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/fb-creatives/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/fb-creatives)<a href="https://agentmods.dev/skills/alecs5am/ralphy/fb-creatives"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/fb-creatives/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/fb-creatives"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/fb-creatives.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 205 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 204 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 | $0.00315 | $0.04547 |
| Opus 5.5 | $0.00126 | $0.01819 |
| Sonnet 5.5 | $0.00063 | $0.00909 |
| Haiku 4.5 | $0.00032 | $0.00455 |
Grade A, and why
fb-creatives scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
How to make an N-creative FB / Meta / IG static ad pack for a real brand — generalized niche know-how, not one specific ad. A domain overlay on the standard pipeline: supplies the 5-set creative matrix (A real-people · B How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
FIRES on a generic N-creative ad-pack brief: "make 32 FB creatives for ", "ad pack for ", "set of Meta ads", "creative matrix", "8-10 static ads for IG feed", "performance creatives for our cold-traffic campaign". Any brand, any vertical — the skill is brand-agnostic.
DO NOT FIRE when:
- The brief is for ONE still (poster, drop graphic, hero image) → use
/posterinstead. - The brief is for a moving video (UGC / unboxing / talking-head) → match the matching
/ralphy-ugc-*skill. - The user points at one specific ad to reproduce (
@template:<slug>, "remix this exact ad") → that is the remix path. Seedocs/skills-vs-templates.md. - The user pasted
@guideline:<slug>for a register the pack sits in (photoreal humans, anti-AI-slop) → runralphy guideline show <slug>first and fold its rules into the A-set portrait prompts.
What this skill is
A generalized matrix overlay, not a finished ad pack. It does not name a brand, a hero, a price, or a number — it tells the art-director HOW a multi-register static ad pack 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 site-grounding invariant.
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. - Real-brand pre-flight: site-grounding before ANY prompt. When the brief names a real brand URL, dispatch a Playwright sub-agent to crawl home +
/docs+/pricing+/features+/examplesBEFORE drafting brand-DNA. Readartifacts/refs/research.md(the sub-agent's digest), not a singleWebFetchof the home page. Every palette hex in a prompt must trace toartifacts/refs/tokens.json; every named API symbol in code-creative slots must trace to "Documented API surfaces" inresearch.md. Skipping this costsotaocr-fb-001$1.20 (wrong-palette v1 burn) + 5/32 hallucinated-Python-SDK creatives. Full discipline:.agents/skills/researcher/references/site-grounding.md. --ref artifacts/refs/hero.pngon EVERY gen. Once captured, pass the live-site hero screenshot as--refon all N creatives. Brand-palette + type drift across the pack drops to near zero. Without it, each prompt re-interprets "blue CTA" slightly differently — at 32 concepts the drift compounds.- Verify SDK / API surface before any code-creative. If the C / E sets render code on screen, the named API symbol (
import foo,foo.parse()) must exist on the brand's docs. If the landing only documents curl, the ad shows curl — not an invented Python wrapper. Curl is the strictly-safe fallback for HTTP APIs. - Append-only on regen. Re-rolling a slot writes
.v2.png, never overwrites. Failed / dark-bg v1 generations stay on disk as A/B reference. - The reference-required gate still fires for named real persons / IPs in the A or D set — refuse without a ref or logged
--no-ref-consent. - 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 · 208 lines · 315 tokens per session scan A c00ab4d43559
fb-creatives is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 315 tokens to every session and 4,547 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.