Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Find Winning Ecommerce Products

ASecurity

Meta-skill for finding e-commerce winning products by correlating social hype signals with marketplace competition data and preparing deployment-ready store listings. Use when users want trend scouting for dropshipping/white-label opportunities with explicit data gates and execu…

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashexpressrailstestingapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill find-winning-ecommerce-products --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Find Winning Ecommerce Products?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Find Winning Ecommerce Products
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-find-winning-ecommerce-products/badge)](https://www.skillsdirectory.com/skills/rondoflow-find-winning-ecommerce-products)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: find-winning-ecommerce-products
description: "Meta-skill for finding e-commerce winning products by correlating social hype signals with marketplace competition data and preparing deployment-ready store listings. Use when users want trend scouting for dropshipping/white-label opportunities with explicit data gates and execu…"
category: "Data & Analytics"
author: community
version: "1.0.0"
icon: chart-bar
---

# Purpose

Identify product opportunities by combining:
1. social momentum,
2. regional demand checks,
3. marketplace competition/sales signals,
4. store deployment readiness.

This is an orchestration skill. It does not guarantee profitability.

# Required Installed Skills

- `tavily-search` (inspected latest: `1.0.0`)
- `goplaces` (inspected latest: `1.0.0`)
- `api-gateway` (inspected latest: `1.0.29`)
- Deployment target:
  - `woocommerce` via `api-gateway` (supported), or
  - `shopify` (inspected latest `1.0.1`, currently under maintenance)

Install/update:

```bash
npx -y clawhub@latest install tavily-search
npx -y clawhub@latest install goplaces
npx -y clawhub@latest install api-gateway
npx -y clawhub@latest install shopify
npx -y clawhub@latest update --all
```

Verify:

```bash
npx -y clawhub@latest list
```

# Required Credentials

- `TAVILY_API_KEY` (trend and web data collection)
- `GOOGLE_PLACES_API_KEY` (regional demand proxy via `goplaces`)
- `MATON_API_KEY` (market/deployment APIs via `api-gateway`)

Preflight:

```bash
echo "$TAVILY_API_KEY" | wc -c
echo "$GOOGLE_PLACES_API_KEY" | wc -c
echo "$MATON_API_KEY" | wc -c
```

Mandatory behavior:
- Never fail silently on missing keys.
- Always return `MissingAPIKeys` with missing variables and blocked stages.
- Continue with non-blocked stages and mark output as `Partial` when needed.

# Inputs the LM Must Collect First

- `product_niche` (example: `pets`)
- `target_region` (country/city scope)
- `target_store` (`woocommerce` or `shopify`)
- `risk_tolerance` (`low`, `medium`, `high`)
- `max_cogs` (maximum source cost)
- `min_margin_target` (percentage)
- `shipping_time_limit_days`
- `ad_angle` (problem-solution, UGC demo, before-after)

Do not propose deployment before constraints are explicit.

# Tool Responsibilities

## tavily-search

Use for trend and sourcing discovery:
- find viral product mentions and trend lists,
- gather social evidence summaries,
- locate supplier listings (AliExpress/Alibaba/web catalogs),
- extract competitor storefront/product page signals.

## goplaces

Use for regional demand proxy checks:
- query related local businesses/search entities,
- compare demand-like signals across cities/regions,
- support geo-prioritization for launch/testing.

Important limitation:
- `goplaces` is a Places API interface, not direct social trend telemetry.
- Treat it as location demand context, not a standalone trend oracle.

## api-gateway

Use for structured market and store operations when connections exist:
- marketplace/analytics connectors if available in user account,
- WooCommerce product draft creation,
- optional Search Console-like enrichment if connected.

Operational constraints from inspected skill:
- requires `MATON_API_KEY`
- requires active per-app OAuth connections (`ctrl.maton.ai`)
- API key alone is not sufficient

Capability disclosure:
- `woocommerce` is explicitly listed in inspected api-gateway references.
- `shopify` inspected skill is currently under maintenance and may be unavailable.
- `helium 10` and `jungle scout` are not explicitly listed as native api-gateway app names in the inspected version.

# Canonical Causal Signal Chain

1. `Trend Scan (tavily-search)`
- discover products with strong recent social momentum.
- candidate example pattern: `"TikTok made me buy it" + niche + last 7 days`.

2. `Social Evidence Scoring`
- score each candidate by recency, source diversity, and repeat mention frequency.
- require at least 2 independent sources for shortlisting.

3. `Regional Demand Check (goplaces)`
- check target-region relevance proxies.
- prioritize products with cross-region consistency, not one-off spikes.

4. `Market Data Gate (api-gateway)`
- attempt sales/competition metrics via connected provider.
- if Helium 10/Jungle Scout path is unavailable, trigger explicit gate message and fallback mode.

Required gate format:
- `DataGateStatus`: `available` or `blocked`
- `Reason`: missing key / missing connection / provider unsupported
- `Action`: exact remediation steps and link

If user requests Helium 10 discount onboarding:
- include user-provided affiliate URL when available,
- otherwise use placeholder explicitly as user action item: `[HELIUM10_LINK_OR_COUPON]`.

If user requests Jungle Scout onboarding:
- include user-provided affiliate URL when available,
- otherwise use placeholder: `[JUNGLESCOUT_LINK_OR_COUPON]`.

5. `Sourcing Check (tavily-search)`
- find supplier options,
- compare estimated COGS and shipping windows,
- flag risky supplier signals (unclear shipping, no ratings, poor consistency).

6. `Deployment`
- WooCommerce path: create product draft via api-gateway `woocommerce` endpoints.
- Shopify path: if unavailable/maintenance, emit blocked deployment status and WooCommerce/manual fallback package.

7. `Creative Output`
- generate product listing copy,
- generate one TikTok ad script matched to selected angle.

# Output Contract

Always return:

- `TrendCandidates`
  - shortlisted products
  - evidence score and sources

- `MarketCheck`
  - competition/sales insight
  - DataGate status and provider path used

- `SourcingTable`
  - supplier options
  - estimated COGS
  - shipping-time estimate
  - risk notes

- `StoreDraft`
  - title
  - product description
  - key benefits
  - price suggestion
  - draft payload for `woocommerce` or `shopify` (if available)

- `TikTokAdScript`
  - hook (first 2 seconds)
  - demo beats
  - CTA

- `NextActions`
  - exact steps to publish and test

# Quality Gates

Before final output, verify:
- trend evidence is recent and source-backed
- product economics satisfy user constraints
- deployment path is real (not assumed)
- unsupported integrations are explicitly disclosed
- missing keys/connections are clearly reported

If any gate fails, return `Needs Revision` with missing evidence/dependency list.

# Failure Handling

- Missing `TAVILY_API_KEY`: return `MissingAPIKeys`, skip trend/sourcing web stages, ask for seed product URLs.
- Missing `GOOGLE_PLACES_API_KEY`: return `MissingAPIKeys`, skip regional-demand stage.
- Missing `MATON_API_KEY`: return `MissingAPIKeys`, skip gateway market/deployment stages.
- Missing api-gateway app connection (HTTP 400): keep pipeline running in analysis mode and provide connection setup steps.
- Shopify unavailable (maintenance): mark deployment as blocked and provide WooCommerce/manual import fallback.
- Helium 10/Jungle Scout unavailable via gateway: disclose unsupported provider path and continue with proxy competition analysis.

# Guardrails

- Never claim a product is guaranteed to win.
- Never fabricate sales volume, margins, or review counts.
- Never hide blocked provider paths.
- Keep recommendations tied to observed evidence and declared assumptions.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →