brand reputation analyzer
Converts unstructured reviews and mentions into evidence-calibrated reputation intelligence and operational action plans.
$5
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentsbrand reputation analyzer
Example session with this skill installed
Analyze these recent reviews for our 'SwiftDash' delivery app: 'Late again, third time this week' (1 star), 'Love the interface but the driver got lost' (3 stars), and 'Best app ever' (5 stars).
- Read your context and instructions
- Compiled the brand reputation analyzer
- Generated the UI component
I have analyzed the 3 recent feedback items for SwiftDash. The sample is small and self-selected, indicating high uncertainty for broader brand health, but it surfaces specific operational friction in fulfillment and navigation.
Reputation Intelligence Summary
Scope and Data Quality
The analysis covers 3 reviews for SwiftDash. Sources include app store/marketplace feedback. The sample size is extremely low, meaning patterns are preliminary and should be treated as isolated or emerging rather than corroborated.
Executive Readout
Positive sentiment is driven by UI design and general brand affinity. However, significant negative sentiment exists regarding delivery reliability and driver navigation. A high-intensity complaint regarding repeated lateness suggests a potential operational failure in the fulfillment chain that requires immediate investigation despite the low sample volume.
Signal Normalization
| Signal | Normalized topic | Sentiment | Intensity | Evidence level | References |
|---|---|---|---|---|---|
| "Late again, third time this week" | Delivery Latency | Negative | High | Isolated (Recurring for user) | Review 1 |
| "Love the interface" | App UI/UX | Positive | Moderate | Isolated | Review 2 |
| "Driver got lost" | Driver Navigation | Negative | Moderate | Isolated | Review 2 |
| "Best app ever" | General Satisfaction | Positive | High | Isolated | Review 3 |
Complaints and Operational Patterns
| Priority | Theme | Evidence | Customer impact | Likely operational area | Confidence |
|---|---|---|---|---|---|
| 1 | Delivery Reliability | Single report of 3x latencies in one week. | High (Churn risk) | Logistics / Fulfillment | Low |
| 2 | Navigation Accuracy | Report of driver getting lost. | Moderate | GIS / Routing API | Low |
Emerging Risks
Risk: Delivery Consistency.
Status: Watch.
Trigger: User reported 3 incidents in one week.
Consequence: Rapid churn if the "Swift" brand promise is violated.
Action: Audit courier transit times for that user's region.
Recommended Actions
- Immediate response: Contact the user from Review 1 to investigate the specific route delays.
Operational improvement: Review driver-side navigation handoff to ensure addresses are passing correctly to maps.
3.
Evidence-gathering: Monitor "latency" keywords over the next 14 days to see if this is a localized or systemic spike.
Monitoring Plan
- Metric: Mentions of "late" or "lost" per 100 reviews.
- Threshold: Escalate to Ops if "late" mentions exceed 5% of weekly feedback.
- Cadence: Weekly review of negative sentiment topics.
Next steps
- Provide a larger CSV export of reviews from the last 30 days to validate the latency trend.
- Check if Review 1 and Review 2 originated from the same geographic zone.
brand-reputation-analyzer.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Unstructured feedback from reviews, social media, and support tickets is often noisy, repetitive, and contradictory. Teams struggle to distinguish isolated anecdotes from systemic operational failures, leading to misprioritized fixes and reactive brand management.
What it does
- Normalizes messy feedback by standardizing synonyms and separating multi-issue comments into distinct topics.
- Classifies sentiment and intensity at the topic level to capture nuance in mixed reviews.
- Weights evidence by frequency, recency, and source quality to separate noise from corroborated patterns.
- Identifies emerging risks and operational bottlenecks before they escalate into reputational crises.
- Generates prioritized action plans categorized by immediate response, product improvements, and monitoring thresholds.
Why this beats prompting it yourself
Generic prompts often suffer from "averaging bias" or hallucinate trends from small samples. This skill uses a rigorous evidence-calibration framework that explicitly flags sampling bias and requires corroboration across multiple dimensions before labeling a pattern as strong.
Use cases
- Audit product launches by tracking emerging complaints across app stores and social mentions.
- Monitor hospitality or retail service quality across different regions and segments.
- Analyze competitor sentiment to identify gaps in their customer experience or reliability.
- Convert high volumes of support transcripts into structured operational intelligence for product teams.
Known limitations
Requires qualitative feedback as input. Cannot infer total customer prevalence without a known denominator for the data sample.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 19 days ago
- Passed all security checks, Safe to install