The-Utopia-Studio
- 131 skills
- 0 followers
- 14 hours ago last updated
- ▌ Concept Council · the-utopia-studio bundleFirst-contact teardown of a raw product idea. Fires when a fellow says "here's my idea", "tear this apart", "rip this concept apart", "what am I missing", or "what should I build first". Convenes five adversarial lenses, names the one load-bearing gap, and returns a Gap Map plus one First-Probe Brief costing under a week. NOT for an already-scoped concept you want stress-tested against the five so-whats (use so-what-stress-test) or scored numerically across eight dimensions (use problem-quality-scorecard).
- ▌
- ▌ Dataset Builder · the-utopia-studio bundleTurn field artefacts into a labelled dataset and 20+ golden cases — the seed of the eval suite that gates the build. Attaches a ground-truth label to every real artefact, scores each label on the evidence ladder, and clears each case through four gates (provenance, ground-truth, unreachable, held-out) so a foundation model cannot pre-pass its own memorised test. Fires on "make our own dataset", "create golden cases", "label this", "turn our field logs into a test set the model hasn't seen", "seed the eval suite". Not for finding which sources are proprietary in the first place (use yoda-data-sourcing, section 03), not for composing the labelled cases into the four-band spread / autonomy level / cost budget of a scoreable spec (use eval-first-spec, section 07), not for splitting an expert's teachable procedure from show-only judgment (use explicit-vs-tacit-capture, section 03).
- ▌ Design Critique · the-utopia-studio bundle냉철한 디자인 비평 스킬. 15년 경력 수석 디자이너 페르소나로 UX, 비즈니스 목표, 시각적 원칙을 기준으로 제출된 디자인(이미지, 코드, URL, 기획안)을 분석한다. 4개 평가 기준 + 날카로운 질문 2개 + 우선순위 액션 플랜 3개를 고정 포맷으로 출력. 브랜드 디자인 시스템이 존재하면 이탈 여부를 반드시 검증한다. 트리거: '비평해줘', '리뷰해줘', '뭐가 문제야', '피드백 줘', '크리틱해줘', '어떻게 생각해'.
- ▌ Eval First Spec · the-utopia-studio bundleTurn a validated wedge into the scope you can SCORE — a one-sentence job, 20 pass/fail golden cases drawn from real artefacts, an L0–L4 autonomy level with a failure taxonomy and a derived acceptable failure rate per mode, and a cost-per-outcome budget to the cent. Fires on "spec the build", "define scope", "scope the v1", "write the spec", "how do we know it works". Not for the component pipeline or effort split (use compound-system-architecture), not for pilot price / terms / commercial success metrics (use pilot-six-term-sheet), not for whether the thing gets adopted at all (use wedge-five-questions).
- ▌ Evidence Ladder · the-utopia-studio bundleWeights a pile of "validation" by what people DID, not what they said. Takes interview quotes, sign-ups, LOIs, pilots, payments and places each on one ladder — money moved 1.0, behaviour observed 0.7, artefact shown 0.5, verbal commitment 0.3, opinion 0.1 — then returns a weighted evidence table, the weight of the load-bearing claim, and for every low signal the cheapest probe that raises it a rung. Fires on "how strong is this signal", "score the interview", "did they actually validate", "weight this evidence", "is this real validation". NOT a build gate on a problem (use problem-quality-scorecard), NOT a picker for which test to run next (use probe-matrix), NOT a transcript summary (use summarize-interview). This is the reference skill the rest of the module cites for the ladder.
- ▌ Prompt Engineer · the-utopia-studioMakes a repository AI-native by creating AGENTS.md, .cursorrules, and documentation that helps any AI agent understand the codebase. Follows the WHAT/WHY/HOW framework from best practices. Use when the user asks to "make repo AI-ready", "add cursor rules", "create AGENTS.md", "set up for AI coding", or "make agents work better". Don't use for deployment (use deployment-engineer), monitoring (use monitoring-setup), or code organization (use repo-structurer).
- ▌ Metrics · the-utopia-studio bundleThis skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance. Covers questions like "how much memory is my service using" or "is my service slow".
- ▌ Refine Flywheel · the-utopia-studio bundleStands up the post-launch loop for a shipped AI product — ship behind sign-off → observe tweak-time (how much the customer edits before accepting) → learn by re-running the WHOLE eval set on every model release → refine by promoting autonomy only as a scored eval result, never by feel. Fires on "what happens after launch", "improve the product", "set up the loop", "a new model dropped, should we upgrade", "can we raise the autonomy / drop the sign-off yet". Returns a filled flywheel cadence doc. NOT for which metrics/North Star/retention to track (use metrics-that-matter), NOT for turning one trace into a discovery interview (use trace-to-interview), NOT for writing the eval set or autonomy ladder in the first place (use eval-first-spec — this re-runs what that created).
- ▌ Repo Structurer · the-utopia-studioCleans up and structures a repository for production. Adds README files to every directory, modularizes code, removes dead files, and makes the repo LLM-smart. Use when the user asks to "clean up", "structure", "document", or "organize" their repo. Don't use for code review or bug fixing.
- ▌
- ▌ Workflow Design · the-utopia-studio bundleFires when a fellow needs to coordinate MORE THAN ONE agent to get the work done — "design the workflow", "orchestrate the agents", "set up the fleet", "how do the agents work together", "which agents do I need and when do they spawn", "multi-agent setup". Returns a workflow + fleet map: the multi-step orchestration, a spawn-by-rule fleet (researcher, analyst, prototyper, drafter, critic) each with an observable spawn trigger, and a Think/Build/Admin surface assignment (Claude.ai / Claude Code / Cowork), then kills a single-agent design where a fleet is needed and any spawn rule with no trigger. Do NOT fire to spec ONE agent's role/tools/memory (use agent-design), to design the product's internal request-time pipeline of input→router→reason→validate (use compound-system-architecture), or to write the pass/fail eval (use eval-first-spec).
- ▌ Account Tier Scoring · the-utopia-studio bundleUse this skill when you want a production-grade account scoring system instead of a vibes-based one: it tiers every account onto a Bronze/Silver/Gold/Diamond ladder, scoring pre-conversion accounts on intent signals + ACV potential and trials/customers on activation depth + expansion headroom. It encodes the judgment that makes scoring trustworthy — a hard self-serve gate with LinkedIn headcount verification, an enterprise persona gate, anonymous-signal and social-engagement caps, prior-relationship floors, and never-demote rules — with every threshold exposed as a tunable default. Each run produces a verified tier tag and ACV tag, a prepended signal-stack snapshot in account memory, a CRM lead-score sync, and correctly routed Gold/Diamond alerts with per-stakeholder engagement recommendations.
- ▌ Cold Offer Architect · the-utopia-studio bundleUse this skill when the thing being sold to strangers isn't landing, or before writing a single line of cold copy — to build a new cold-traffic offer, audit an existing one against a hard bar, or diagnose why one that reads fine gets no replies. Covers cold email, cold DM, cold ads, and cold mail: any audience with zero trust and no reason to believe you. Produces an architected offer plus a pass/fail score against eight binary criteria. Trigger phrasings: "my offer isn't converting", "low reply rate", "nobody's booking", "fix my offer", "what should I offer", "score this offer", "is this offer any good", "we changed the copy and nothing happened".
- ▌ Email Deliverability · the-utopia-studio bundleUse this skill when emails hit spam, open rates drop, a domain or IP gets blocklisted, or a sender wants a deliverability audit before scaling volume. Triggers: "why are we going to spam", "audit my email setup", "open rates dropped", "we got blocklisted", "warm up this domain", "check my deliverability". Produces a severity-ranked audit or a root-cause diagnosis with a recovery plan and the thresholds to monitor.
- ▌ Technical Dd · the-utopia-studio bundleGenerate investment-grade Technical Due Diligence reports for The Studio (Utopia Capital). Use this skill whenever the user mentions technical due diligence, TDD, tech DD, technical assessment, technical evaluation of a company, or wants to assess whether a startup's technology works, is well-built, can scale, and what the technical risks are. Also trigger when the user uploads company materials (pitch decks, technical docs, corporate profiles) and asks for a due diligence analysis, technical review, or investment assessment focused on technology. This skill produces branded .docx reports suitable for sharing with co-investors or the company itself. Even if the user just says 'run DD on this company' or 'assess this startup' or 'review these materials', use this skill — it's the standard workflow for technical evaluation at The Studio.
- ▌ Four Lenses Test · the-utopia-studio bundleScores a specific concept across the four build-risk lenses — Desirability, Usability, Feasibility, Viability — where each lens is graded ONLY by its named tool (onion+JTBD+Kano for Desirability, a watched usability observation for Usability, a dev spike for Feasibility, ICE anchored to measured value for Viability) and run by its dual-track owner (Product/Design discovery beside Engineering delivery). Fires on "is this desirable / usable / feasible / viable", "should we build it", "run the four lenses", "go or no-go on this concept", "is this worth building". Output is a filled Four-Lens Scorecard: per-lens tool, owner, evidence + ladder weight, score, and an AND gate that KILLS the go if any single lens fails, every claim tagged [Fact]/[Assumption]/[Hypothesis]. NOT for the full problem→vision→strategy→roadmap spine (use product-frame-stack), NOT for scoring the PROBLEM on 8 dimensions (use problem-quality-scorecard), NOT for the five-question so-what gut check on the whole idea (use so-what-stress-test).
- ▌ Guardrail Design · the-utopia-studio bundleFires when a fellow needs to decide how an AI product is stopped from doing the wrong thing — "design the guardrails", "when does a human sign off", "how do we handle failures / bad outputs", "what confidence threshold should we auto-approve at", "where do we put the human in the loop". Returns a guardrail spec: every failure mode placed on a cost-of-error × volume matrix, a three-layer stack (rules in code → confidence threshold → human sign-off) sized per mode, a derived confidence threshold, and a human-sign-off trigger for every high-cost / low- confidence path. Do NOT fire to derive the acceptable failure rate or pick the autonomy level (use eval-first-spec), to lay out the whole component pipeline (use compound-system-architecture), or to decide whether a human can now be REMOVED because accuracy has held (use refine-flywheel).
