Maintain a ranked opportunity database with provenance and deduplication.
npx skills add https://github.com/nmrtn/nanopm --skill pm-opportunities
Please help me install this Agent Skill. Skill: pm-opportunities Source: https://github.com/nmrtn/nanopm/tree/main/pm-opportunities Command: npx skills add https://github.com/nmrtn/nanopm --skill pm-opportunities
Build and maintain a ranked database of user opportunities (Teresa Torres-style — the user problems behind what you build, not the solutions). Stored as an LLM-wiki under .nanopm/opportunities/: one file per opportunity + a ranked INDEX, a LOG, and an editable SCHEMA. Bootstrap drafts the initial set from feedback + your assumptions + Nano's hypotheses; add captures one problem at a time. Two levels only (Theme → Opportunity); no scoring at v1 — a coarse priority instead.
Bootstrap the initial opportunity DB using the bootstrap phase and review the resulting INDEX.md before writing.
High-intent search queries and answers about installing and using this skill.
To build a database of user opportunities, bootstrap the initial set from user feedback, internal assumptions, and generated hypotheses. This creates an LLM-wiki under .nanopm/opportunities/ containing a ranked INDEX, a LOG, and an editable SCHEMA.
Capturing product problems instead of features requires a Teresa Torres-style opportunities database. It uses a two-level hierarchy (Theme → Opportunity) with explicit provenance tagging (evidence-backed, user-stated, or nano-hypothesis) to distinguish actual user needs from proposed solutions.
Maintaining provenance and preventing duplicates in an opportunities database is handled through safe write governance. The system automatically deduplicates entries, reindexes INDEX.md, and logs all changes to LOG.md to maintain an auditable trail of evidence-backed user problems.
Yes, you can use a two-level hierarchy to organize user problems for LLM processing. The schema is strictly limited to Theme → Opportunity with no scoring at v1, using a coarse priority instead to keep the dataset structured for LLM-wiki retrieval.
To generate new product opportunities across existing themes, use the generate lifecycle mode. This workflow drafts candidate opportunities based on the current schema, while the add mode captures individual problems one at a time for incremental dataset evolution.
huuhiep0303Guide users through divergent and convergent thinking to refine raw ideas.
kasperjungeDefine outcomes and success metrics for early-stage product strategy.
jsagirTrack grant opportunities across discovery, research, application, and submission stages.
SethGammonMaintain a markdown knowledge base with interlinked topics and an index.
