Frontend
MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines; designpowers personas/accessibility/critique/handoff. Triggers: frontend, UI, U…
Interaction Design
Use when designing states, transitions, animations, error handling, loading patterns, feedback, or any behaviour that responds to user action — ensures interactions are perceivable, operable, and inclusive
Lcx Report Bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
Design Debate
Use when a design direction is uncertain, when the team could go multiple ways, or when the user wants to see competing approaches argued before committing — orchestrates structured debate between agents who advocate for different directions
Init Deep
(builtin) Initialize hierarchical AGENTS.md knowledge base
Research Planning
Use when user needs are unclear, assumptions need validation, or the design brief identifies gaps in understanding — plans what to learn, which methods to use, and from whom
Deep Interview
Socratic spec-clarification interview engine. Engages the user in a targeted Q&A session to clarify requirements, calculate ambiguity, and generate a polished requirements report (pm.md), presentation slides (slides.md), and a ready-to-run execution plan. Triggers: deep-interview, deepinterview, spec-interview, spec interview, ouroboros interview, ooo interview, pm interview, grill-me, grill me.
Designpowers Critique
Use when reviewing design work against a plan, design principles, or quality standards — provides structured critique covering design intent, accessibility, consistency, and user impact. This is the Designpowers critique skill — use this instead of the Superpowers design-critique when working within a Designpowers workflow
Ulw Loop
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
Debugging
MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimal…
Voice And Tone
Use when establishing or applying brand voice — defining voice attributes, tone adaptation across contexts, vocabulary lists, writing examples, and ensuring consistent personality across the interface
Taste Feedback
Use during the build phase to show the user intermediate visual output and ask for taste direction before the full build completes — enables mid-flight course correction so taste mismatches are caught early, not in review
Design Debt Tracker
Use when critique or review produces deferred findings, when checking accumulated design compromises, or when deciding what to address in the next iteration. Maintains a living register of design debt — the minor issues, future-iteration notes, and conscious compromises that accumulate across a project
Design System Alignment
Use when working with or building design systems — tokens, components, naming conventions, theming, or pattern libraries — ensures consistency, accessibility compliance, and systematic thinking
Frontend Ui Ux
Designer-turned-developer who crafts stunning UI/UX even without design mockups
Git Master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git work.
Design Review
Use when the user wants to evaluate something that ALREADY EXISTS rather than build something new — \"review this\", \"audit this screen\", \"what's wrong with this page\", \"is this accessible?\", or when they share a screenshot, URL, or existing code/markup. Runs the existing reviewers (design-critic, accessibility-reviewer, heuristic-evaluator) in parallel against the artefact and reconciles t…
Programming
MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc / gofumpt+golangci-lint v2+nilaway+go-race), parse-don't-validate, exhaustive match, typed errors, no any/unwrap/panic, 250 LOC ceiling, TDD. Routes to…
Ast Grep
Use ast-grep (sg) for AST-aware code search and rewrite across 25 languages. Trigger for structural code matching or deterministic codemods: find every function/call/class/import shaped like X, rewrite console.log to logger.info, strip `as any`, migrate require() to import, find empty catch blocks or missing await, and scan/apply YAML rules. Prefer this over rg/grep when the target is syntax shap…
Clone
AI Website Cloner Skill: Point the AI agent at a target URL to automatically reverse-engineer and clone it into a modern Next.js/Tailwind v4/shadcn UI React project.
Inclusive Personas
Use when defining who a design serves — creating personas, user stories, or scenarios — ensures the full ability spectrum and situational contexts are represented from the start, not retrofitted
Verification Before Shipping
Use before declaring any design work complete, fixed, or ready — requires running verification and confirming output before making any success claims. Evidence before assertions, always
Accessible Content
Use when writing or structuring any user-facing content — interface copy, labels, error messages, help text, headings, alt text, link text, or form instructions — ensures content is readable, navigable, and meaningful for everyone
Coding Agent Sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline, Kodu, Cursor CLI, Aider, or unknown local agent logs. Covers transcripts, session IDs, rollout JSONL, state SQLite, Claude projects/pre-compact histories,…
Heuristic Evaluation
Use after a build to evaluate usability against Nielsen's 10 heuristics and run cognitive walkthroughs of every key task. Dispatches the heuristic-evaluator agent in parallel with design-critic and accessibility-reviewer, then feeds findings into the reconciliation protocol. This is the usability lens — \"will people actually be able to use this?\" — distinct from craft critique and accessibility…
Refactor
Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.
Responsive Patterns
Use when designing complex responsive layouts — breakpoint strategy, layout shifts, content reflow, responsive typography, container queries, and ensuring the experience works across the full device spectrum
Cognitive Accessibility
Use when evaluating mental load, wayfinding, focus management, memory demands, or decision complexity in any interface — ensures designs work for people with cognitive differences, under stress, or managing divided attention
Eval Loop
Agent Evaluation & Benchmark Loop: Automate dataset collection, run test inputs, grade output quality (LLM-as-judge), group failure patterns, and refine prompts.
Adaptive Interfaces
Use when designing for user preferences — motion sensitivity, contrast needs, colour schemes, text sizing, information density, or any interface behaviour that should adapt to individual needs
Synthetic User Testing
Use after the fix round to validate the design by walking through key tasks as each persona — simulating how Jordan (low-vision), Priya (non-native speaker), Marcus (motor impairment), or any project persona would actually experience the interface. Catches the issues that code review misses because they only surface in the act of using
Design Md
Use when the user provides a DESIGN.md file — the open, Apache-2.0 design-system format from Google Labs (Stitch) that coding agents read to build brand-consistent UI. When a DESIGN.md is present in the project (or the user points you at one), READ IT and build faithfully from its tokens, which produces much higher-fidelity, on-brand output than inferring a design from scratch. A DESIGN.md is the…
Review Work
Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE after completing any significant implementation work. Triggers: 'review work', 'revie…
Token Architecture
Use when building or restructuring design token systems — global tokens, semantic tokens, component tokens, naming conventions, theming, and multi-platform token distribution
Design Retrospective
Use after shipping or completing a design project — structured reflection on what worked, what didn't, and what taste decisions landed. Adds observations to the design record (design-memory) about how the user designs — a descriptive journal, not preferences applied to future projects
Ui Composition
Use when building layouts, choosing colours, setting typography, establishing visual hierarchy, designing responsive behaviour, or making any visual design decision — ensures every visual choice serves both aesthetics and accessibility
Ulw Plan
MUST USE for planning before coding: 5+ steps, ambiguous scope, multiple modules, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the inten…
Taste Report
Use when the user wants to see how they design — \"what's my taste\", \"show me my taste report\", \"how do I decide\", \"what are my patterns\", or periodically as the personal profile matures. Generates a longitudinal, reflective report from the PERSONAL taste profile (design-memory) — recurring moves, tells, evolution, blind spots — that helps a designer understand their own instincts. Persona…
Start Work
Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.
Comment Checker
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
Inspiration Scouting
Use when the team needs aesthetic references, interaction examples, or visual inspiration beyond competitive research — finds design patterns, UI references, and creative approaches that match the brief and taste profile
Usability Testing
Use when planning or conducting usability tests — writing test scripts, defining tasks, selecting participants, analysing findings, and turning observations into design actions
Visual Qa
Rigorous visual QA for any UI you built or changed, across BOTH web/page UIs and TUI/terminal UIs. MUST USE after building or changing any UI to verify it visually before declaring it done. Captures objective reference evidence with a bundled diff script (image-diff for screenshots, tui-check for terminal captures), then runs two parallel read-only oracle passes (design-system and functional inte…
Design Handoff
Use when design work is complete and needs to be communicated to engineering — creates specifications, documents rationale, accessibility requirements, and interaction details in a format engineers can implement directly
Remove Ai Slops
Remove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST, then runs categorized cleanup via parallel `deep` agents in batches of 5, then verifies with quality gates. Covers 10 slop categories including performance equivalences, excessive complexity (object annotations, if/elif variant chains), and oversized modules (250+ pure…
Motion Choreography
Use when designing animation sequences, page transitions, micro-interactions, loading states, or any motion that communicates meaning — ensures motion is purposeful, performant, and safe for motion-sensitive users
Browse
Open the lazyantigravity Session Browser dashboard in your web browser to check active workflows, task checklists, and live code diffs.
Rules
Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.
Lsp
Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.