Design skills

Review a PR or the current branch for a Lumen design-system change — routes each changed file to React (web/Tailwind) or React Native (useStyleSheet) guidelines, checks the Nx version plan, and reports a flat, severity-scored finding list. Use when the user asks to review a PR, review code changes, check a branch, do a local code review, or provides a GitHub PR URL.

The English summary is being prepared. Showing the original description.

Use when researching external libraries/frameworks (React, Radix, Tailwind, etc.) — reach for the Context7 MCP to get up-to-date docs. Not for internal codebase or design-system-token questions.

The English summary is being prepared. Showing the original description.

Use when building or styling a component in libs/ui-react or libs/ui-rnative — the cross-platform styling principles, plus routing to the platform mechanics: Tailwind + cva + cn on web, useStyleSheet + themeJS + lx on React Native. Load this before writing component styles.

The English summary is being prepared. Showing the original description.

Sync processed CSS design tokens with JavaScript theme objects for React Native. Use when aligning tokens after Figma sync, checking token consistency, or updating JS theme files manually.

The English summary is being prepared. Showing the original description.

Generate sophisticated initial access payloads designed to bypass email gateways and endpoint antivirus systems while executing Command and Control (C2) agents. Use this skill to craft malicious LNKs, ISOs, Weaponized Office Documents, and HTML Smuggling techniques for Red Team campaigns.

The English summary is being prepared. Showing the original description.

Identify and exploit Clickjacking (UI Redressing) vulnerabilities where a malicious website iframes a target application, tricking victims into performing unintended actions (e.g., transferring funds, deleting accounts, or granting permissions) via hidden layers.

The English summary is being prepared. Showing the original description.

A relentless interview to sharpen a plan or design.

The English summary is being prepared. Showing the original description.

One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".

The English summary is being prepared. Showing the original description.

Inspect or exercise the paused gaia curate orchestration scaffold for one source URL. The command currently persists an INITIALIZED run ledger and reports status; its 25 named workflow states and transition methods are a design skeleton, not an implemented automated curation or merge pipeline. Use only for scaffold development, status inspection, or dry-run contract work. For live curation, use gaia-full-pipeline or gaia-consult. Trigger phrases: "/gaia-quick-curate", "inspect gaia curate", "curate scaffold", "quick curate status". For batch/multi-page runs use gaia-curate-dynamic; for crawler branches use gaia-bot-curate; for pending intake proposals use gaia-draft-curate.

The English summary is being prepared. Showing the original description.

Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.

The English summary is being prepared. Showing the original description.

UI design and implementation for real product surfaces with taste-first critique, reference routing, project-specific design briefs, variation comparison, and implementation verification. Use when Codex should redesign, build, polish, or critique frontend UI by reading project context, exploring taste, routing through `references/catalog.md`, synthesizing `PROJECT_DESIGN.md` or `design.md`, using investment gates to avoid wrong taste/reference/scope, implementing in the existing stack, and evaluating whether the result is actually better. Best for app screens, dashboards, landing pages, query tools, product surfaces, and design explorations; not for backend-only work or tiny cosmetic edits.

The English summary is being prepared. Showing the original description.

Divergent ideation across model families — the same brainstorm, but each cognitive frame is handed to a different model (Claude sub-agent, OpenAI Codex, a cheap third via OpenCode) so the ideas diverge by frame and by model priors at once. Use for open design questions, architecture and API shape, naming, schema choices, fuzzy bugs with no known root cause, or on "multi adhd", "brainstorm with everyone", "wide ideas from all models". Skip for lookups, syntax, and anything phrased as "quick", "standard" or "canonical".

The English summary is being prepared. Showing the original description.

Create visually polished, editable PPT/PPTX presentations in a clean PPTPRO style. Use when the user asks for a beautiful, designed, non-generic PowerPoint deck, especially course presentations, reading applications, source-backed slides, scripts matched to slide pages, or requests to avoid AI-looking beige/card templates and repeatedly check visual quality.

The English summary is being prepared. Showing the original description.

Shape, implement, review, copy-edit, or harden Arcade user interfaces. Use for the website, terminal UI, game HUDs, interaction flows, responsive behavior, accessibility, Geist consistency, and any change affecting what a user sees, understands, chooses, or does. Skip backend-only, telemetry-only, generated-file, and test-only work with no shipped UI impact.

The English summary is being prepared. Showing the original description.

Guide for creating distinctive, production-grade frontend interfaces. Covers visual design systems, typography, color, motion, spatial composition, and web interface standards. Use when designing UI, establishing design systems, or reviewing visual quality of frontend code.

The English summary is being prepared. Showing the original description.

Establishes behavioral baselines from historical telemetry (process, network, or logon events) so hunts can flag rare and first-seen activity instead of relying on static signatures. Activates for requests to build a telemetry baseline, find rare or first-seen activity, or compute frequency baselines for anomaly hunting.

The English summary is being prepared. Showing the original description.

Hunts for anomalous authentication such as password spraying, brute force, and impossible-travel logons by aggregating Windows logon success/failure events per account and source over time. Activates for requests to hunt anomalous logons, detect password spraying or brute force, or find suspicious authentication patterns.

The English summary is being prepared. Showing the original description.

Hunts for lateral movement via remote service creation, admin share writes, and remote WMI process creation by correlating Windows logon, service install, and process-creation events. Activates for requests to hunt lateral movement, detect PsExec/WMIexec activity, or find remote execution over SMB and WMI.

The English summary is being prepared. Showing the original description.

Hunts for Active Directory credential and replication attacks — DCSync, Golden/Silver Ticket, and DCShadow — by analyzing directory-service-access (4662), Kerberos TGS (4769), and logon (4624) events for replication abuse and forged-ticket anomalies. Activates for requests to hunt DCSync, detect golden/silver tickets, or find Active Directory replication abuse.

The English summary is being prepared. Showing the original description.

Product Owner - scans codebase and creates or amends GitHub issues with PRD. Use when: PRD, feature, issue, create issue, amend issue, what should we build, plan feature, design feature, scope, requirements.

The English summary is being prepared. Showing the original description.

Build or iterate on a Pulp WebView UI using the native WebView bridge, embedded assets, directory-backed dev resources, and focused WebView validation.

The English summary is being prepared. Showing the original description.

The investigation harness for "why is this slow?" over a Pulp Perfetto trace (.pftrace). Runs the hypothesis→query→drill-down chain-of-evidence loop autonomously and returns a plain-English root cause + evidence + a concrete fix. TRIGGER on "why is my plugin slow to open", "find the slowest frames", "why is the UI stuttering", "why is my plugin using so much CPU", "which DSP node is expensive", "the load meter looks calm but CPU is pinned", or a named `pulp trace gpu-startup|gpu-health|gpu-probe` analysis. Ships Pulp-specific hints for dsp, frame, js, gpu, and cross-platform symptoms.

The English summary is being prepared. Showing the original description.

Leveraged-prototype dev loop (`pulp loop`) — focus marker plus normal watch/rebuild loop, with AOT analyzer guidance and deferred ar-swap/PR-monitor playbook. Use when porting an existing UI/bundle to Pulp, doing visual/behavioral parity work, or batching upstream framework gap fixes.

The English summary is being prepared. Showing the original description.

Search, inspect, plan, apply, remove, pack, and scaffold local Pulp package manifests. Use for Pulp-native source/UI/template kits and for untrusted or semi-trusted manifest-bearing artifacts that must be reviewed before project mutation.

The English summary is being prepared. Showing the original description.