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/freespirits/social-auto-engine/gemini-carouselnpx skills add Freespirits/social-auto-engine --skill gemini-carouselgit clone --depth 1 https://github.com/Freespirits/social-auto-engineWrote 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/freespirits/social-auto-engine/gemini-carousel)<a href="https://agentmods.dev/skills/freespirits/social-auto-engine/gemini-carousel"><img src="https://agentmods.dev/badge/skills/freespirits/social-auto-engine/gemini-carousel.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 5.1 | $0.00092 | $0.00976 |
| Opus 5 | $0.00046 | $0.00488 |
| Sonnet 5 | $0.00018 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
gemini-carousel 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 6d 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.
This is a copy
100% identical to gemini-carousel — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Carousel
CRITICAL: Auto-start on load
When this skill triggers, go straight to Step 1. Do not summarise.
Step 1. Gather inputs
Ask:
Paste the content you want in the carousel. A post, section of a newsletter, research notes, or a framework all work.
Wait for the content, then call AskUserQuestion:
[
{
"question": "Brand style?",
"header": "Style",
"multiSelect": false,
"options": [
{"label": "Pull from brand-kit.md", "description": "Use the colours and typography in my project brand file"},
{"label": "I will type brand colours", "description": "I will paste hex codes and font preferences"},
{"label": "Suggest for me", "description": "Pick a palette and typography based on the content"}
]
},
{
"question": "Number of slides?",
"header": "Slides",
"multiSelect": false,
"options": [
{"label": "6 slides", "description": "Concise, fast read"},
{"label": "8 slides", "description": "Standard carousel length"},
{"label": "10 slides", "description": "Deep-dive carousel"}
]
}
]
Step 2. Build the design brief
Analyse the content and produce a slide-by-slide brief with:
- Slide 1 (Cover): hook, large bold text, visual direction
- Slides 2 to N-1 (Body): one idea per slide, max 15 words per slide, visual suggestion
- Slide N (CTA): repost ask, name, link or offer
For each slide include:
- Slide number
- Headline (max 8 words)
- Body text (max 15 words)
- Visual suggestion (icon, colour block, illustration, diagram)
Tell the user:
Here is the design brief. Tell me what to change, or say "generate" when you are happy.
Wait for approval. Do not proceed until the user explicitly approves.
Step 3. Output per-slide prompts
Once approved, output one Gemini image generation prompt per slide, each in its own code block, numbered clearly.
Every prompt follows this structure:
Act as an expert graphic designer. Create a LinkedIn carousel slide at 1080x1350 pixels (4:5 aspect ratio).
Brand style:
- Primary colour: [HEX]
- Secondary colour: [HEX]
- Accent colour: [HEX]
- Typography: [bold industrial headline font, clean geometric body font]
- Aesthetic: modern, authoritative, high contrast
Slide [N of M]: [slide purpose]
Content:
- Headline: "[headline text]"
- Body: "[body text]"
- Visual element: [specific visual suggestion]
Layout instructions:
- [Headline placement and size]
- [Body placement and size]
- [Visual placement]
- [Background treatment]
Constraints:
- Vertical 4:5 aspect ratio at exactly 1080x1350 pixels
- No watermarks, no logos unless specified above
- Maintain visual consistency with the other slides in the set
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.
- 6d ago First seen · 122 lines · 92 tokens per session scan A cc0bf2a52d41
gemini-carousel is a skill published in the GitHub repository Freespirits/social-auto-engine (23 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 976 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gemini-carousel, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
repo-eco-mcp-app
Inline Claude Desktop widget for any public Eco game server - live player counts, meteor countdown, world stats. A hand-rolled MCP Apps reference implementation in Python (no bundler, no React). Triggers - eco-mcp-app, claude-desktop-eco-widget, mcp-apps-reference-implementation.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
consensus-mechanisms
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.