Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gabrielmoreira/agent-skills-mirror --skill ecommerce-product-montagegit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/ecommerce-product-montage)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/ecommerce-product-montage"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/ecommerce-product-montage/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/gabrielmoreira/agent-skills-mirror/ecommerce-product-montage"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/ecommerce-product-montage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.01076 |
| Opus 5 | $0.00041 | $0.00538 |
| Sonnet 5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
ecommerce-product-montage 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 3d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecommerce Product Montage
Use this workflow when the goal is a short that sells, not just one that looks good. The failure mode to avoid is a pretty montage with no sales spine: strong footage, pleasant cuts, and zero reason for the viewer to act.
This workflow decides structure and sequencing for selling footage. It does
not write the ad copy — when the hook, angles, or CTA text are not given, hand
off to product-ad-video-script for the script, then come back here to assemble.
It does not re-explain music tooling — for beat-driven placement use
beat-sync-montage or music-intelligence.
This is a OpenChatCut-native workflow. Use the current project, source assets, asset-frame inspection, AV/script context, and OpenChatCut editing tools.
When to switch workflows
- No script yet, only a product/offer →
product-ad-video-scriptfirst, return here to cut. - Music should drive the cut placement →
beat-sync-montage(andmusic-intelligencefor tools). - Many clips, no selling intent, just the strongest cut →
multi-clips-to-reels. - N distinct selling variants from one pool →
batch-montage-variants, using this workflow per cut.
Workflow
- Fix the one job the edit must do: which objection it dissolves or which action it drives (save, tap, buy, follow). If the brief names none, propose one and confirm.
- Inventory the material by sales role, not by file: hero demo, UGC reaction, proof (review/result), context b-roll, price/offer card. See references/material-roles.md. Footage that fills no role is parked, not force-inserted.
- Lay the sales spine before cutting: hook (0–3s, the open loop) → pain/context → demo → proof → CTA. See references/sales-spine.md. Every beat maps to a spine position; a clip with no spine position is cut.
- Lead with the hook from a real moment, not a title card. The first three seconds either open a loop ("you are doing X wrong") or show the payoff; a logo sting as opener loses the scroll.
- Place the demo where the viewer is curious, not where the script says "demo." Demo proves the hook; if the hook is a result, demo the path to it.
- Insert proof as a pattern interrupt, not a block. One real review line or result frame beats a stacked proof montage. See references/proof-placement.md.
- Hold the CTA long enough to read. Price, offer, and the exact action each get a legible beat; a CTA flashed for one cut is a CTA nobody acts on.
- Keep claims grounded. Do not manufacture prices, guarantees, medical, or earnings claims the assets do not support. Pull offer text from the product page or user notes; if absent, ask.
- QA by the spine, not by the cut list: can a cold viewer state the offer and the action after watching once? If not, the edit sells nothing.
- Report the spine coverage and any role with no usable footage, so a thin section is flagged before shipping.
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.
- 3d ago First seen · 62 lines · 82 tokens per session scan A 854318607772
ecommerce-product-montage is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,076 once invoked, about $0.0004 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 2026-09-10.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.