ommakes
UserSkills for product design
Categories
Indexed Skills (18)
design-ask
Unpacks poorly written Jira or Azure DevOps tickets into design-relevant framing. Use this skill whenever a designer pastes in a ticket description, acceptance criteria, or any product/engineering requirement and wants to understand what the actual design work is. Trigger when someone says things like "can you help me understand this ticket," "what is this ticket actually asking for," "decode this ticket," "unpack this AC," "what design work does this require," or pastes raw ticket text and asks what to do with it. Also trigger when a designer mentions they're confused about scope, unclear on requirements, or trying to figure out if something is a content change vs. a flow vs. a new pattern. This skill is especially useful when tickets are written prescriptively (they specify a solution like "add a dropdown") instead of descriptively (explaining the user need), or when acceptance criteria are written from a dev/QA perspective with no design context.
design-rationale
Help designers articulate the cognitive science, behavioral psychology, and platform standards behind their design decisions. Use this skill when a designer needs to explain why they made a decision in a critique, design review, or stakeholder meeting. Also use when auditing a screen for principle alignment, preparing for pushback, or evaluating whether a decision is truly irreversible. Trigger on phrases like: "how do I explain this decision", "what principle applies here", "help me defend this", "how would I articulate why I did this", "can you audit this screen", "what's the rationale for", or any request that involves justifying a design choice with evidence beyond personal preference.
vois-loop
Iterative design build loop for the Vois design system. Wraps design-ask, vois-router, and the full skill chain (vois-patterns, vois-components, vois-tokens, righter, design-rationale) in a loop that detects conflicts between skills and routes back upstream when something doesn't resolve cleanly. Includes an inline validation pass (no external skill required) that checks implementation correctness before design-rationale closes the loop. Use this as the single entry point for any feature build that starts from a ticket, brief, or raw description. Trigger when someone says "build this", pastes a ticket, or asks to run the full design loop.
vois-router
Orchestrates the Vois design system skill chain. Use this skill as the single entry point whenever you're doing any UI work against the Vois design system — building a screen, picking a component, writing copy, or defending a design decision. The router reads your input, identifies the right starting point and skill sequence, and packages context forward so you don't have to re-explain the problem at each step. Works with vois-patterns, vois-components, vois-tokens, righter, and design-rationale. Each of those skills can still be used standalone — this router is additive, not a replacement. Trigger when someone says "build this screen", "what component should I use", "help me write this copy", "route me through the design system", or pastes any feature brief, ticket, or design question without specifying which skill to use.
feedback-synthesizer
Turns raw survey results (scores + open-text comments) or any pile of qualitative feedback (reviews, support tickets, open-ended comments) into a scored, statistically-tested, thematically-coded synthesis with severity-ranked findings. Trigger when someone pastes raw survey data, a CSV of responses, or a pile of qualitative feedback and wants it turned into findings. Entry point 2 of the research loop (see research-loop); also runs standalone without a survey-architect-built survey.
research-loop
Orchestrates survey-architect, feedback-synthesizer, and research-reporter as an iterative research loop that routes back upstream when a downstream step can't proceed cleanly, with per-study state and a per-product longitudinal benchmark. Use this as the single entry point for any UX research task — a new study, raw data to make sense of, or a report to write — rather than calling the three skills directly. Trigger when someone starts a new research study, pastes raw feedback/survey data without a study already in motion, or asks to "run the research loop."
research-reporter
Turns a feedback-synthesizer output into a stakeholder-ready report — exec summary, methodology, benchmark comparison, and prioritized recommendations — formatted for the audience reading it (markdown or Notion for internal readers, Word for formal/external stakeholders). Trigger when someone has synthesis output ready and wants it turned into something shareable, says "write this up," "make me a report," or "turn these findings into something I can send to leadership." Entry point 3 of the research loop (see research-loop).
survey-architect
Turns a research question into a validated, deploy-ready survey: a short intake, the right instrument for what's being measured (SEQ, SUS, UMUX-Lite, SUPR-Q, NPS, CSAT, CES, PSSUQ, or a custom item set), and a platform-native file for Qualtrics, Typeform, or an in-app survey. Trigger when someone says "I need to survey users about X," "what should I ask users after they do Y," "build me an NPS survey," "help me measure usability of Z," or pastes a vague research need and wants it turned into an actual instrument. Entry point 1 of the research loop (see research-loop).
onboarding-flow
Design new onboarding flows or evaluate/critique existing ones — signup sequences, setup checklists, first-run wizards, personalization quizzes, permission priming, paywalls — for SaaS/web products or consumer/mobile apps. Use this whenever someone asks to design, build, spec, improve, review, audit, or critique onboarding, a first-run experience, a getting-started flow, a signup sequence, an account setup wizard, or "the first thing users see," whether starting from scratch or from screenshots/a description of an existing flow. Pulls current visual reference from Mobbin, routes all UI copy to righter, and routes all structure/styling to the vois skills (vois-patterns → vois-components → vois-tokens).
changelog-writer
Write external-facing changelog and release note entries in a pithy, tastefully sassy, occasionally clever voice that makes software updates fun to read without burying what actually shipped. Use this skill whenever someone asks to write, draft, or review a changelog entry, release notes, "what's new" post, or product update announcement for end users. Also trigger when someone pastes a list of shipped features/fixes and wants them turned into public-facing copy, or asks to make a changelog "less boring," "more fun," or "not sound like corporate speak."
designer-ic-assessment
Facilitates a structured behavioral assessment interview for IC designer levels, incorporating AI fluency across competency areas. Use this skill when someone wants to run a designer self-assessment, a manager assessment of a designer, or set up an IC level calibration session. Trigger whenever someone mentions designer levels, IC rubric, design assessment, career calibration, manager assessment, or designer growth conversations. Also trigger if someone says they want to evaluate a designer's AI fluency, run a competency interview, or prepare for a calibration meeting.
gtm-positioning
Framework-based skill for B2B product positioning, GTM strategy selection, and website messaging. Use when someone asks for help positioning their product, choosing a GTM strategy, writing homepage or website copy, messaging for different buyer personas, content strategy by awareness stage, or ad and landing page copy. Based on the Fletch framework by Anthony Pierri.
metrics-tagging
Analyze UI mockups, screenshots, or prototype frames to identify all trackable interactions and generate a complete analytics event taxonomy table, including multi-step task/flow completion events. Use this skill whenever a designer uploads a screen, mockup, prototype screenshot, or UI frame and wants to know what should be tagged, what events to fire, or how to document analytics for handoff. Also trigger when someone asks to "tag this screen," "identify events," "create a tagging spec," "what should we track," "build an event table," or "tag this flow/task" for any UI. If a designer shares any visual of a UI and mentions analytics, tracking, tagging, GTM, events, funnels, or metrics — use this skill.
righter
Apply UX content writing principles to review existing UI copy or write new UI copy from scratch. Use this skill whenever someone asks you to: review, audit, critique, or improve UI text, error messages, button labels, tooltips, empty states, onboarding copy, form helper text, or any software interface copy. Also trigger when someone asks you to write new UI copy, label a button, draft an error message, write a modal, or create any in-product text. If the request involves words that appear inside software — use this skill.
vois-components
Component selection rubrics organized by job-to-be-done. Use after vois-patterns determines structure, before vois-tokens applies tokens. Optionally records each choice via the vois_record_component_choice MCP tool if one is available. Use when deciding between similar components — Dialog vs Drawer, Toast vs Banner, Select vs Combobox, etc.
vois-patterns
Structural decision trees for container types, form states, table layouts, and page-level patterns. Use before vois-tokens. Routes to righter skill for all microcopy (labels, errors, buttons, helpers). Use when building pages, forms, features, workflows.
vois-tokens
Rules and patterns for building UI with shadcn/ui, Tailwind v4 or StyleX, and Motion against a Vois design token set. Use when building components, pages, or any UI that should conform to the workspace design system. Covers spacing, typography, color tokens, component architecture, animation, accessibility, and modern CSS/StyleX patterns.
longform
Write or review long-form thought-leadership content: Medium/blog posts, LinkedIn essays, newsletter pieces, and the narrative sections of a deck or GTM page. Uses a persona and voice blended from Nancy Duarte's storytelling structure and Wes Kao's operator-voice frameworks. Trigger when someone asks to write, draft, edit, or review an essay, blog post, thought leadership piece, LinkedIn post, or newsletter. Also trigger on phrases like "help me write this essay," "make this post sound less generic," "give this a stronger hook," or "review my draft" when the draft is long-form narrative content. Not for UI copy (use Righter) and not for GTM page structure (use gtm-positioning), though this skill supplies the narrative sections inside that structure too.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.