メニュー
High-level concept research grounded in best practices and top 1% PM thinking.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Apply Jobs-to-be-Done (Christensen / Competing Against Luck flavor) to a feature idea, document, or problem statement. Produces a JTBD canvas with the job, the struggling moment, desired progress, current alternatives, and hire/fire criteria. Flags where the stated feature is a solution masquerading as a job, and where evidence is thin. Use when shaping a feature, challenging a brief, or interpreting customer research.
Apply MoSCoW prioritization (Must / Should / Could / Won't) to a list of candidate solutions, defending each placement against explicit criteria and inviting challenge. Designed for discussion mode — never just outputs a table, always defends placements and surfaces where MoSCoW is the wrong framework. Use after OST when shaping a feature, or directly when you have a solution list and need to negotiate scope.
Build an Opportunity Solution Tree following Teresa Torres' Continuous Discovery format, pragmatic variant — allows inferred opportunities marked as hypotheses when evidence is thin. Takes a JTBD canvas plus context and produces a tree with desired outcome, clustered opportunities, candidate solutions, and assumption tests for the riskiest paths. Use after JTBD when shaping a feature, or directly when an outcome is already clear.
Produce a Monday-morning standup-style recap of the previous week's merged work, drawn from git history, GitHub PRs, and linked GitHub Issues. Output is technical-but-narrative — the way a tech lead would brief their PM. Groups work by product area, anchors each item to its issue/epic title where one exists, and explains the problem each merge solved. Use on Monday mornings or when catching up after time away. Default window is the previous 7 days.
Scaffold this repo with the Builders Camp Claude OS (CLAUDE.md, skills, standards, registries). Use for new projects.
Full architecture, code quality, tests, and performance audit for large changes.
| name | research |
| description | High-level concept research grounded in best practices and top 1% PM thinking. |
| disable-model-invocation | false |
| allowed-tools | Read, Glob, Grep |
| argument-hint | [decision or topic to research] |
Output: Decision: Best practices: Common mistakes: Top 1% considerations: Recommendation:
Stop after recommendation.
