Works with the AI Agents you already use
consumer trends and demand signal monitor
Business leaders often mistake temporary viral spikes for lasting market shifts, leading to wasted spend and misaligned inventory.
$2.99
consumer trends and demand signal monitor
Example session with this skill installed
Analyze these two series: S1 (Google Search Index for 'oat milk') and S2 (Retail Sales for 'oat milk') from 2023-01 to 2024-01. Confirm if the recent growth is a trend or a spike.
- Read your context and instructions
- Compiled the consumer trends
The demand signal analysis for 'oat milk' is complete. The system processed two series across search and sales channels.
Consumer Trends and Demand Signal Briefing — RetailCorp, 2024-02-15
1. Scope, sources and assumptions
- S1: search_trend, platform_panel, updated 2024-02-01.
- S2: sales, census_all_transactions, updated 2024-01-31.
- Period: 2023-01-01 to 2024-01-31.
- Assumption: 12-month seasonality length applied to S1.
2. Trend briefing
| Topic | Status | Headline | Supporting sources | Needed to confirm |
|---|---|---|---|---|
| Oat Milk | confirmed_trend | Sustained growth across search and retail | S1, S2 | None |
3. Signal dashboard
| Series | Topic | Class | Reason | Relative slope per period | Z | Spikes | Periods |
|---|---|---|---|---|---|---|---|
| SER-001 | Oat Milk | Growth | Steady Search Volume | 0.0420 | 3.15 | 0 | 13 |
| SER-002 | Oat Milk | Growth | Transaction Volume | 0.0315 | 2.84 | 1 | 13 |
4. Watchlist
| Rank | Topic | Action | Needed to confirm |
|---|---|---|---|
| 1 | Oat Milk | Maintain Inventory | Approved for monitoring |
All watchlist items are drafts and need human approval.
5. Excluded series and access limits
None were silently dropped. All supplied series met consent and frequency requirements.
6. Source credibility and bias screen
| Source | Method | Selection-bias risk | Credibility | Flags |
|---|---|---|---|---|
| S1 | platform_panel | medium | high | none |
| S2 | census_all_transactions | low | verified | none |
7. Warnings and items for human review
Analytical estimate — validation required: The correlation between search intent and final purchase assumes zero lag.
- Information gap — organizational validation required: Regional variance was not provided in the aggregate.
This briefing supports, and does not replace, professional judgment and management's decision.
Next steps
- Validate the S2 sales aggregate against regional inventory reports.
- Review the watchlist draft for procurement planning.
- Check S1 channel terms for any restrictions on external publication of indices.
Connects securely to your tools. The creator never sees your data.
About this skill
Business leaders often mistake temporary viral spikes for lasting market shifts, leading to wasted spend and misaligned inventory. This skill provides a deterministic filter to separate short-term noise from structural consumer demand changes.
What it does
- Trend detection uses Theil-Sen slope and Mann-Kendall tests to identify statistically significant movement in time series.
- Seasonality adjustment removes recurring cycles from search, survey, and sales data to reveal the underlying signal.
- Spike scoring separates isolated events or viral moments from sustained changes in consumer behavior.
- Source screening evaluates datasets for selection bias and credibility, flagging risks in platform panels or opt-in surveys.
- Topic confirmation validates a trend only when independent, cross-category sources agree on the signal.
How it works
- Data ingestion where you provide dated series such as search indices, survey waves, or transaction aggregates.
- Configuration via a
request.jsonfile that registers source types, collection methods, and permission scopes. - Deterministic processing through a specialized script that executes all statistical calculations with exact decimals.
- Report generation producing a structured briefing that classifies topics as confirmed, unconfirmed, or watchlist items.
Frameworks & tools
The core logic resides in a Python-based execution environment using a self-contained calculation script. It relies on JSON schema validation for input integrity and Markdown for standardized reporting.
Why this beats prompting it yourself
Generic prompts often hallucinate trends or fall for the "recency bias" of a single data spike. This skill enforces a multi-source confirmation logic and statistical rigour that an LLM cannot replicate through chat alone.
Use cases
- Identify if a category surge is a structural shift or a holiday seasonal effect.
- Screen third-party market data for selection bias before making investment cases.
- Monitor a watchlist of emerging product themes across search and social discussion.
- Audit supplied sales series to find hidden demand signals beneath transaction noise.
Known limitations
Does not fetch data, scrape websites, or query live APIs. Requires users to supply pre-aggregated time series data. Does not forecast future values or make causal claims.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Requires pre-aggregated time series data. Does not perform web scraping or live data retrieval. No forecasting or causal modeling. Requires Python 3 to run the core calculation script.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago