About this skill

Problem

After a product launch, public feedback often mixes press releases, marketing posts, templated praise, and emotional complaints. Relying only on official specs, sales figures, or trending topics can mislead product decisions. This skill helps identify whether key claims were delivered, which modules are receiving concentrated criticism, how competitors may attack, and whether sentiment is likely to recover or worsen over the next 1-3 months.

How It Works

The skill uses parameters such as product_name, company_name, launch_time_window, competitor_product, and focus_dimensions to run a search-denoise-quantify-analyze workflow:
- Targeting: Identify the exact product, company, and launch window, then extract official selling points as the baseline for claim-versus-experience analysis.
- Multi-source collection: Search user reviews, hands-on posts, complaints, bug reports, return feedback, and community discussions across platforms.
- Source grading: Separate professional reviews, detailed user reports, vague emotional reactions, and likely marketing noise.
- Module labeling: Map feedback to performance, system stability, battery, AI features, camera, support, pricing, and related dimensions.
- Risk assessment: Extract the top recurring pain points, classify their scope and diffusion level, and rate the risk to sales, brand image, or retention.
- Trend inference: Judge future sentiment based on PR response, fixability, and the speed of public discussion.

Limits and Caveats

This is best for launch sentiment scanning, competitor attack-surface analysis, claim validation, and reputational risk forecasting. It is not a substitute for full user research, sales forecasting, or compliance review. Results depend on the quality and timing of public sources returned by web_search and sentiment_analysis. Sample size, platform bias, and recency should be noted. If search results are dominated by homogeneous praise with little experiential detail, the output should flag possible marketing influence rather than treating it as genuine consensus.

Screenshots

Use Cases

One month after launch, a product manager checks whether the official AI selling point is widely accepted by users.
A brand PR owner screens for return issues, BUG reports, and experience shortfalls before concentrated complaints spread.
A market analyst compares competitor user satisfaction to identify the selling points our product is most vulnerable on.
A user researcher compiles real praise and core complaints within three months of launch to produce a risk assessment.

Best For

Product managers monitoring post-launch reputation who need to separate real user feedback from marketing posts.
PR owners handling social-media risk who need to spot concentrated complaints before they spread.
Market researchers doing competitive strategy who need to compare user satisfaction and experience gaps.
Decision makers evaluating product launches who need to check whether claimed selling points match real experience.