Design & frontend
15,938 rows, by stacks then stars
1,697 of these skill files have been read, by 1,179 distinct authors, and what they tell an agent counted. What Design & frontend authors agree on, and what they forbid
kfeng209-oss/cognitive-ux/skills/cognitive-ux-forms Skill
1★ repoDesign and audit forms, applications, intake journeys, and high-stakes submission flows using evidence-informed UX. Use when people must enter correct information, save progress, correct errors, review, and submit; return field necessity review, task flow, labels/examples, validation/recovery behavior, accessibility requirements, and completion-quality testing.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-health Skill
1★ repoDesign and audit health-information, patient-portal, appointment, refill, and care-communication websites using evidence-informed UX. Use when people need to understand care information or manage care; return health-literacy structure, uncertainty/provenance rules, task flows, privacy and escalation design, accessible support, and representative patient/caregiver validation.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-jobs Skill
1★ repoDesign and audit job boards, careers sites, recruiting portals, and application journeys using evidence-informed UX. Use when people must discover roles, evaluate fit, apply, manage candidate status, or review candidates; return search/filter rules, transparent role information, accessible application and status flows, accommodation/consent safeguards, and fairness-aware validation.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-learning Skill
1★ repoDesign and audit learning, course, tutoring, practice, and educational websites using cognitive-science evidence. Use when learners must understand, practice, receive feedback, remember, and return; return objective-to-practice sequencing, cognitive-load audit, accessible media rules, mastery signals, and learning—not just completion—measures.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-marketplace Skill
1★ repoDesign and audit marketplaces, directories, comparison sites, and third-party listing platforms using evidence-informed UX. Use when people must find and select a provider, seller, service, or listing; return a query/refinement model, comparable attributes, ranking explanation, trust/review rules, safe handoff, and validation plan.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-nonprofit Skill
1★ repoDesign and audit nonprofit, fundraising, and advocacy websites using evidence-informed UX. Use when people must understand a cause and donate, volunteer, contact a representative, or take another informed action; return impact narrative, consent-aware donation flow, ethical action design, accessibility checks, and retention-oriented validation.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-onboarding Skill
1★ repoDesign and audit first-run, activation, setup, and guided onboarding experiences using evidence-informed UX. Use when a new user must reach initial value in a product; return a time-to-value map, progressive setup, permission and data-request disclosure, empty-state design, recovery paths, accessibility checks, and activation-quality metrics.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-portal Skill
1★ repoDesign and audit member, customer, student, and account portals using evidence-informed UX. Use when authenticated people must access personal information and repeat tasks; return a task-oriented account architecture, secure yet accessible authentication/recovery, record/receipt patterns, help paths, privacy safeguards, and task-success validation.
Cognitive ux product marketing
kfeng209-oss/cognitive-ux/skills/cognitive-ux-product-marketing Skill
1★ repoDesign and audit product-marketing websites for complex software, services, and subscriptions using evidence-informed UX. Use when a visitor must evaluate capabilities, fit, plans, proof, and a demo or trial; return audience paths, capability-to-outcome mapping, transparent comparison, accessibility requirements, and validation metrics.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-sales Skill
1★ repoDesign and audit focused sales, campaign, portfolio, launch, and lead-generation landing pages using evidence-informed UX. Use for a visitor who must understand one offer and take one clear next step; return message hierarchy, proof and objection map, honest CTA design, accessibility checks, and a comprehension test rather than generic visual polish.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-travel Skill
1★ repoDesign and audit travel search, comparison, booking, and itinerary-management websites using evidence-informed UX. Use when people must plan a trip, compare routes or stays, book, and manage changes; return constraint-first search, itinerary structure, full-price disclosure, recovery paths, and task validation.
kfeng209-oss/cognitive-ux/skills/cognitive-ux-workflow Skill
1★ repoDesign and audit SaaS applications, internal tools, and recurring knowledge-work workflows using evidence-informed UX. Use when people repeatedly create, review, organize, approve, or resolve work; return an object/action model, primary and recovery flows, state/undo rules, accessible interaction requirements, and time-to-correct-outcome validation.
kfeng209-oss/cognitive-ux/skills/cognitive-ux Skill
1★ repoRoute website and interface requests to the right evidence-informed Cognitive UX archetype skill. Use when a user needs help choosing among sales, commerce, marketplace, booking, learning, content, documentation, dashboard, workflow, onboarding, forms, community, portal, nonprofit, health, finance, travel, admin, civic, or jobs UX; identify the primary user task, relevant risks, and installable specialist skill instead of applying generic UI advice.
jpoindexter/ux-flow-skills/skills/userflow Skill
1★ repoUse when the user invokes /userflow, asks which UX flow or layout patterns apply to what they're building, or describes an app, feature, or screen to build or review and wants the right proven flow guidance pulled in automatically. Also use at the start of any UI build when it's unclear which flow-* skills are relevant.
shahroz-a/skills/skills/uigrids-interface-review Skill
1★ repoReview and improve product interfaces using evidence-based UI Grids guidance. Use for UI or UX audits, implementation reviews, and fixes involving forms, navigation, motion, feedback, empty states, interface audio, mobile reach, hover or focus parity, accessibility, and responsive behavior. Do not use for brand exploration, illustration, or subjective visual taste without an interface problem to solve.
ssdiwu/507-skills/write/507-ppt Skill
1★ repo原创视觉幻灯片制作:把已收口的逐页内容用可组合页面组件与设计令牌生成可编辑 .pptx 或独立单文件 HTML,并完成双载体验证。Use when user mentions 制作 PPT、生成 pptx、做成幻灯片、做 HTML deck、网页演示、slides rendering、presentation visual design、瑞士风 PPT、杂志风 PPT;内容仍需编排、讲稿或逐页稿未收口时使用 507-stage,不使用本 skill。
andr-ca/agentharness/.claude/skills/code-review-ui Skill
1★ repoUse when reviewing frontend, UI, or component code. Covers accessibility (WCAG AA), state management, bundle size, keyboard navigation, hydration, and rendering performance. Load instead of the general code-review skill for UI-focused reviews.
andr-ca/agentharness/.claude/skills/go-conventions Skill
1★ repoUse when writing, reviewing, or refactoring Go code — naming conventions, receiver naming, error wrapping, interface design, goroutine safety, and common pitfalls (goroutine leaks, defer-in-loop, nil map writes).
whatsuppiyush/god-of-skills/art-and-photography/ai-interior-design Skill
1★ repoOne living room across 14 interior-design styles, each with the prompt, from Scandinavian to japandi to maximalist.
whatsuppiyush/god-of-skills/marketing/landing-page-teardown Skill
1★ repoPaste a URL, get a conversion audit: hierarchy, hook, objections, CTA, scored 0-100.
jeremyinthebay/relay-skills/skills/mobile-verification Skill
1★ repoTest what a page actually DOES on a phone — real taps, real scrolling, real animations — using Playwright instead of a browser-automation tab that is structurally blind to motion. Use whenever verifying mobile behaviour, testing touch interactions, checking horizontal overflow or touch-target sizes, before merging any front-end change, or when a scroll/animation/click test reports "nothing happened" and you need to know whether the page is broken or your harness is.
shahrulestar/skills/skills/ux-writer Skill
1★ repoComprehensive UX writing and typography audit for UI text — landing pages, SaaS, web apps, dashboards, e-commerce, marketplaces, developer tools, CLI, browser extensions, mobile apps, AI/chat products, and more. Covers headings, body text, labels, buttons, placeholders, navigation, billing, onboarding, helper text, validation, empty states, i18n, and accessibility. Use when reviewing or rewriting visible copy for any product type. Trigger on "review copy," "typography audit," "SaaS copy," "landing page," "dashboard microcopy," "checkout copy," "mobile app strings," "extension popup," or "i18n copy."
