Plugin Claude Code
SHELEG Design methodology: cinematic scroll-driven landing pages (single scroll clock, layered degrade-to-calm motion, WebGL particle formations), a motion doctrine that decides whether to animate before it decides how, and thirty-nine pluggable visual style packs, each with a ready-made token layer …
Command
Apply the SHELEG Design methodology (single-clock, layered, degrade-to-calm motion) to the current landing-page / hero / scroll-animation task — or its style packs to product UI (dashboards, admin, internal tools).
Plugin Claude Code
Production patterns for building agent orchestrators — and for billing the LLM access they burn.
Plugin Claude Code
Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…
Skill Claude CodeCodex
Use when measuring whether an agent actually works — building an eval suite, judging a trajectory rather than a final answer, turning production traces into regression fixtures, calibrating an LLM judge against human labels, or gating a release on offline evals. Covers the three observability primitives (run, trace…
Skill Claude CodeCodex
Use when the question is what the agent is TOLD rather than how its loop is wired — writing or fixing a system prompt, shaping tools so the model picks the right one, deciding whether a job wants a workflow or an agent, or choosing between ReAct, reflection and voting. Also auditing an agent system somebody else…
Skill Claude CodeCodex
Use when an agent must talk to something outside its own process — building or consuming an MCP server, exposing or calling another agent over A2A, publishing to the MCP Registry, or putting a gateway in front of agent traffic. Carries the MCP 2026-07-28 wire surface and what it deprecated (server/discover, stateless…
Skill Claude CodeCodex
Use when building an agent system — an orchestrator, an LLM-powered tool, a chatbot with tool use, an AI pipeline — or metering and billing the LLM access it burns. Covers tool-calling loops, pipelines with human checkpoints, provider routing with fallback/retry, memory architecture, retrieval and decay, context…
Plugin Claude Code
Full-cycle UX for AI agents: design the chain (foundation -> flows -> screens -> scenarios) before any UI code, keep it in sync on every change, and verify the code against it with evidence-backed audits.
Instructions file
Claude Code instructions for ssheleg/super-ux, covering claude.md — super-ux, where the artifacts are, gates, adding a skill and adding a hard rule.
Cursor rule
Brand voice and copy — docs/brand/ is the source of truth for how the product speaks; any public-facing text change updates it in the same change and passes docs/brand/lint.py.
Cursor rule
Write or rewrite any text a user reads (interface strings, errors, empty states, landing and pricing pages, posts, changelogs, store listings, ads, email): apply when asked to write copy, rewrite a headline or CTA, fix microcopy, or when a draft reads machine-made.
Cursor rule
Cursor rule "super-ux" from ssheleg/super-ux, covering ux scenarios — hard rule (super-ux) and which rule owns which question.
Cursor rule
Audit the codebase against docs/ux/scenarios.md: apply for UX audits, scenario compliance checks, pre-release UX verification, or when asked to verify that all buttons/states/errors exist.
Cursor rule
Design or improve user flows (docs/ux/flows.md): apply for task analysis, flow diagrams, screen states, wireframes, heuristic UX evaluation, or any 'improve/fix the UX' request.
Cursor rule
Maintain docs/ux/foundation.md (personas, Jobs to Be Done, customer journeys, user stories): apply when defining who the users are and why they use the product, during product discovery, or when scenarios need a WHY layer to trace to.
Cursor rule
Maintain docs/ux/scenarios.md (the UX scenario base): apply when creating or updating UX scenarios, starting any new feature or project, changing user-facing behavior, or onboarding a codebase into scenario-driven development.
Cursor rule
Product vision (docs/ux/vision.md): apply when defining what the product is and what it refuses to become, when a proposed feature feels off-strategy, or when a scope argument has no document that settles it.
Plugin Claude Code
Scenario-driven UI development: a versioned design chain in docs/ux/ — product vision -> personas, JTBD, journeys and stories -> user flows -> a screens+states UI map with Figma frames -> traced use-case scenarios -> evidence-backed audits -> concrete fix plans. Skills: vision, ux-foundation, ux-flows, ux-scenarios…
Command
Initialize the brand pack — read the foundation and existing copy, propose a voice pack with reasoning, seed docs/brand/, and sweep the interface into the string registry.
Command
Run the brand linter over docs/brand/ and the declared sources — contract, terminology, string consistency, facts, channel limits, bot safety, AI markers and locales.
Command
Recalibrate the brand pack after positioning, personas, pricing or naming changed — propagate the change through terminology, strings and every locale in the same edit.
Command
Single entry point for the verbal identity — status across voice, terminology, facts, channels, strings and locales, then a menu of applicable actions (init, calibrate, update, validate, write, audit).
Command
Write, edit, adapt or humanize copy for a named surface — interface strings, landing and pricing pages, blog, changelog, social posts, store listings, ads, lifecycle email — in the product's recorded voice.