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-model-swap/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-model-swap)<a href="https://agentmods.dev/skills/alecs5am/ralphy/ugc-model-swap"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-model-swap/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-model-swap"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/ugc-model-swap.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 | $0.00199 | $0.01660 |
| Opus 5 | $0.00100 | $0.00830 |
| Sonnet 5 | $0.00040 | $0.00332 |
| Haiku 4.5 | $0.00020 | $0.00166 |
Grade A, and why
ugc-model-swap 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a swap brief: "same video but with a different girl/guy", "recreate this clip with ", "give me 4 versions of this clip with different people", "swap the creator in this UGC video".
DO NOT FIRE when:
- The user wants a brand-new ad authored from a product (no source clip to mirror) →
/ugc-ad. - The user wants a different niche of video → match that niche's skill.
What this skill is
The craft specialist for the swap kind of remix. The user supplies a source clip and a replacement person/character; this skill mirrors the source faithfully and changes only the on-camera subject. It runs through ralphy generate / ralphy render like everything else.
Hard invariants
- Provider invariants stand. Source analysis, generation, and render all go through
ralphy(ralphy ref analyze-video <slug>for the source breakdown;ralphy generate videofor the swap;ralphy render). No Higgsfield MCP, no raw API. ReadMODELS.mdbefore naming a model id. - Model choice is the trap — get it right (per
MEMORY.md):- Photoreal human replacement →
kwaivgi/kling-v3.0-pro.bytedance/seedance-2.0blocks photoreal-human i2v anchors (privacy filter), even AI-generated ones — it fails the swap. Do NOT reach for seedance for a realistic person, regardless of what a non-ralphy tutorial claims. - Stylized / non-human character (cartoon, creature, mascot) →
bytedance/seedance-2.0is fine and often better for non-default physics motion. The privacy filter only bites photoreal humans.
- Photoreal human replacement →
- Reference gate. If the replacement is a named real person ("make it Tom Cruise"), the reference-required gate fires — refuse without a ref or logged
--no-ref-consent. A generic replacement ("a young woman with red hair") proceeds without a ref. - Don't recreate copyrighted source audio. Mirror the structure of the source; the user supplies/approves the actual VO and music.
The craft, in five rules
- Single continuous scene — no numbered splits. Describe the entire video as ONE flowing paragraph. "Scene 1 / Scene 2" labels confuse i2v models and break continuity.
- Face always in frame — state it repeatedly. If the action has the subject look down, reach, or place something, the camera must NOT follow. Put the lock inline in the action AND as a closing rule: "FACE IS ALWAYS CENTER FRAME. Camera locked on the face. Never tilts down. Never follows the hand."
- Props — hyper-specific, with negatives. If there's one prop, forbid the variations the model invents: "only ONE standalone ice cube resting in the palm — no bucket, no bowl, no container, no pile."
- Body mechanics — describe the motion, not the intent. Not "she puts it away" → "she deliberately reaches her hand down and tucks the cube into the waistband, her hand moves below frame, the object disappears from view." Specific mechanics = faithful output.
- Lock the setting up top. Open the prompt with the interior/exterior + lighting ("INTERIOR kitchen, soft window light, blurred counter behind") before any action, or the model relocates the scene.
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.
- 10d ago First seen · 77 lines · 199 tokens per session scan A b16f5c14f018
ugc-model-swap is a skill published in the GitHub repository alecs5am/ralphy (133 stars, last pushed today), licensed Apache-2.0. It adds 199 tokens to every session and 1,660 once invoked, about $0.0010 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
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.
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.
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…
open-video
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future). Use when the user wants to turn a concept, script, or reference image into a finished video or multi-shot film — single shots, image-to-video, first-last-frame interpolation, reference-video/audio styling, or stitched…
image-generation-gateways
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI…
runway-video
Build and operate production-safe Runway API video generation, video editing, and character-performance workflows with native Runway models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance.