riskiest-assumption-test
Walks the founder through assumption dump, risk × impact ranking, falsifiable hypothesis rewriting, and test-method selection — produces a 1-page Assumption Test Plan with the top 3 ranked hypotheses, success/kill criteria, and an interactive HTML risk × impact matrix. Use after `validation-canvas` and BEFORE `pitch-deck` — pitching on untested assumptions is sales theater. Triggers on phrases like "test my assumptions", "riskiest assumption", "RAT", "what should I validate first", "assumption mapping", "experiment design", "how do I de-risk this", "Wizard of Oz test", "fake door test", "concierge MVP", "smoke test", "pre-sale validation", "5-interview rule", or when the user has `validation-canvas.md` with populated Stress Tests and asks what to do next. Job — "what have we proven?" (experimental). This is the upstream half of validation closure; the downstream half is updating the canvas based on results (loop-back). NOT a discussion of testing in general (use `team-composer`); NOT a generic experiment plat
Repository SourceNeeds Review
brand-workshop
Simulate a collaborative branding team to create a launch-ready brand identity package from a business overview. Use this skill whenever the user asks to create a logo, brand identity, tagline, or brand concept for a business, product, app, or project. Also trigger when the user says things like "help me brand this," "I need a logo," "come up with a tagline," "brand identity for my app," or provides a business description and asks for visual identity work. This skill runs a structured multi-role brainstorming workshop and produces: a brand strategy brief (.md), tagline, code-generated logo (.svg), favicon pack with HTML install snippet, social banner set (OG / X / LinkedIn / Instagram), descriptions pack (tagline + bios + elevator pitch + boilerplate), and a starter design-system.md (tokens only). Even if the user only asks for a logo or only a tagline, use this skill — the full workshop produces better results. For pitch decks, hand off to the `pitch-deck` skill, which consumes `design-system.md` directly. D
Repository SourceNeeds Review
startup-grill
Adversarially grill a startup idea or pitch with a panel of domain-aware probers (VC partner, growth marketer, founder strategist, UX researcher, plus a flexible technical-or-brand fifth seat and up to 3 domain specialists from team-composer's catalog), and ship a structured kill report ranked across two axes — severity (lethal vs material) and fixability (fixable vs unfixable). Use this skill when the user says: "grill my startup", "grill this idea", "stress-test my pitch", "pressure-test my idea", "roast my pitch", "rip apart this", "tear apart my deck", "kill my idea", "pre-mortem my startup", "find the weaknesses in my idea", "what would kill this startup", "what would a VC hate about this", "give me brutal feedback on my deck", "be ruthless about this idea", "where would this fail", "is this fundable", "investability check", or uploads a one-pager / validation-canvas.md / RAT plan / pitch deck and asks for adversarial review. Use this skill — NOT `team-composer` — whenever the user wants an *adversarial*
Repository SourceNeeds Review
team-composer
Assemble the right virtual team for brainstorming, planning, or building a project or feature — tech, healthcare, finance, climate, biotech, and beyond. Use this skill whenever the user asks to "brainstorm," "discuss," "plan," "review," or "build" a project or feature and doesn't specify exact roles. Also trigger when the user says things like "bring a team," "who should be involved," "let's workshop this," "assemble a team," or asks for multi-perspective feedback on a product decision. This skill analyzes the project context and selects the optimal set of role-based personas to contribute meaningfully. Even if the user only mentions one or two roles, use this skill to fill in the gaps — a well-composed team produces better results than ad-hoc role selection.
Repository SourceNeeds Review