- ▌ Monitoring Setup · the-utopia-studioConfigures error tracking (Sentry), product analytics (PostHog), health monitoring, and alerting. Provides verification commands and concrete output templates. Use when the user asks to "set up monitoring", "add error tracking", "configure Sentry", "add analytics", or "set up alerts". Don't use for deployment (use deployment-engineer), security (use security-auditor), or integration linking (use integration-linker).
- ▌ Security Auditor · the-utopia-studioAudits repository security — hardcoded secrets, dependency vulnerabilities, environment variable management, and authentication patterns. Use when the user asks to "check security", "find secrets", "audit dependencies", or "secure my repo". Don't use for code review, deployment, or monitoring.
- ▌
- ▌ Efecto Web Design · the-utopia-studioDesign web pages and app UIs with Efecto — create sessions, build layouts with JSX and Tailwind CSS, manage artboards, and push real-time design changes via MCP tools. Use when asked to "design a page", "build a landing page", "create a website", "design a dashboard", "make a UI", or any visual design task. Requires Efecto MCP server.
- ▌
- ▌
- ▌ Templates · the-utopia-studio bundleThis skill should be used when the user wants to add a service from a template, find templates for a specific use case, or deploy tools like Ghost, Strapi, n8n, Minio, Uptime Kuma, etc. For databases (Postgres, Redis, MySQL, MongoDB), prefer the database skill.
- ▌ Proof · the-utopia-studio bundleWeb-first skill for working with Proof documents via proofeditor.ai. Use when a Proof URL is shared, when creating collaborative docs in Proof, or when an installed Proof preference says new docs should live there.
- ▌ Salim · the-utopia-studio bundleCoach Studio fellows through the Cobuild curriculum as Salim — Utopia's fellow coach. Use when a fellow says 'I'm stuck', 'what should I do next?', 'review my [discovery/PRD/pitch]', 'I'm in M[X] and...', 'help me think through [problem]', 'can you check my [JTBD/canvas]?', or any pedagogy-style question. Salim is Socratic — he asks before telling, never produces artifacts the fellow should produce themselves, and is disciplined about Discovery before Build. He's module-aware (M1-M9) and points fellows to the right skills and frameworks. Outputs persistent cobuild logs to Proof.
- ▌ Deal Velocity Engineer · the-utopia-studio bundleDiagnose and fix deal velocity problems. Sales cycle diagnostics, stage exit criteria, pipeline deflation, zombie deal elimination, multi-threading, mutual action plans, AI-driven deal scoring, revenue intelligence integration (Gong/Chorus), and compression tactics with sourced benchmarks. Trigger on 'deal velocity,' 'sales cycle too long,' 'deals stalling,' 'pipeline velocity,' 'stage exit criteria,' 'zombie deals,' 'pipeline deflation,' 'deals stuck,' 'multi-threading,' 'mutual action plan,' 'deal inspection,' 'pipeline hygiene,' 'cycle time,' 'stage conversion,' 'deals die in negotiation,' 'we keep slipping deals,' 'reps can't close,' or 'pipeline is bloated but nothing closes.' Connects stage gates, deal scoring, inspection cadence, and pipeline deflation into the operating cadence. Includes modern AI/automation patterns (HubSpot Breeze, Salesforce Agentforce, predictive pipeline management). BOUNDARY: For forecast methodology see revops-forecasting. For pipeline visibility and dashboards see gtm-metrics
- ▌ Pitch Deck Web · the-utopia-studio bundleBuild a responsive, interactive pitch-deck website from a brand book + a PRD/example deck. Use when the user asks to "build a pitch deck", "make an investor deck", "create a sales deck", generate a deck site from a brand book, or scaffold a deck from a PRD or existing slides. Pulls brand tokens (colors, typography, voice) from a brandbook-builder-style repo, runs a guided brief (investor vs sales, copy approval, image/logo intake, reference mining), then scaffolds a Vite + React + TS + Tailwind + motion deck site mirroring the utopia-os-deck section-scroll pattern.
- ▌ Data Rights Clause · the-utopia-studio bundleDraft the data-rights clause for a fellow's first paid pilot. Run the three-part test — the data must be workflow exhaust, must compound with use, and must be covered by a clause signed at pilot
- ▌ Fellow Path Router · the-utopia-studio bundleRoutes a fellow through the Icarus module by situation type, not by tearing down one idea. Fires on "where do I start", "I already have a product / traction — which stages apply to me", "onboard me to Icarus", "which stages should I skip", "I have a mature product, what's my path". Classifies the fellow as Type A (blank page), B (traction, no moat), or C (mature product) on the evidence ladder, then returns a keep / trim / subtract / leap stage ledger and a think:build:test ratio tied to that type's dominant risk. Do NOT fire to tear down or grade one idea (use concept-council or so-what-stress-test), to assess the fellow's own skill level (use fellow-level-ladder), or to draw the platform build-vs-buy line (use platform-vs-venture).