From product-eval
Drafts leadership decision artifacts (narrative, FAQ, decision memo) from existing research evidence, forcing a yes/no or option choice with a recommendation and explicit ask.
How this skill is triggered — by the user, by Claude, or both
Slash command
/product-eval:write-briefThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Produce the human decision artifact for a decided problem or bet, in the requested style. Narrative and FAQ styles persuade and align humans around the problem, why now, impact, and ask; memo style forces a yes/no or option choice with a recommendation and explicit ask. It is not an implementation spec. Each style renders from the same `.product-eval/<scope>/` content (problem, evidence, themes...
Produce the human decision artifact for a decided problem or bet, in the requested style. Narrative and FAQ styles persuade and align humans around the problem, why now, impact, and ask; memo style forces a yes/no or option choice with a recommendation and explicit ask. It is not an implementation spec. Each style renders from the same .product-eval/<scope>/ content (problem, evidence, themes, scores, decision). Never invent metrics, owners, or dates, write "Not provided in input" instead.
The brief is gated on decision-readiness. Check the item's latest verdict in .product-eval/<scope>/decisions-log.md: if there is no passing (Decide-now) verdict, or the latest outcome is "Run a research sprint", do not produce a confident brief. Say so, and offer a "decision-readiness brief" that states the gaps and points to design-test for the cheapest validating test instead.
Also run the conformance preflight in DATA-CONTRACT.md (Validation) on the scope files you render from; if scores.md, themes.md, or decisions-log.md fails a check, report the violation rather than rendering a brief from inconsistent data.
--style narrative | faq | memo | bothA flowing readout: problem → why now → proposed solution → customer & business impact → success metrics → the ask. Prose, not bullets; one quantified claim early; explicit before/after; no unsupported roadmap commitments. Optional press-release voice (write it as if already shipped). Structure and starters in references/opportunity-brief.md.
The hard-questions version, the completeness gate. Answer the question bank in references/opportunity-brief.md (problem, customer, timing, alternatives, limitations, out-of-scope, failure modes, success metrics, one-way doors, …). This version is also the scaffold the critique lens-panel attacks before the doc is "done".
A decision-oriented memo that forces a yes/no or option choice by a deadline, for driving a decision, not persuading. Headings in order: purpose & decision requested (one sentence + deadline) · executive summary (customer + business impact) · current state & evidence (each claim with source + strength) · root cause · options considered (≥3 incl. do-nothing; table Option | Summary | Benefits | Tradeoffs | Key risk | Why not selected) · recommended strategy (falsifiable success/failure criteria) · metrics scorecard (Metric | Baseline | Target | Owner | Date) · economics if relevant · risks/dependencies/mitigations (owner + close date) · the ask (concrete, owner- and time-bound). Run critique on the recommendation's falsifiability and whether do-nothing is honestly weighed.
Narrative as the readout, FAQ as the backing appendix.
references/opportunity-brief.md.critique (panel mode) on the FAQ and tag each answer resolved / open / contested before calling it done..product-eval/<scope>/docs/.The brief in the requested style plus the critique summary (resolved / open / contested counts). Lead with the one-paragraph essence. End with Next move: and recommend resolving open FAQ items, pressure-testing the plan if commitment risk remains, or turning the approved decision into a build brief.
npx claudepluginhub sparkline-ventures/product-evalCreates shareable briefing documents from sessions, research, or learnings. Generates dual-audience formats like proposals, summaries, and research syntheses for humans and AI agents.
Creates one-page decision briefs with conclusion-first layout, options comparison table, risk mitigation section, and next steps. Designed for executive updates, elevator pitches, or board summaries.
Structures product decisions into concise docs with options, trade-offs, comparisons, recommendation, reversibility, and next steps for stakeholder review.