dineshrevunuru/SuperSkills/apply-visual-hierarchy Skill
1★ repoDirects attention on a screen using NN/g visual-design principles — scale, contrast, position, Gestalt grouping — plus legibility floors (line length, text contrast, limited palette). Use when laying out any screen, section, page, slide, or component; when deciding what users should see first; when grouping related elements; or when work is described as 'cluttered', 'busy', 'flat', 'nothing stands out', 'nothing pops', 'where do I look first', 'hard to scan', or 'make this scannable'. This is generic craft — Dinesh's taste values live in design-taste, which OVERRIDES this skill; load design-taste first.
dineshrevunuru/SuperSkills/audit-accessibility Skill
1★ repoRun a WCAG-grounded accessibility audit on a design, prototype, or live page, severity-rate every finding, and enforce the hard accessibility launch gate. Use when asked to 'audit accessibility', 'check a11y', 'is this accessible?', 'run the accessibility gate', 'check contrast / keyboard / screen reader / focus states / target sizes', or before ANY external-facing launch or handoff — nothing Dinesh ships skips this gate. Also use to decide whether assistive-tech user testing is needed on top of the audit.
dineshrevunuru/SuperSkills/build-frontend-interfaces Skill
1★ repoBuilds distinctive, production-quality frontend interfaces — pages, components, landing pages, case-study pages, claude.ai artifacts — in Dinesh's visual register. Use when asked to 'build a page', 'build this component', 'code this UI', 'make a landing page', 'create an artifact', 'redesign this screen', or for any HTML/CSS/React/Next.js work where how it looks matters as much as whether it runs. Plans before coding, with design-taste loaded as the default direction; routes tooling to web-artifacts-builder or the built-in artifact-design. NOT for throwaway test prototypes (build-coded-prototypes) or post-build mechanical QA (verify-ui-quality).
dineshrevunuru/SuperSkills/build-token-system Skill
1★ repoBuilds a primitive → semantic → component design-token system with Figma variables and code (CSS custom properties / JSON) synced from day one — tier architecture, naming grammar, theming and dark-mode structure, and the canonical token files. Use when starting the styles for a new product or site, when asked to 'set up design tokens', 'create CSS variables', 'tokenize this', 'add dark mode', 'theme this', 'sync Figma variables with code', or 'name these tokens' — and whenever hex codes, px values, or font sizes are being hardcoded into components and need a system. Produces the canonical token files that apply-personal-brand and every UI-building skill consume.
dineshrevunuru/SuperSkills/codebase-design Skill
1★ repoThe deep-module vocabulary and heuristics for structuring the React/Next/TypeScript code Dinesh ships — a lot of behavior behind a small interface, placed at a clean seam, tested through that interface — so an ARIA sub-agent (or future-him) can navigate and safely edit a shipped app fast. Use when designing or restructuring a component/hook/module's interface, deciding where a seam goes, asking 'is this module too shallow?', 'should this be one module or three?', 'how do I make this testable / AI-navigable?', 'this wrapper adds nothing', or when another SHIP skill needs the deep-module language. Names things exactly — module, interface, depth, seam, adapter, leverage, locality — and runs the deletion test + the two-adapter rule. NOT for prototypes (throwaway code needs no seams — `build-coded-prototypes`); NOT a diff review (`review-shipped-code` flags a shallow module, this reshapes it).
dineshrevunuru/SuperSkills/craft-critique Skill
1★ repoCritique and review the way Dinesh does — for any design, prototype, copy, case study, or claim. Load when reviewing work ('review this', 'critique this', 'what do you think', 'is this good enough', 'ready to ship?'), when evaluating claims about markets/users/positioning, when auditing AI-generated output for inflated claims, OR to stress-test a plan or positioning BEFORE it's built ('grill me', 'poke holes', 'stress-test this', 'talk me out of this', 'what am I missing'). This file is the SINGLE SOURCE OF TRUTH for the evidence-discipline protocol; other skills reference it, never restate it. It owns judgment and verdict language (and the grilling stress-test) — mechanical pre-ship checks (browser automation, cross-device, performance) belong to verify-ui-quality, which defers here for the judgment layer.
dineshrevunuru/SuperSkills/craft-motion Skill
1★ repoDesigns and implements UI motion the way Dinesh ships it — choreography, stagger math, state feedback, and working code for CSS, GSAP, and Framer Motion, all inside the quiet register where motion presents the evidence and is never the show. Use when adding or fixing any animation: 'animate this', 'add a transition', 'stagger these cards', 'motion for this modal/list/page', hover/press feedback, loading/success/error states, scroll reveals, or when motion 'feels robotic/janky/too much'. Load design-taste FIRST — every curve, duration tier, and the overshoot law live there, never here.
dineshrevunuru/SuperSkills/create-visual-assets Skill
1★ repoCreates finished static visual assets — posters, case-study hero images, OG/social cards, cover art, one-page PDF art pieces — using a two-step philosophy-first method: write a short design philosophy, then express it on canvas as PNG/PDF, inside Dinesh's minimal taste. Use when asked to 'make a poster', 'design a cover', 'create an OG image', 'hero image for this case study', 'make a social card', 'turn this into a visual piece', or any standalone static graphic. NOT for UI screens (build-frontend-interfaces), charts (visualize-data), or anything that moves (craft-motion).
dineshrevunuru/SuperSkills/define-ux-success-metrics Skill
1★ repoDefines how a design's success will be measured: HEART goals→signals→metrics, SUS/SEQ/NPS instrument selection, UX benchmarking waves, and analytics measurement plans with macro/micro conversions. Use when asked 'how do we measure success', 'what metrics should we track', 'define KPIs for this feature', 'set up HEART', 'should we use NPS', 'benchmark our UX', 'write a measurement plan', or before any launch that will later be judged. NOT for analyzing usability findings (analyze-usability-data), designing A/B tests (use-quantitative-evidence), or measuring AI output quality (write-ai-evals).
dineshrevunuru/SuperSkills/design-agentic-ux Skill
1★ repoDesigns the surfaces of an AI that ACTS — multi-step plan display, run progress, streaming and think-time states, interrupt/cancel/undo, human-in-the-loop approval gates and review queues, memory visibility and control, and non-determinism affordances (regenerate, versions). Use when an AI works over multiple steps or on the user's behalf: 'show the agent's plan', 'design the approval flow', 'what does the user see while it's working', 'add a regenerate button', 'let users see or edit what it remembers', 'the agent did something without asking', 'progress UI for a long-running AI task', 'design the review queue'. Owns the acting-AI experience; what happens when the AI is WRONG (hallucination, refusal, error states) belongs to design-ai-trust-and-failure-states.
Design ai trust and failure states
dineshrevunuru/SuperSkills/design-ai-trust-and-failure-states Skill
1★ repoDesign the user-facing reliability layer of any AI product: uncertainty and confidence display, provenance/citations, hallucination and sycophancy mitigations, explainability calibrated to stakes, and a named cause + recovery path for EVERY failure — refusal, timeout, content filter, context overflow, mic/STT death, TTS death, dead live-embed. Use when asked 'what happens when the AI is wrong/fails/refuses', 'design the error/fallback/empty state for the AI', 'how do we show confidence or sources', 'the model hallucinated', 'the mic/voice broke', or before shipping ANY AI feature — no AI surface ships with only a happy path. Owns failure UX; measuring failure belongs to write-ai-evals.
Design conversational interfaces
dineshrevunuru/SuperSkills/design-conversational-interfaces Skill
1★ repoDesign the behavior of an AI conversation once a conversation is the chosen interface — chatbots, guided-selling agents, support bots, voice-assistant dialogues, AI companions. Covers intent catalogs, turn design, question strategy, recommendation patterns, repair (guide vs fallback), refusal and safety gates, suggestion chips/prompt controls, and memory/proactivity dosing. Fuses NN/g chatbot research with Dinesh's shipped conversational products (the live Tara salon chatbot, the Boo portfolio agent, the Echo Show honest-shopkeeper). Use when asked to 'design a chatbot', 'write the conversation flow', 'script the bot', 'design the dialogue', 'what should the assistant say / ask', 'add an AI assistant to the site', or when reviewing a conversational agent's UX. NOT for deciding whether to use chat at all (design-stage-interfaces) or for voice mechanics like barge-in (design-voice-interactions).
dineshrevunuru/SuperSkills/design-growth-surfaces Skill
1★ repoDesign the surfaces whose job is conversion — onboarding flows, signup, first-run experiences, upgrade prompts, paywalls, trial flows, pricing pages, and launch/landing pages — as designed strategy with pricing awareness, activation metrics, and a mandatory ethical-persuasion filter (no dark patterns). Use when the ask involves 'onboarding', 'first-run', 'signup flow', 'paywall', 'upgrade flow', 'pricing page', 'free trial', 'landing page', 'launch page', 'activation', 'improve conversion', 'more signups/bookings', or diagnosing funnel drop-off that ends in a design change. Growth is designer-owned here, not a marketing handoff.
dineshrevunuru/SuperSkills/design-interaction-flows Skill
1★ repoDesign-time interaction design: feature flows, task flows, user flows, and wireflows, plus PRD-to-scenario translation and systematic edge-case + failure-path enumeration. Use when asked to 'map the flow', 'design the user flow / task flow', 'design this feature end-to-end', 'translate this PRD into screens/scenarios', 'what are the edge cases', 'what happens if X fails', or before any high-fidelity screen work on a new feature. NOT for research-time experience maps (journey/empathy maps — that is map-customer-journey) and NOT for designing the content of each state (that is design-ui-states).
dineshrevunuru/SuperSkills/design-output-contracts Skill
1★ repoDesigns structural output contracts for AI features so the model can ONLY produce designed UI — never a prose reply, never a fabricated fact. Use when building or reviewing an intent router, forced tool call (tool_choice), closed-enum classifier, generative-UI system, or any surface where 'the model must respond with UI/JSON only'; when someone says 'the model keeps replying in text', 'how do I stop it hallucinating a number', 'constrain the output', 'structured output', 'route the utterance to a component', or 'what happens on an unmatched input'. Owns the guarantee layer: schema, enum, fallback routing, verified-store data. Distilled from Dinesh's shipped routers (the Boo portfolio router, the Saathi commerce loop).
dineshrevunuru/SuperSkills/design-stage-interfaces Skill
1★ repoBreaks AI output out of chat into structured, generated UI on a 'stage' — one present-tense surface that re-composes per intent — and owns the conversation-vs-GUI decision. Use when someone asks 'should this be a chatbot?', when a design 'reads as chat' or the mandate is 'avoid a chat interface', when designing how an AI answer appears on screen ('generative UI', 'intent-based UI', composed answers, voice-first screens, Echo Show / kiosk / ambient displays), or when designing the switch between talking and showing. For behavior once inside a conversation (turns, question phrasing, repair), use design-conversational-interfaces instead.
dineshrevunuru/SuperSkills/design-taste Skill
1★ repoDinesh Reddy Revunuru's canonical interface taste. Load BEFORE making any visual, layout, motion, or interaction decision — designing a screen, building UI, choosing a layout, adding animation, reviewing a design, or picking between design directions. This file is the SINGLE SOURCE OF TRUTH for his taste values; every other skill references it and must never restate these values. When in doubt whether a design choice fits Dinesh, load this skill.
dineshrevunuru/SuperSkills/design-ui-states Skill
1★ repoDesigns every state a screen can be in — empty, loading, error, partial, ideal — plus forms, validation, and confirmation dialogs, per NN/g guidelines. Use when designing or reviewing any screen ('what does this look like with no data?', 'design the empty state', 'add a loading state', 'write the error handling', 'design this form', 'should this be a toast or inline error?', 'do we need a confirmation dialog?'), when a mockup only shows the happy path, or when choosing between indicator, validation, and notification feedback. Deterministic UI only — AI/model failure states belong to design-ai-trust-and-failure-states.
dineshrevunuru/SuperSkills/design-voice-interactions Skill
1★ repoDesigns and builds voice interfaces the way Dinesh ships them: barge-in with duck-and-resume, turn-taking, live interim transcript ink, push-to-talk, VAD noise hygiene, echo guards, mic consent lifecycle, truthful mic status, and voice error repair — governed by the voice-first law (voice drives, screen follows; type is an equal fallback). Use when adding voice to anything — 'add voice input', 'voice assistant', 'talk to the app', 'wire up the mic', 'STT/TTS', 'push-to-talk', 'it talks over the user', 'barge-in doesn't work', 'the mic status is wrong', smart-display / Echo Show experiences, or reviewing any speech UI.
Document and govern design system
dineshrevunuru/SuperSkills/document-and-govern-design-system Skill
1★ repoDocuments design-system components (variants, states, props, usage rules, content standards) and runs system governance — NN/g 6-dimension maturity assessment to pick the highest-leverage gap, contribution rules, review cycles with yes/no criteria, versioning and deprecation. Use when asked to 'document this component', 'write usage guidelines', 'audit our design system', 'set up a contribution process', 'people keep building one-offs', 'the system is drifting', or 'where should we invest in the design system next'. NOT for creating token values (build-token-system) or designing new component states (design-ui-states).
dineshrevunuru/SuperSkills/facilitate-design-workshop Skill
1★ repoPlan and facilitate design workshops — kickoffs, ideation/design-studio sessions, journey-mapping workshops, prioritization exercises, and design critiques run as group sessions. Use when asked to 'run a workshop', 'facilitate a session', 'plan a kickoff', 'run an ideation/brainstorm', 'do a design sprint exercise', 'run dot voting', 'prioritize as a group', 'run a design critique', or when preparing a whiteboard-challenge / collaborative exercise for a Product Designer interview loop. Covers agenda design, diverge-converge structure, timeboxing, voting mechanics, remote facilitation, and difficult-participant handling.
dineshrevunuru/SuperSkills/improve-animations Skill
1★ repoSurvey a whole codebase's motion as a senior motion advisor, then produce a prioritized, register-aware audit and self-contained implementation plans other agents (including cheaper models) execute. READ-ONLY on source — it plans motion fixes, it never applies them. Use when the ask zooms OUT on the whole app's motion: 'improve the animations', 'audit the motion', 'the app feels janky/sluggish/cheap', 'where should the motion get better', 'make this feel more polished', or 'give me a roadmap of animation fixes' — not a verdict on one diff. Mirrors improve-code-architecture's scan→report→plan shape for motion.
dineshrevunuru/SuperSkills/model-domain-language Skill
1★ repoBuild the ONE shared name per concept — a ubiquitous language / domain model — used identically across client conversations, the design system, and the code. Challenge conflicting terms, sharpen fuzzy ones, scenario-test where concepts meet, and capture the resolved vocabulary in a GLOSSARY.md. Use when a term is overloaded or has rival synonyms ('does booking mean the slot or the record?', 'the client says appointment, the code says session'), when asked to 'define domain terms', 'build a glossary', 'harden the terminology', 'create a ubiquitous language', or 'this word means three things'; when a name conflict surfaces mid-build; or when another skill needs the domain vocabulary maintained. NOT for token VALUES (build-token-system) or UI-copy strings (write-ux-microcopy) — this owns the concept and its one true name; NOT for decision records (write-decision-rationale).
dineshrevunuru/SuperSkills/moderate-usability-session Skill
1★ repoModerates a live usability-test session the NN/g way: think-aloud intro script, neutral re-prompts, echo/boomerang/Columbo probes, intentional silence, the no-premature-rescue rule, atomic note capture, and observer ground rules with a post-session debrief. Use when running or preparing to run a session with a real participant — 'moderate the session', 'run the usability test', 'facilitator script', 'think-aloud instructions', 'the participant is stuck / asks for help / went quiet — what do I say?', 'brief my observers', 'debrief after the session'. NOT for planning the study (plan-usability-test), writing the tasks (write-task-scenarios), or analyzing results afterward (analyze-usability-data).
