Borrowing it
Nothing to install: this file belongs to alecs5am/ralphy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alecs5am/ralphy/main/.agents/skills/carousel/SKILL.mdgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/carousel)<a href="https://agentmods.dev/skills/alecs5am/ralphy/carousel"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/carousel/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/alecs5am/ralphy/carousel"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/carousel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 110 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Agent Snooping · line 172 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 173 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00285 | $0.03302 |
| Opus 5.5 | $0.00114 | $0.01321 |
| Sonnet 5.5 | $0.00057 | $0.00660 |
| Haiku 4.5 | $0.00028 | $0.00330 |
Grade A, and why
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 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic multi-slide carousel brief: "make an IG carousel about X", "5-slide LinkedIn post", "swipe-through deck", "story-style series of N slides", "multi-style carousel with 6 aesthetics", "explainer carousel for our launch". Any subject — the skill is subject-agnostic.
DO NOT FIRE when:
- The brief is for ONE still (poster, drop graphic) → use
/posterinstead. - The brief is for N static ads across registers (FB / Meta ad pack) → use
/fb-creativesinstead. - The brief is for a video (the slides animate, the mascot moves) → match a
/ralphy-ugc-*video skill + editor playbook. - The user points at one specific carousel to reproduce → that is the remix path. See
docs/skills-vs-templates.md.
What this skill is
A generalized cover-first / dual-ref / mascot-fit overlay, not a finished carousel. It does not name a mascot, a topic, or an aesthetic — it tells the art-director HOW multi-style carousels are built so a strong one comes out for whatever the user is pushing. It runs through ralphy generate image; no HyperFrames compose stage is needed when the text bakes inside the image.
Hard invariants
- All generation routes through
ralphy generate image(no raw API). ReadMODELS.mdbefore naming any model id. gpt-5.4-image-2for baked text on carousel slides. Validated 30/30 slides onralphy-carousel-001for 1-2-line headlines + small label + sub-line legible and spelled right. gemini smudges small embedded type — don't finalize there.- Carousel batches serialize per style, but parallel across styles is fine. Don't run two bg gen-loops on the same OpenRouter key writing to the same prompt files at once.
- Never mutate prompt-input files while a background gen-loop is reading them. The gen loop
cats each prompt file per iteration — a mid-flightrmormvcorrupts the batch. Edit / delete prompt files AFTER background jobs finish (or before they start). Seeralphy-carousel-001Finding B. - Append-only on regen. Re-rolling a slide writes
.v2.png; the pre-fixpunk-01.v1.pngandacid-01.v1.pngstay on disk for A/B. - The reference-required gate fires when the brief names a real person / branded product / IP in a slide subject. A no-name mascot + a fictional brand proceeds without a ref.
- The quality gate refuses, not warns — two failed
scoreImagein a row → stop and report options.
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 · 176 lines · 285 tokens per session scan A 53bf90374a6b
carousel is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 285 tokens to every session and 3,302 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.