- Home
- Skills
- Research & Analysis
- Content Analytics Evidence Mapper
More screenshots
Works with the AI Agents you already use
Content Analytics Evidence Mapper
Turn supplied content metrics into comparable evidence and one controlled experiment—without pretending correlation proves impact.
$11
Content Analytics Evidence Mapper
Example session with this skill installed
Analyze this content table and compare format using engagement_rate = engagements / impressions × 100. Hold platform, account, audience state, and the 48-hour exposure window constant. I want one testable next experiment, not a prediction.
- Read your context and instructions
- Compiled the content analytics evidence
Demonstration Output
VERDICT: DESCRIPTIVE_ONLY
The fictional matched cohort contains two short-video items and two static-image items. Median engagement rate is 4.25% for short video and 3.00% for static image, a calculated difference of 1.25 percentage points in this supplied window.
DECISION: DESCRIPTIVE_ONLY
├─ Metric: engagements / impressions × 100
├─ Comparable stratum: same fictional platform, account, audience state, 48h
│ ├─ short-video: n=2, median=4.25%, range=4.00–4.50%
│ ├─ static-image: n=2, median=3.00%, range=3.00–3.00%
│ └─ observed difference: +1.25 points for short-video; not causal
├─ Limitation: small selected sample; representativeness unknown
└─ Proposed test: change format only and retain the same topic and publish slot
Next action: run the proposed one-variable test across the declared observation window and evaluate the same formula. No future reach, conversion, sales, or algorithm claim is produced.
Connects securely to your tools. The creator never sees your data.
About this skill
Compare content metrics without inventing causation
Content dashboards make it easy to compare numbers that should never be compared: different exposure windows, audience states, account scopes, metric definitions, or denominators.
Content Analytics Evidence Mapper validates a supplied export or pasted table, calculates only declared rates, and compares formats or other variables inside compatible cohorts. It then converts one useful descriptive difference into a bounded experiment with one changed variable and a visible decision rule.
What it delivers
- A clear
DESCRIPTIVE_ONLY,INSUFFICIENT_COMPARABILITY, orBLOCKEDverdict - Declared metric formulas with numerator, denominator, and scale
- A compact cohort map with counts, medians, ranges, and missing coverage
- Explicit limitations and refused inferences
- One proposed experiment with a baseline, hold-constant fields, observation window, and decision rule
Boundaries
It does not scrape platforms, access accounts, predict reach or sales, establish causation, write posts, or build a content calendar. If no usable input is supplied, it runs a labelled fictional Demonstration Output.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Analyzes supplied data only. It does not scrape platforms, access accounts, predict reach or sales, establish causation, write posts, or build a content calendar. Ambiguous metric definitions or incompatible cohorts produce an explicit blocker. Cross-model behavior and marketplace outcomes remain unverified.
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 2 months ago