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/poster/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/poster)<a href="https://agentmods.dev/skills/alecs5am/ralphy/poster"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/poster/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/poster"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/poster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00290 | $0.02541 |
| Opus 5.5 | $0.00116 | $0.01016 |
| Sonnet 5.5 | $0.00058 | $0.00508 |
| Haiku 4.5 | $0.00029 | $0.00254 |
Grade A, and why
poster 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic still-poster brief: "make a poster for ", "drop poster", "poster-as-landing-page", "flyer", "key art", "hype graphic", "album-cover style still", "merch drop announcement image". Any subject, any aesthetic — the skill is subject- and style-agnostic.
DO NOT FIRE when:
- The user points at one specific poster to reproduce (
@template:<slug>, "remix this one", names a slug) → that is the remix path. Seedocs/skills-vs-templates.md. - The user wants a moving video (the wordmark animates, the hero talks) → match the video format / template, load the matching video craft-overlay skill (
ugc-*), and use the editor playbook, not this skill. - The user pasted
@guideline:<slug>for a register this poster sits in (photoreal humans, anti-AI-slop) → runralphy guideline show <slug>first and fold its rules into the hero-photo slot.
What this skill is
A generalized layout overlay, not a finished poster. It does not name a brand, a hero, or a palette — it tells the art-director HOW this class of poster is built so a strong one comes out for whatever the user is promoting. It runs through ralphy generate image; it does not bypass the reference-required gate or the quality gate.
Hard invariants
- All generation routes through
ralphy generate image(no raw API). ReadMODELS.mdbefore naming any model id — the stack below is a default, not a hardcode. - The reference-required gate still fires for a named real entity in the hero or product slot (a real person, a recognizable branded product, an IP). A fictional brand + an original glyph + a generic product proceeds without a ref. Make the brand glyph explicitly ORIGINAL in the prompt ("NOT any existing brand") so the model does not drift toward a trademarked mark.
- The quality gate refuses, not warns — two failed
scoreImagein a row → stop and report options. - Real-brand pre-flight: site-grounding before any prompt. If the poster targets a real brand (user's own startup, a customer's site, any URL given), dispatch a Playwright sub-agent to crawl home +
/docs+/pricing+/features+/examplesBEFORE drafting the brand-DNA or prompt. Readartifacts/refs/research.md(the sub-agent's digest), not just a WebFetch of the home page. Every{{palette}}hex must trace toartifacts/refs/tokens.json; every named API symbol in body copy or code-creative slots must trace to "Documented API surfaces" inresearch.md. Full discipline + sub-agent prompt template:.agents/skills/researcher/references/site-grounding.md. Skipping this costsotaocr-fb-001$1.20 + 5/32 hallucinated-SDK creatives.
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 · 97 lines · 290 tokens per session scan A d8c556fe875e
poster is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 290 tokens to every session and 2,541 once invoked, about $0.0012 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
schematics
Creates or refines publication-quality technical diagrams with the native generateimage tool (Nano Banana Pro through Ace or a Gemini key, GPT Image 2 through an OpenAI key), method and architecture overviews, pipelines, CONSORT and PRISMA flows, experimental workflows, biological pathways, circuits and conceptual…
visual-style-direction
Translate a creative brief, brand system, or reference set into an original, portable visual-direction system for image and video production. Use for art direction, reference analysis without imitation, design tokens, palette and contrast, typography, composition, texture and material, lighting, lens and camera…
ideogram-image
Generate, remix, edit, inpaint, reframe, background-process, describe, layerize, and upscale images with the Ideogram Developer API. Use when Codex must integrate Ideogram 4.0 or 3.0, render reliable typography or structured layouts, use style or character references, build synchronous or webhook workflows, migrate…
recraft-image-design
Design and produce raster images, native SVG artwork, brand-controlled visuals, and documented image edits with Recraft's API. Use for Recraft model and route selection, exact request construction, image-to-image, inpainting, outpainting, background work, vectorization, remix/exploration, palette and typography…
alibaba-image-models
Plan, prompt, call, edit, iterate, and productionize Alibaba Cloud Model Studio image generation with current Wan 2.7 Image, Qwen-Image 2.0, and Z-Image Turbo models. Use for Alibaba/DashScope text-to-image, multi-reference generation, instruction editing, character-consistent image sets, typography and layout work…
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.