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/ugc-ad/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/ugc-ad)<a href="https://agentmods.dev/skills/alecs5am/ralphy/ugc-ad"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-ad/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/ugc-ad"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-ad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 79 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 | $0.00231 | $0.01812 |
| Opus 5 | $0.00115 | $0.00906 |
| Sonnet 5 | $0.00046 | $0.00362 |
| Haiku 4.5 | $0.00023 | $0.00181 |
Grade A, and why
ugc-ad 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic UGC-ad brief: "make a UGC ad for ", "creator reviewing my ", "testimonial ad", "problem/solution short for ", "before/after for " (when the emphasis is a talking creator, not a pure product montage).
DO NOT FIRE when:
- The user points at one specific ad to reproduce → remix path (
ralphy template use <slug>). Seedocs/skills-vs-templates.md. - The user wants to swap only the creator/person in an existing clip →
/ugc-model-swap. - The brief is a static image ad, not video → that is a different niche.
What this skill is
A generalized overlay, not a finished ad. It tells the pipeline HOW believable UGC ads work so the scenarist and art-director produce a strong one for whatever the user is selling. It runs through the normal pipeline and never bypasses the intake gates, the reference-required gate, or the quality gates.
Hard invariants
- Provider invariants stand. All generation via
ralphy generate(OpenRouter media + ElevenLabs only — no FAL, no Higgsfield, no Canva, no raw API). Renders viaralphy render <id>. ReadMODELS.mdbefore naming any model id. - Reference gate. A named real brand product ("iPhone 16", "CeraVe cleanser") fires the reference-required gate — refuse without a ref photo or logged
--no-ref-consent. A no-name / generic product proceeds without a ref. - AI-creator faces are synthetic personas, not real people. Build a consistent non-existent creator (see workflow). Do not face-mix toward a recognizable real person.
- Music is a separate ElevenLabs pass. Kling
--audiois for the VO/lipsync only; ban music in the Kling prompt and overlay an instrumental bed in the editor stage (perMEMORY.mdKling-no-music note).
The niche, in one paragraph
A UGC ad lives or dies on believability and the first 3 seconds. The viewer must feel a real person is talking to them, not a brand. The hook is a problem mirror — show the viewer their own problem so they stop scrolling because they see themselves. Then a transformation/hope beat, then a real verdict, then a low-friction CTA. Trust comes from mannerisms (a nervous laugh, a hair tuck, direct eye contact, pointing at the product) far more than from polished delivery. The single biggest AI tell is a too-perfect, too-symmetrical creator and a studio-clean voice — fight both.
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.
- 9d ago First seen · 81 lines · 231 tokens per session scan A 152e39729a66
ugc-ad is a skill published in the GitHub repository alecs5am/ralphy (132 stars, last pushed 14d ago), licensed Apache-2.0. It adds 231 tokens to every session and 1,812 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
molecule-visualization
Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.