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/justparent/google-slides-mcp/example_skillnpx skills add JustParent/google-slides-mcp --skill example_skillgit clone --depth 1 https://github.com/JustParent/google-slides-mcpWhat 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 | $0.00107 | $0.01981 |
| Opus 5 | $0.00053 | $0.00991 |
| Sonnet 5 | $0.00021 | $0.00396 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
google-slides 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Slides (low-level MCP)
This skill explains the canonical way to drive the google-slides-mcp server.
Tools are exposed as mcp__google-slides__<tool> (shown below by bare name).
Mental model: copy → reuse → fill → prune
The Slides API has no cross-presentation slide copy, and recreating elements by hand loses styling fidelity. So the high-fidelity pattern is always:
- Copy the whole showcase deck (
copy_presentation) — this clones masters, layouts, theme and color scheme, and brings every example slide along as a reusable palette. - Duplicate the example slides you want (
duplicate_slide) within that copy. - Fill them with real content (
set_element_text,replace_all_text). - Prune the leftover palette slides at the very end (
prune_parked_slides).
Editing the copy this way is functionally identical to hand-editing the showcase.
Never rebuild a slide by reading its elements and recreating them in a different deck — that drops theme/master/placeholder styling and will not be pixel-perfect. Always start from
copy_presentation.
Prerequisites
- The MCP server is configured in the client, and the user has run the one-time
login (
google-slides-mcp-auth). If a tool returns "No cached Google credentials…", tell the user to run that command; do not try to work around it. - You need the showcase/template presentation ID (the long ID in its URL:
https://docs.google.com/presentation/d/<ID>/edit). If the user doesn't give you one, find it withsearch_presentations(see below) before asking.
Finding existing decks (Drive discovery)
search_presentations searches the user's Drive across native Google Slides
and PowerPoint (.pptx/.ppt) files — use it whenever the user refers to a
deck by description rather than ID:
search_presentations(order_by="createdTime desc", owned_by_me=true, max_results=1)
→ "the last presentation I created"
search_presentations(name_contains="corporate template", file_type="google_slides")
→ find a template by name
search_presentations(full_text_contains="Q3 revenue")
→ decks mentioning a topic (order_by is ignored by Drive for full-text queries)
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 · 182 lines · 107 tokens per session scan A 46febbd14c54
google-slides is a skill published in the GitHub repository JustParent/google-slides-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,981 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…