product-discovery-skills

Rank customer opportunities from a clustered-opportunities artifact. Ranks ONLY the phase-specific clusters - it never merges a person's recurring need into one ranked object. Cross-phase persistence is surfaced as an annotation on each linked cluster plus a non-ranked persistent-needs map, so the roadmap keeps the per-phase granularity it needs to prioritize between solution surfaces. Reads importance recorded upstream, counts prevalence per cluster, and shows the winner under three decision lenses - by importance, by prevalence, and balanced - with a single recommended focus.

Extract customer opportunities and insights from each ICP-screened interview transcript. Appends a bulleted detected-items section to the bottom of every transcript file. Does not rank or prioritize - pair with opportunity-sizer for cross-transcript scoring.

Cluster opportunities across ICP-screened transcripts into a deduplicated list, with each cluster carrying a customer-voice label, a phase, and a list of supporting interviewees with verbatim quotes. Hard-partitions by phase (Torres' moments-in-time rule). Writes one artifact in the TEMP folder, ready for opportunity-sizer downstream.

Screen interview transcripts against an Ideal Customer Profile (ICP). Copies matching transcripts into a temporary folder with a screening overview, ready for downstream analysis.

Strip the 'Opportunity Analyst Skill detected Opportunities and Insights' section from every transcript in a folder, so the opportunity-analyst skill can be re-run cleanly. Sibling skill to opportunity-analyst.

Build a phase map for a Job-to-be-Done (JTBD) before opportunity extraction. Drafts top-down with the user, then validates against 3 deterministically sampled ICP-screened transcripts. Outputs a phase-map artifact inside the TEMP folder, ready for opportunity-analyst to use as a controlled vocabulary for tagging opportunities to phases.