The Sentiment Map
Track how audiences respond emotionally to your competitors over time
You see what competitors post but miss how audiences actually feel about it. By the time a sentiment shift shows up in sales data, you have already lost weeks.
That is the gap this drop closes. It is a marketing skill built for Claude, and it takes about ten minutes to set up the first time. After that it runs in under a minute.
Who should use it
Marketing managers who already monitor competitor activity and need to spot shifting sentiment before it becomes a trend
How it works
The skill file does five things, in this order.
1. Collect response samples. Copy recent comments, reviews and social replies from three competitor touchpoints into Claude.
2. Request sentiment coding. Ask Claude to tag each response by dominant emotion and whether it suggests satisfaction, frustration or indifference.
3. Identify pattern clusters. Have Claude group similar sentiments and flag recurring themes that appear across multiple sources.
4. Compare time windows. Run the same analysis on older data from four weeks back and ask Claude to highlight what changed.
5. Extract strategic signals. Ask Claude what the sentiment shifts suggest about competitor strengths wearing thin or new vulnerabilities opening.
What comes back
A coded sentiment archive that shows you which competitor promises are losing credibility and where audience patience is thinning
The mistake to avoid
Run this monthly, not daily. Sentiment shifts that matter take weeks to build. Track the same competitor touchpoints each time so your comparison stays consistent.
Running it
Save this as SKILL.md inside a folder named after the skill, then drop the folder into your Claude Code skills directory or upload it to a Claude Project. Claude reads the frontmatter to decide when the skill applies, so keep the description line intact. For a one-off run, paste the prompt block directly.
Where this fits
On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.
In the file
I am tracking competitor sentiment over time. Below are audience responses to {competitor_name} collected from {source_types} during {time_period}.
{response_data}
Please:
1. Tag each response with the dominant emotion (e.g. trust, frustration, disappointment, enthusiasm, skepticism, indifference)
2. Code each as suggesting satisfaction, dissatisfaction or neutral stance
3. Group responses that share similar themes or concerns
4. Identify recurring phrases or concepts that appear multiple times
5. Flag any responses that indicate a change in expectations or a broken promise
6. Summarize the overall sentiment profile in three sentences
Present your analysis in a table with columns for response excerpt, emotion tag, satisfaction code and theme cluster. Then list the top five recurring themes with frequency counts.
If I provide a second dataset from an earlier period, compare the two and highlight:
- Sentiments that have intensified or weakened
- New themes that emerged
- Themes that disappeared
- Strategic implications for positioning