(pptx.__version__)"
python -m markitdown --help >NUL 2>&1
If they fail:
python -m pip install --quiet python-pptx "markitdown[pptx]"
What ships with it
3 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.
- 1mo ago First seen · 165 lines · 152 tokens per session scan A ed54b41246f1
pptx is a skill published in the GitHub repository XMZF-vAI/clerkbox (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 152 tokens to every session and 2,445 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
authoring
How to write Stencila Markdown (.smd) and work with executable documents in related flavours (.myst, .qmd). Use when creating or editing .smd files, adding executable code chunks, inline expressions, parameters, figures, tables, math, or document metadata, or when unsure how Stencila Markdown differs from plain…
conversion
Converting documents between formats with stencila convert - lossless vs lossy targets, quantifying conversion losses, decoding options, and ingesting documents by DOI, arXiv, or PubMed Central identifier. Use when converting to or from DOCX, PDF, LaTeX, JATS, IPYNB, MyST, Quarto or other formats, or importing…
execution
How Stencila executes documents - kernels, staleness-driven re-execution, execution options, and debugging chunks that error or do not re-run. Use when running stencila execute or render, when a code chunk is not re-running, when choosing a language/kernel, or when reading execution errors.
publishing
Publishing Stencila documents - rendering to HTML/PDF/DOCX with themes, building and pushing workspace sites, publishing to Ghost or Zenodo, and signing outputs with content credentials. Use when the user wants to publish, deploy a site, apply a theme, produce final outputs, or push to Ghost, Zenodo or Stencila Cloud.
convert
Convert a document between formats, reporting any conversion losses.