dineshrevunuru/SuperSkills/plan-usability-test Skill
1★ repoPlans a usability test end-to-end the NN/g way: study goals → qual/quant fork → sample size (5-user rule and exactly when it fails) → moderated/unmoderated × remote/in-person mode choice → recruiting numbers → mandatory pilot with fix-then-freeze. Use when asked to 'plan a usability test', 'set up user testing', 'test this prototype/app/flow', 'how many users do I need', 'is 5 users enough', 'moderated or unmoderated?', 'remote or in-person?', or when a stakeholder wants metrics from a small study. Produces a complete test plan document.
dineshrevunuru/SuperSkills/research-technical-docs Skill
1★ repoInvestigate a TECHNICAL question against high-trust PRIMARY sources — official docs, source code, specs, first-party API references — trace every load-bearing assertion back to the authority that owns it, version-pin each citation, and save the findings as one cited Markdown file. Use when researching how a library/framework/API actually behaves before building on it, checking an API signature or config default, resolving 'does X support Y', 'is this deprecated', 'what changed in version N', 'how does Next.js / React / Framer Motion / GSAP / the Anthropic / ElevenLabs API do Z', or when an agent states a technical fact from memory and it needs sourcing. Researches DOCS and APIs — not markets (conduct-business-research), not users (the UX-research wing), not your own repo (codebase-design). Every assertion follows craft-critique's evidence protocol; the saved file files into build-research-repository.
dineshrevunuru/SuperSkills/review-shipped-code Skill
1★ repoSource-level code review for the React/Next/TypeScript apps Dinesh ships (a salon booking app, his portfolio) — the hole craft-critique (reviews the design) and verify-ui-quality (measures the rendered UI) leave open: neither reads the CODE. Runs two isolated passes — a STANDARDS axis (his repo conventions + front-end craft: accessibility, design-token conformance, React/Next idioms, no dead code) and a SPEC axis (fidelity to the originating problem/spec) — because a change can pass one and fail the other. Use when asked to 'review this code', 'review the diff/PR/branch', 'review since main', 'is this code ready to ship', 'code review before merge', 'did I build what the spec asked', or before merging any production front-end change. NOT for prototypes — those are reviewed for feel, not code (build-coded-prototypes).
dineshrevunuru/SuperSkills/run-heuristic-evaluation Skill
1★ repoRuns an expert usability inspection without users: Nielsen's 10 heuristics operationalized with per-heuristic violation questions, a multi-evaluator two-pass protocol with aggregation, and a cognitive walkthrough for learnability. Produces a prioritized expert-review deliverable. Use when someone says 'run a heuristic evaluation', 'expert review this UI', 'inspect this against the heuristics', 'cognitive walkthrough', 'find usability problems without testing users', or when there is no time/budget/access for a usability test. NOT for severity rating (analyze-usability-data owns the 0–4 scale), WCAG audits (audit-accessibility), or testing with real users (plan-usability-test).
dineshrevunuru/SuperSkills/synthesize-research-data Skill
1★ repoSituational orchestrator that turns raw qualitative (and mixed qual+quant) research — interview transcripts, field notes, diary entries, open survey text, session recordings — into traceable themes, calibrated insights, user need statements, and How-Might-We questions. Reads the DECISION + data type + problem, then SELECTS a synthesis approach from a menu (thematic coding · affinity · framework-mapping to JTBD/journey/matrix · mixed qual+quant) instead of marching one fixed pipeline — while enforcing the same rigor constants every time (traceability, a mandatory disconfirming-case hunt, prevalence as X of Y never a bare %, a confidence level per finding, negative cases reported). Use when the ask is 'synthesize the research', 'what did we learn from the interviews', 'affinity map these notes', 'code these transcripts', 'turn this data into insights/findings', 'map this to jobs-to-be-done / the journey', 'write need statements', or 'write HMW questions'. Owns the Define-stage outputs (need statements + HMWs). NOT for usability-test findings + severity (analyze-usability-data), persona/JTBD artifacts (build-personas), journey/empathy maps (map-customer-journey), or statistical claims from large samples (use-quantitative-evidence).
