Works with the AI Agents you already use
media coverage monitoring
Analyzes media coverage data to produce topic distribution, sentiment shares, net sentiment score, total and average reach, top stories, and daily trends. Excludes license-restricted items. Decision support only.
$1.99
media coverage monitoring
Example session with this skill installed
Analyze the 15 news mentions from June 2024 for TechCorp. Focus on the AI product launch and exclude stories with less than 5,000 reach. Data: [Source: TechDaily, Date: 2024-06-12, Reach: 15000...]
- Read your context and instructions
- Compiled the media coverage monitoring
The analysis of TechCorp media coverage for June 2024 is complete. The report includes topic classification and reach metrics for the AI product launch.
Media Coverage Analysis — TechCorp, June 2024
1. Coverage summary
The dataset included 15 mentions across 8 media outlets. After applying a minimum reach filter of 5,000, 12 items remained for analysis.
2. Topic distribution
| Topic | Count | Share |
|---|---|---|
| AI Product Launch | 9 | 75% |
| Corporate Finance | 2 | 17% |
| Sustainability | 1 | 8% |
3. Sentiment analysis
- Positive: 66.7%
- Neutral: 25.0%
- Negative: 8.3%
- Net Sentiment Score: +58.4
4. Reach metrics
- Total Reach: 245,000
- Average Reach: 20,416
- Top Story: "TechCorp Redefines LLMs" (TechDaily, 85k reach)
5. Trends
Daily volume peaked on June 12th with 6 mentions following the keynote. Trending topics shifted from technical specs to market impact over the 30-day period.
6. Coverage digest
- TechCorp Redefines LLMs | TechDaily | Positive | 85,000 reach
- The Future of Enterprise AI | Business Insider | Positive | 42,000 reach
- Quarterly Earnings Report | MarketWatch | Neutral | 12,000 reach
7. Warnings and limitations
3 items were excluded due to the reach threshold (< 5,000). 1 item was omitted based on license_status: restricted.
Next steps
- Review the raw data for the excluded stories to ensure no critical niche outlets were missed.
- Use the sentiment score to adjust the messaging for the next phase of the product rollout.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual media tracking often results in fragmented data that fails to show the big picture. This skill processes raw coverage data into a structured digest with sentiment, reach, and topic analysis.
What it does
- Topic classification generates frequency tables with counts and percentage shares for all coverage items.
- Sentiment analysis calculates positive, neutral, and negative distributions along with a net sentiment score.
- Reach metrics aggregates total and average audience reach while ranking top stories.
- Trend tracking identifies daily coverage summaries and period-over-period changes.
- Data filtering excludes items based on license restrictions or user-defined reach thresholds.
How it works
- Data ingestion reads the provided media outlet names, dates, headlines, and sentiment values.
- Request building constructs a
request.jsonfile following a strict schema including coverage arrays and parameter filters. - Execution triggers a deterministic Python script to perform the calculations.
- Reporting outputs a formatted Markdown analysis covering summary, topics, sentiment, reach, trends, and a final digest.
Frameworks & tools
The skill utilizes a self-contained Python processing script (scripts/run.py) and JSON Schema for input validation. It operates on structured media data including source, date, headline, topics, sentiment, and reach.
Why this beats prompting it yourself
Relying on an LLM to calculate sentiment shares and reach averages often leads to hallucinations or mathematical errors. This skill offloads the heavy lifting to a deterministic script, ensuring every percentage and net score is calculated accurately and consistently.
Use cases
- Analyze a batch of press mentions to see which topics dominated the news cycle.
- Calculate net sentiment scores for a brand after a specific campaign launch.
- Identify the highest-impact stories based on estimated audience reach.
- Compare coverage volume and sentiment trends between two distinct time periods.
Known limitations
This skill does not perform real-time monitoring or sentiment inference. It requires pre-labeled sentiment data and cannot verify license compliance beyond excluding items marked as restricted.
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-labeled sentiment data. No real-time feed integration. Deterministic analysis based only on provided input data.
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 1 day ago