bohewu
UserCodex-first multi-agent workflow toolkit with global skills, workspace-local model profiles, a runtime-neutral core, and Claude Code/Copilot exports.
Categories
Indexed Skills (16)
artgen-scaffold
Docs-only guidance for turning a bounded 2D asset request into a reusable brief, provider-neutral generation prompt, versioned output plan, manual checks, and copy-ready handoff. Use for sprites, animation frames, tiles, icons, UI elements, and simple props; do not use it to claim that image generation or asset processing has occurred.
devtools-ux-audit
Browser-evidence workflow for auditing a normal user's experience across desktop-first, responsive, and mobile web interfaces. Use when a UX review needs viewport-specific navigation, interaction, snapshot, console, network, or screenshot evidence; prefer Chrome DevTools and allow an equivalent browser tool only when it preserves the evidence contract.
frontend-aesthetic-director
Use for implementation or review that changes visible frontend UI: landing pages, dashboards, forms, tables, components, responsive cleanup, accessibility states, design-system alignment, existing-UI polish, or faithful implementation of an approved screenshot, Figma note, wireframe, or UI concept. Do not use for backend-only work, conceptual critique without implementation, or a formal UX audit.
ui-communication-designer
Communication-first conceptual UI design and critique for one task flow, screen, or bounded journey. Use to diagnose unclear interaction, restructure a flow, recommend screen-level changes, or rewrite labels, instructions, CTAs, helper text, errors, warnings, and confirmations from a PRD, screenshot, wireframe, copy set, or UX findings. Do not use for browser evidence collection or implementation-ready component specifications.
ui-ux-workflow
Docs-only conceptual UI/UX workflow for one bounded experience, surface, or journey. Use to produce an assessment, low-fi wireframe, mid-fi direction, user/data/operation flows, state transitions, a reusable downstream prompt, and a thin read-only preview handoff. Do not use for implementation-ready component contracts, code generation, browser-backed audit evidence, or a full interactive prototype.
run-adaptive
Select and either execute or prepare the smallest sufficient agents_pipeline engineering workflow while preserving route-independent execution presets and explicit policy overrides. Use when the user explicitly invokes `$run-adaptive` or asks for adaptive Simple/Flow/Pipeline routing.
run-flow
Adopt and execute the installed agents_pipeline bounded flow workflow with at most five tasks, risk-derived verification, and an optional reviewer gate. Use when the user explicitly invokes `$run-flow` or requests the normal multi-task agents_pipeline engineering flow.
run-modernize
Adopt and execute the installed agents_pipeline modernization workflow for repository assessment, roadmap creation, handoff, and explicitly requested phase execution. Use when the user explicitly invokes `$run-modernize` or requests agents_pipeline modernization planning.
run-pipeline
Adopt and execute the installed agents_pipeline full-pipeline workflow, including risk-derived planning, task routing, implementation, verification, review, retries, status artifacts, and cleanup. Use when the user explicitly invokes `$run-pipeline`, asks to use or run the agents_pipeline pipeline, or requests the full high-risk or multi-module workflow instead of a simple or bounded flow.
run-simple
Adopt and execute the installed agents_pipeline simple workflow for one small, clear implementation with minimal ceremony and bounded delegation. Use when the user explicitly invokes `$run-simple` or asks to use the agents_pipeline simple mode.
run-analysis
Adopt and execute the installed agents_pipeline post-hoc analysis workflow for correctness, complexity, robustness, and conditional numerical findings. Use when the user explicitly invokes `$run-analysis` or requests the agents_pipeline analytical review mode.
run-ci
Adopt and execute the installed agents_pipeline CI/CD workflow for docs-first pipeline design, validation, and optional configuration generation. Use when the user explicitly invokes `$run-ci` or requests agents_pipeline CI/CD planning or generation.
run-committee
Adopt and execute the installed agents_pipeline committee workflow for multi-perspective architecture, security, QA, product, and simplicity decision support. Use when the user explicitly invokes `$run-committee` or requests the agents_pipeline committee mode.
run-general
Adopt and execute the installed agents_pipeline general workflow for mixed coding, planning, writing, analysis, maintenance, or monetization work that needs general-purpose routing. Use when the user explicitly invokes `$run-general` or asks for agents_pipeline general mode.
run-spec
Adopt and execute the installed agents_pipeline docs-first specification workflow to produce a review-ready development specification and handoff. Use when the user explicitly invokes `$run-spec` or asks for an agents_pipeline development spec.
run-ux
Adopt and execute the installed agents_pipeline UX audit workflow with profile-aware evidence, specialist findings, scoring, and prioritized actions. Use when the user explicitly invokes `$run-ux` or asks for an agents_pipeline product UX audit.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.