gooseworks-ai/goose-skills / skills/shared/comment-mining
comment-mining
VerifiedMine comments and replies on social posts, videos, and ads for recurring customer language, questions, objections, desired outcomes, complaints, product requests, purchase signals, and creative opportunities. Use for voice-of-customer research grounded in linked source evidence.
Comment Mining
Turn public comment threads into evidence a growth team can use.
Inputs
- Brand/product and research question.
- Post, reel, video, or ad URLs; or creators/competitors to sample.
- Target market, platforms, time window, and desired sample size.
Workflow
- Use
scrapecreators-apito collect post context, top-level comments, and replies from the relevant platforms. Sample across multiple posts and creators instead of overfitting to one viral thread. - Preserve parent-and-reply context where it changes meaning. Remove obvious spam, duplicate comments, tag-only replies, and giveaways unless they are the subject of the study.
- Code each useful comment into one or more buckets: pain, desired outcome, objection, question, comparison, use case, purchase intent, product request, workaround, delight, complaint, churn risk, or exact product language.
- Mark buying-intent strength separately: curiosity, consideration, price or availability question, comparison, stated purchase, repeat use, and recommendation.
- Cluster semantically similar statements while retaining representative wording, the post context, and source links.
- Report prevalence as sample counts by platform and source type, not market-wide percentages.
- Convert the strongest clusters into testable messages, hooks, FAQ topics, product questions, or research follow-ups.
Output
- Coverage and sampling method.
- Ranked theme table with top-level and reply counts, representative language, source links, and confidence.
- Objection and question bank.
- Purchase, product-request, workaround, and churn signals.
- Recommended next tests for creative, landing pages, content, or product research.
- Limitations and gaps.
Never expose private information, infer sensitive traits, or claim the sample represents all customers.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |