Gaurav890
UserA production-grade operating system for shipping software with AI coding agents: durable context, product design, skills, MCPs, orchestration, security gates, evidence, and GitHub workflows.
Categories
Indexed Skills (30)
codex-adapter
Validate and operate Everything Agentic Engineering with Codex. Use when configuring Codex for this repository, checking AGENTS.md or skill discovery, preparing parallel Codex worktrees, packaging the repository plugin, reviewing Codex hooks, or diagnosing Claude/Codex contract drift.
design-engineering-quality
Route substantial design-critical web UI through the smallest relevant Emil Kowalski design-engineering capability. Use during implementation, live iteration, motion work, UI-library selection, and polish when the external suite is installed; preserve the approved project design system, tokens, accessibility, evidence, and independent evaluation.
design-intake
Collect the minimum product-specific visual constraints, generate comparable design directions, and obtain explicit approval before design-system or token changes. Use for design-critical greenfield products, major redesigns, inherited brands, theme creation, or substantial UI work where palette, typography, density, geometry, motion, accessibility, platform, or brand authority is unclear.
design-system
Establish or revise a product-specific design contract after discovery, strategy, interaction design, and design-direction selection. Use for substantial new UI, redesigns, or system changes that need a coherent visual thesis, reference synthesis, component language, motion, accessibility, responsive behavior, and required states.
product-design-router
Select the minimum valid product-design phases for substantial UI/UX work. Use for new products, ambiguous features, redesigns, inherited interfaces, agentic experiences, or frontend changes where discovery, strategy, system, implementation, audit, or critique readiness is uncertain.
specialist-router
Route the smallest reviewed specialist capability needed for a task, enforce risk-driven reviews, and record what expertise was used and what it produced. Use during task planning and whenever work touches authentication, payments, privacy, incidents, reliability, multi-agent systems, internationalization, accessibility, unfamiliar codebases, or design-critical product experience.
accessibility-audit
Audit inclusive interaction quality against WCAG 2.2 AA where applicable. Use before shipping substantial UI or after changes to navigation, forms, dialogs, menus, tables, motion, color, focus, or agentic controls.
agentic-ux
Design understandable, controllable, and trustworthy human-agent experiences. Use for copilots, tool-calling agents, generated artifacts, background work, approvals, multi-agent systems, persistent memory, streaming, or long-running workflows.
benchmark
Conduct structured competitive and adjacent-product analysis across UX patterns, features, strengths, constraints, and gaps. Use when entering an unfamiliar category, starting 0→1 work, preparing a redesign, or testing whether a proposed experience is differentiated.
capability-router
Select the smallest justified project capability from durable profiles and task evidence. Use when a user asks what agents, runtimes, external collections, tools, or optional integrations a project needs; when optional capability scope is unclear; or before proposing installation, activation, credentials, network, sandbox, provider, model, MCP, production, approval, or merge authority.
context-handoff
Preserve project continuity before ending a substantial task or session by updating current truth, verified progress, decisions, risks, blockers, and exact next actions without dumping noisy transcripts.
create-prd
Turn a product idea into a rigorous PRD with stable requirement IDs, user journeys, non-goals, edge cases, security/privacy considerations, metrics, and testable acceptance criteria.
decompose-prd
Convert a PRD into atomic implementation tasks with dependencies, file ownership, requirement traceability, verification methods, and parallelization safety.
design-critic
Independently critique and score a running product experience against product intent, design system, interaction quality, originality, responsiveness, accessibility, agentic UX, and performance. Use after implementation and audits; the critic must not be the builder.
design-ops
Prepare durable, implementation-ready product-design delivery artifacts and handoff. Use after design decisions stabilize or before engineering, review, release, or cross-team transfer when ambiguity would create rework.
design-system-audit
Audit a design system for consistency, completeness, accessibility, component and token coverage, documentation drift, and cross-platform coherence. Use before scaling, redesigning, migrating, or releasing a mature product system.
design-tokens
Encode approved visual and interaction decisions as DTCG-compatible primitive, semantic, component, theme, layout, density, motion, and agentic-state tokens. Use after a visual thesis exists or when evolving an established token system across web and mobile.
discover
Structure ambiguous product discovery and opportunity mapping before solution design. Use for 0→1 products, vague feature requests, unfamiliar workflows, conflicting stakeholder assumptions, or missing evidence about users, constraints, and outcomes.
interaction-design
Define flows, states, transitions, feedback, failure, recovery, and control before screen styling. Use for new workflows, complex forms, multi-step tasks, destructive operations, asynchronous work, or interfaces whose UX logic is not yet explicit.
loop-engineering
Execute a bounded autonomous engineering loop with explicit goal, context, allowed actions, acceptance criteria, retry budget, evidence, persistent state, and safe terminal states.
parallel-plan
Create a safe multi-agent execution plan with a dependency DAG, file ownership matrix, worktree strategy, merge order, and verification gates.
polish
Refine launch-critical visual, content, and interaction details after functionality, design-system integrity, audits, and independent critique pass. Use immediately before shipping, not to conceal unresolved product or interaction problems.
research-ledger
Run current research using Perplexity, Firecrawl, and Playwright with source-quality labeling, conflicts, uncertainty, and a concise recommendation.
responsive-audit
Evaluate real interface behavior across small mobile, large mobile, tablet, laptop, desktop, and wide layouts. Use before release or when changing layout, navigation, tables, dialogs, dense content, or breakpoint behavior.
security-gate
Perform a structured security gate before merging sensitive changes, covering threat model, auth/authz, secrets, injection, SSRF, uploads, webhooks, MCP/browser permissions, dependencies, and verification.
self-improvement-loop
Research, evaluate, and propose safe evidence-backed improvements to the agentic engineering harness. Use for scheduled ecosystem monitoring, release-note review, capability-gap analysis, skill/MCP/design practice updates, or requests to make the repository learn from new internet developments without silently changing trusted behavior.
strategize
Turn discovery, user-needs, benchmark, and product evidence into a focused UX strategy. Use before committing to information architecture, interaction, or visual direction when priorities, assumptions, risks, or differentiation are unresolved.
token-audit
Audit implementation and token sources for raw visual values, arbitrary utilities, duplicate semantics, invalid aliases, missing theme coverage, unused tokens, and undocumented exceptions. Use after tokenized UI changes or before system-scale release.
user-needs
Identify and layer functional, emotional, social, and underlying user needs. Use after discovery or whenever a requirement is feature-led, a problem statement embeds a solution, or the team needs to distinguish user outcomes from requested functionality.
performance-ux
Evaluate loading, responsiveness, stability, rendering, bundle, asset, animation, and data-flow costs as product-experience quality. Use before major launches or after changes likely to affect LCP, INP, CLS, hydration, large lists, images, fonts, or transitions.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.