dineshrevunuru/SuperSkills/verify-ui-quality Skill
1★ repoMechanical pre-ship verification of self-built UI: measures the build against design intent (spacing, type, states, interaction parity), drives every click-path with browser automation, checks cross-device/cross-browser, and runs a front-end performance pass (Core Web Vitals, jank, layout thrash, bundle size). Use when asked to 'verify this page', 'QA before ship', 'run a pre-launch check', 'test it on mobile', 'check performance', 'is it fast', 'click through everything', or after build-frontend-interfaces finishes anything external-facing. This skill runs the machines and reports measurements — it never issues verdicts; judgment and PASS/BLOCKED language belong to craft-critique.
dineshrevunuru/SuperSkills/write-ai-evals Skill
1★ repoDesigns and runs evals for any AI feature the way Dinesh does — golden sets, grading rubrics, LLM-as-judge, hard safety gates, failure-mode taxonomies fed back into structural fixes, and AI-quality product metrics (acceptance, regeneration, edit-distance). ALSO owns the pre-design model capability assessment: what can this model actually do for this use case, cost-latency-quality tradeoffs, model-tier and provider choice. Use when asked 'which model should we use', 'is the small/cheap model good enough', 'how do we test the AI', 'write test cases for the bot', 'is it hallucinating', 'did the prompt change break anything', 'how do we know the AI is good', or BEFORE designing any LLM, voice, agent, or recommender feature. Measures failure; the user-facing failure UX belongs to design-ai-trust-and-failure-states.
dineshrevunuru/SuperSkills/write-survey Skill
1★ repoDrafts and audits self-administered surveys using NN/g's 10 survey best practices: a per-question bias lint (acquiescence, social desirability, framing, prediction, double-barreled, unbalanced scales), Likert vs. semantic-differential scale construction, and a survey-type-to-design-cycle-stage match. Use when asked to 'write a survey', 'draft survey questions', 'make a questionnaire', 'add an in-app / NPS / CSAT / post-test survey', 'review my survey for bias', or when choosing a rating scale. Not for interview questions (write-interview-guide), recruiting screeners (write-participant-screener), choosing an ongoing metrics program (define-ux-success-metrics), or statistical analysis of results (use-quantitative-evidence).
dineshrevunuru/SuperSkills/write-ux-microcopy Skill
1★ repoWrite or review the words inside an interface — button/CTA labels, link labels, error messages, empty states, confirmation dialogs, field labels, helper text, tooltips, loading strings, notifications. Use when asked 'what should this button say?', 'write copy for this screen', 'review this error message', 'fill this empty state', 'name this CTA', or whenever a design/prototype needs its strings written or fixed. Grounded in NN/g microcopy frameworks (3 C's, 3 I's, 4Ss link labels, error-message guidelines). NOT for long-form writing (case studies, articles → writing-voice) or AI conversation behavior (→ design-conversational-interfaces).
ajwadrana/skills/ios-design/skills/ios-typography Skill
1★ repoiOS typography guidance. Triggers on: typography, fonts, type scale, text styling, iOS fonts, open source fonts, custom fonts, Dynamic Type, font pairing.
The same file is in 1 other repository
Talibabtou/website-shower/skills/website-shower Skill
1★ repoRead-only website maintenance audit. Creates a cleanup checklist for repo shape, TypeScript, React/Next, Tailwind/CSS, API/data, state/domain, dependencies, performance, duplicated types/constants, and unused-code leads.
mblauberg/provenant/skills/code-review Skill
1★ repoUse for source-read-only review of a PR, diff, commit, migration, refactor, or implementation through its dependency cone. Not for root-cause diagnosis, authorised fixes, or browser/UX review; use diagnose, implement, or ui-ux-design.
mblauberg/provenant/skills/playwright Skill
1★ repoUse for terminal-driven browser navigation, interaction, snapshots, screenshots, extraction, or UI-flow debugging. Not for authoring Playwright test suites or frontend design; use tdd or ui-ux-design.
mblauberg/provenant/skills/react-performance Skill
1★ repoUse for measuring or improving React rendering, hydration, bundles, waterfalls, Server Components, or Core Web Vitals. Not for general UI design, TanStack cache semantics, or Vite config; use the matching specialist.