UI/UX, logos, slides, and image generation (7.4K skills)
Implement or revise one governed Proto UI Host Capability connecting a semantic Module to a bounded host responsibility. Use when capability identity, portable need, public shape, availability, failure, replacement, cleanup, fidelity, Adapter realization, and evidence are fixed by current authority.
The English summary is being prepared. Showing the original description.
Execute one bounded read-only Proto UI autonomous-maintenance observation mission. Use for drift hunting, external-oracle comparison, repeatability control, or a no-finding maintenance run. Stop before verification or remediation.
The English summary is being prepared. Showing the original description.
Establish Proto UI repository state, live contributor authority, Agent comprehension scope, task risk, and authorization before work begins. Use at the start of a development session, before autonomous task selection, after a material repository update, or when permission or assessment state may have changed.
The English summary is being prepared. Showing the original description.
Prepare a reviewed Proto UI global release candidate as repository state after current project authority has chosen the exact version and stage. Use for draft Version identity, exact package metadata, notes, bill of materials, rehearsal, and publish dry-run. Publication remains a distinct privileged operation.
The English summary is being prepared. Showing the original description.
Independently review one Proto UI autonomous-maintenance remediation in a fresh read-only context. Use after pui-remediate produces a packet and actual diff. Classify technical-completion eligibility without making product or integration decisions.
The English summary is being prepared. Showing the original description.
Post one already selected Proto UI work-item claim as a reversible GitHub metadata mutation. Use after pui-select produced a current proposal and the exact claim has authorization, live permission, current readiness, and an idempotent write boundary. Do not select work, decide readiness, release claims, or widen the authorized wording.
The English summary is being prepared. Showing the original description.
Record one authorized non-remediation terminal outcome in Proto UI's autonomous-maintenance state. Use after a supported no-finding result, an independently rejected finding, or a blocked mission whose terminal evidence is complete.
The English summary is being prepared. Showing the original description.
Maintain an existing Proto UI Prototype or implement a governed Base or design-language component slice. Use for governed component behavior, anatomy, inheritance, exports, CLI registration, style projection, demos, or public preview work. Do not use to admit a new semantic subject or invent Base ownership from a component name.
The English summary is being prepared. Showing the original description.
Assess and route one bounded Proto UI dependency drift, advisory, or update question. Use to trace manifest and lockfile identity, consumer impact, compatibility evidence, provenance, update risk, and the exact next update or no-action transition. This leaf remains read-only.
The English summary is being prepared. Showing the original description.
Apply one exact-target Proto UI collaboration update through the ordinary governed primitive or an explicitly current-user connected-operation path for archive/ref recovery, Issue reopening/linking, additive carrier publication and service control. Do not manufacture review dispositions, merge, close, release or change privileged settings.
The English summary is being prepared. Showing the original description.
Release one current Proto UI work-item claim when it expired, became invalid, or the contributor stopped. Use only for the contributor's own recorded claim and only when the exact reversible GitHub mutation is authorized. Do not select replacement work, change readiness, or release another contributor's claim.
The English summary is being prepared. Showing the original description.
Review or polish a product UI for accessibility, brand fidelity, hierarchy, rhythm, responsive behavior, themes, interaction states, and generic AI-template patterns. Use for visual audits, accessibility checks, UX polish, UI critique, or pre-ship design review. Do not use for generic code review, backend review, or API design.
The English summary is being prepared. Showing the original description.
Apply product-grounded visual quality constraints during user-visible UI changes. Use for layout, styling, content hierarchy, theming, responsive behavior, or interaction affordances. Stay inactive for logic-only changes that preserve the rendered interface.
The English summary is being prepared. Showing the original description.
Create or redesign product UI in an existing codebase, including a wireframe, substantive visual variations, and an interactive prototype. Use for requests about UI layout, visual direction, screens, flows, components, a landing page, dashboard, or making an interface feel polished. Do not use for backend work, system architecture, decks, or logic-only UI fixes.
The English summary is being prepared. Showing the original description.
Extract, document, or normalize a product UI design system from code, screenshots, or brand sources. Use for visual tokens, theme variables, typography, spacing, colors, radii, shadows, component inventories, variants, states, or building a reusable UI library. Do not use for software architecture, database schemas, or generic system design.
The English summary is being prepared. Showing the original description.
Access Claude Design and Claude artifacts when the request names Claude Design, a Claude artifact, Slides deck, or Design System artifact, or contains a claude.ai/design or claude.ai artifact URL or a .dc.html file. Use for creating and editing designs, decks, design systems, and artifact pages; assets, comments, artifact databases, sharing, versions, rendering, standalone-to-artifact migration, and code-to-design or design-to-code synchronization; otherwise stay inactive.
The English summary is being prepared. Showing the original description.
MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.
The English summary is being prepared. Showing the original description.
Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.
The English summary is being prepared. Showing the original description.
Extract comprehensive site specifications from simple descriptions. Use when analyzing a user's theme request to determine site type, audience, tone, layout requirements, and typography.
The English summary is being prepared. Showing the original description.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
The English summary is being prepared. Showing the original description.
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.
The English summary is being prepared. Showing the original description.
Facilitate design discussion — research context, clarify requirements, draft RFC/ADR
The English summary is being prepared. Showing the original description.
Write effective Architecture Decision Records. Use when: (1) Creating a new ADR, (2) Recording a design decision, (3) User mentions ADR, decision, trade-off, or alternatives
The English summary is being prepared. Showing the original description.
Design guide + benchmarked pitfalls for building Monte-Carlo / Simulated Annealing refinement layers on top of greedy hex-grid layouts for code visualization (packages/gui/src/store/hexLayout.ts, sandbox/hex-sandbox, future Rust ports). Use when: (1) planning to add MC/SA on top of an existing hex-grid pack, (2) deciding whether a simpler SA would match a hierarchical MC with force-directed + chain drag, (3) budgeting wall-clock for million-node cold-start, (4) debugging "blob turns Swiss-cheese" or "folders stop nucleating" during MC refinement, (5) choosing between folder cohesion and raw Σ-link-length as cost function. Contains four hard-won, quantified lessons and anti-patterns that would take a full day of experiments to rediscover.
The English summary is being prepared. Showing the original description.