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/davidroliverba/architectkb/pptx-createnpx skills add DavidROliverBA/ArchitectKB --skill pptx-creategit clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBWrote 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/davidroliverba/architectkb/pptx-create)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/pptx-create"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/pptx-create.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.01735 |
| Opus 5 | $0.00006 | $0.00868 |
| Sonnet 5 | $0.00002 | $0.00347 |
| Haiku 4.5 | $0.00001 | $0.00173 |
Grade A, and why
pptx-create 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 4d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pptx-create
Create a new PowerPoint presentation using a template from the extracted library. Populate slides from an outline, vault notes, or a JSON content specification.
Usage
/pptx-create <title> [--template <slug>]
/pptx-create <title> --template <slug> --from <note-path>
/pptx-create --template <slug> --content <content.json>
Examples
/pptx-create "Q1 Architecture Review" --template baae-community-day-feb2026
/pptx-create "Alpha Programme Update" --from "Projects/Project - Alpha.md"
/pptx-create --template baae-community-day-feb2026 --content slides.json
Instructions
Phase 1: Select Template
- If
--templateprovided, load that template - If not provided, list available templates and ask user to choose:
python3 .claude/scripts/pptx_create.py --list-templates
Use AskUserQuestion to select:
Question: "Which template should be used?"
Header: "Template"
Options:
1. "<most recent template>" (Recommended)
2. "<other template>"
3. "List all layouts first"
Phase 2: Define Content
Determine the content source based on user input:
Option A: Interactive Outline
If user provides just a title, help them build an outline interactively:
- Ask for the presentation structure (sections/topics)
- For each section, ask for key points
- Map each section to an appropriate layout
Option B: From Vault Note
If --from <note-path> is provided:
- Read the vault note
- Extract headings, key points, and relationships
- Map sections to slides automatically:
- H1 → Title slide
- H2 → Section headers
- H3 + bullets → Content slides
- Tables → Content slides with table data
- Images → Image layout slides
Option C: JSON Content Specification
If --content <file> is provided, use the JSON directly. Format:
{
"title": "Presentation Title",
"slides": [
{
"layout": "title-slide",
"content": {
"title": "Presentation Title",
"subtitle": "Author — Date"
}
},
{
"layout": "section-divider-dark-blue",
"content": {
"title": "Section Name"
}
},
{
"layout": "single-column-text",
"content": {
"title": "Slide Title",
"body": ["Bullet 1", "Bullet 2", "Bullet 3"]
},
"notes": "Speaker notes here"
},
{
"layout": "two-column-text",
"content": {
"title": "Comparison",
"left": ["Before item 1", "Before item 2"],
"right": ["After item 1", "After item 2"]
}
},
{
"layout": "large-image-large-text",
"content": {
"title": "Architecture Diagram",
"image": "Attachments/diagram.png",
"body": "Key architecture overview"
}
}
]
}
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.
- 4d ago First seen · 265 lines · 12 tokens per session scan A 8ca371776190
pptx-create is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,735 once invoked, about $0.0001 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.