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 ai-analyst-lab/ai-analyst --skill google-slides-exportgit clone --depth 1 https://github.com/ai-analyst-lab/ai-analystWrote 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/ai-analyst-lab/ai-analyst/google-slides-export)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/google-slides-export"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/google-slides-export/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/ai-analyst-lab/ai-analyst/google-slides-export"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/google-slides-export.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00216 | $0.04451 |
| Opus 5 | $0.00108 | $0.02226 |
| Sonnet 5 | $0.00043 | $0.00890 |
| Haiku 4.5 | $0.00022 | $0.00445 |
Grade A, and why
google-slides-export 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Google Slides Export
Purpose
Create properly formatted Google Slides presentations via the MCP API. Prevents API errors and ensures every deck looks professional -- no text overflow, no overlapping elements, consistent brand design.
When to Apply
Automatically whenever:
mcp__google-workspace__batch_update_presentationwill be called- A Google Slides deck is being designed or built
- The
google-slides-creatororgoogle-slides-revieweragent is running
Section A: Pre-Flight Checklist
Run this checklist BEFORE building any batch_update requests. Fix all violations first.
- Object IDs >= 5 characters -- every NEW object ID you create must be 5+ chars
OK:
slide_2,hdr_bg,title_box,body_txtBAD:s2,t1,bg,p_t1(Only applies to IDs you define; existing IDs from the API can be any length) - No zero-weight outlines -- never set
outline.weight.magnitude = 0BAD:"weight": {"magnitude": 0, "unit": "PT"}-> API error OK: Omit theupdateShapePropertiesoutline block entirely (no border = default) - Slide creation uses
createSlide-- notaddSlide(not a valid request type) - Batches <= 50 requests -- split into batches of 50 and apply sequentially Each batch must complete before the next starts (do not parallelize)
-
deleteObjectonly for confirmed IDs -- only delete element IDs returned byget_pageorget_presentation; never delete IDs you invented - Text boxes are generous -- every text box that holds variable content must be
at least 3000000 EMU wide and use
autoFit: AUTO_FIT
Section B: Design System
Page Dimensions
Width: 9144000 EMU (10 inches)
Height: 5143500 EMU (5.625 inches)
1 inch = 914400 EMU
Color Palette (Default Brand)
Dark navy: {red: 0.118, green: 0.161, blue: 0.231} -- header bars, full-bg dividers
Orange: {red: 0.851, green: 0.467, blue: 0.024} -- highlights, accent callouts
Accent green: {red: 0.02, green: 0.588, blue: 0.412} -- secondary metrics
Off-white: {red: 0.969, green: 0.965, blue: 0.949} -- slide background
White: {red: 1.0, green: 1.0, blue: 1.0} -- card backgrounds, text on dark
Dark text: {red: 0.133, green: 0.133, blue: 0.133} -- body text on light backgrounds
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 · 434 lines · 216 tokens per session scan A cb880243d3f8
google-slides-export is a skill published in the GitHub repository ai-analyst-lab/ai-analyst (298 stars, last pushed 3d ago), licensed MIT. It adds 216 tokens to every session and 4,451 once invoked, about $0.0011 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 2026-09-12.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
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…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.