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 joomcode/joompulse-skills --skill ml-product-analysisgit clone --depth 1 https://github.com/joomcode/joompulse-skillsWrote 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/joomcode/joompulse-skills/ml-product-analysis)<a href="https://agentmods.dev/skills/joomcode/joompulse-skills/ml-product-analysis"><img src="https://agentmods.dev/badge/skills/joomcode/joompulse-skills/ml-product-analysis/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/joomcode/joompulse-skills/ml-product-analysis"><img src="https://agentmods.dev/badge/skills/joomcode/joompulse-skills/ml-product-analysis.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 | $0.00229 | $0.04800 |
| Opus 5.5 | $0.00092 | $0.01920 |
| Sonnet 5.5 | $0.00046 | $0.00960 |
| Haiku 4.5 | $0.00023 | $0.00480 |
Grade A, and why
ml-product-analysis 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Single-Product Analysis
This skill analyzes one product and the products that compete with it, on Mercado Livre (Brasil) or Shopee Brasil, using JoomPulse market data. Given a single product — by a marketplace link, a JoomPulse link, a photo, or a row of data — it identifies the product, finds comparable listings, and returns a product card for the subject plus a ranked table of analogs. For each one it shows price, estimated monthly sales and revenue, rating and reviews; on Mercado Livre also logistics and catalog / buy-box status. Shopee has no catalogue and no buy-box, so that part of the analysis is omitted there, not left blank.
This is different from whole-catalog assortment analysis. If the user wants to know which new products to add to their store, hand off to the gap-analysis skill. This skill works on a single product the seller already has in hand.
Prerequisites
- JoomPulse MCP access is configured for the current agent environment.
- The user provides a marketplace — Mercado Livre (Brasil) or Shopee Brasil — and
one product on it: a marketplace link, a JoomPulse link, a product photo, or a
row of data (a
.csv/.xlsxfile, a pasted table, or typed fields). - The available JoomPulse tools can look up product market data on either marketplace and find comparable listings. The ways of finding comparables differ: on Mercado Livre by image, by meaning, by category and by keyword; on Shopee only by category and by title text.
If JoomPulse MCP access is unavailable, stop and explain that the skill requires JoomPulse MCP setup before it can analyze a product or find competitors.
Scope
- Mercado Livre (Brasil) and Shopee Brasil, one at a time. Other marketplaces are out of scope.
- Sales and revenue are JoomPulse estimates — not real transactions. Disclose this in every output. By contrast, price, rating, and review count are real history from the marketplace — say so. The estimates are built differently on each marketplace: on Mercado Livre from historical listing data, on Shopee from the marketplace's own rounded sold counters refined with review movement. Use the matching disclaimer.
- Prices are marketplace prices only. Do not surface sourcing prices, margins, or profit figures.
- Read-only. The skill does not sign in as the seller or modify any listing.
- Language: write in the language of the message you are answering, and default to pt-BR only when that is unclear. Never infer the language from the store, its listings or the marketplace — those are Brazilian whatever language the seller writes in, so a seller who asks in English gets the whole report in English.
- Keep the workflow invisible. The seller wants the answer, not a play-by- play. Do the analysis quietly and present only the result. If one approach to finding the product or its competitors does not work, switch to another silently; only if every approach fails do you say one short, friendly sentence.
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 Changed · +13 lines 030d60d60631
- 2mo ago First seen · 356 lines · 229 tokens per session scan A c666369bfb6b
ml-product-analysis is a skill published in the GitHub repository joomcode/joompulse-skills (54 stars, last pushed 3d ago), licensed MIT. It adds 229 tokens to every session and 4,800 once invoked, about $0.0009 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.
ml-product-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ml-product-analysisjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 229 | Claude Code |
| scenario-roblox-monetizationscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 125 | Claude Code |
| einbeziehung-online-clickwrap-browsewrapKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 42 | Claude Code |
| renewal-playbookmohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 88 | Claude Code, Codex |
| kurzfristige-preiserhoehung-lieferfristKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 72 | Claude Code |
| plattform-online-gate-rollout-rangfolgeKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 62 | Claude Code |
| stripe-paymentsjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 101 | Claude Code |