Antigravity-OS

Use this skill when the user wants to test, inspect, verify, or screenshot a page in the browser (e.g., "/browser-test", "/browser", "test in browser", "take screenshots", "verify in Chrome", "check devtools"). On Windows environments, this skill bypasses browser_subagent and uses Playwright MCP tools to navigate, evaluate JS/scroll, and capture screenshots reliably.

Use this skill when finding, scoring, or profiling prospects for the Cinematic Digital Showroom offer targeting luxury residential interior designers and boutique interior design studios. Activated by "find prospects", "research interior designers", "find Lagos prospects", "find Dubai prospects", "who should I target this week", "score this designer", "prospect research", "find designers with weak websites", or any task that involves identifying, qualifying, or prioritizing outreach targets for the BEVAMPED studio offer. Do NOT use for general web research, competitor profiling, or sales outreach copy (use sales-enablement or copywriting skills for those).

Run an after-action learning and capability-impact audit after a substantial completed task, milestone, investigation, launch, or creative project. Activate on `/learn`, "what did we learn", "audit what just happened", "which skill should improve", "update our workflow from this", or requests to convert recent work into reusable system improvements. Do not use for ordinary status summaries, unfinished work, generic code review, or automatic skill/memory mutation without explicit approval.

Use this skill when the user asks for senior creative direction, luxury web design judgment, spatial-editorial critique, or taste calibration for high-end interior, architecture-adjacent, spatial storytelling, portfolio, gallery-like, residential design, premium studio, or editorial brand websites.

Analyze and translate design references, award-site videos, screen recordings, screenshots, transcripts, AI observation reports, precedent collections, and inspiration links into brand-specific decisions. Use for requests such as "analyze these references", "what should we borrow", "compare these award websites", "turn these video reports into a plan", or "what should we keep, adapt, reject, or defer". Do not use for competitor pricing/market dossiers, approved motion-library lookup, brand diagnosis without references, or implementation from an already approved plan.

Use this skill when designing, auditing, or planning high-end interior decorator, interior design, spatial design, architecture, styling, furniture, decor, showroom, gallery, or luxury home websites. Activated by requests like "build an interior decorator portfolio", "make this spatial design site feel premium", "create a high-end interiors website", "design a decorator portfolio", "make this feel like a 20k website", "use the design audit grammar", or any visual task where rooms, materials, light, objects, before and after transformations, or curated spaces must drive the experience.

Use this skill when diagnosing or building positioning for interior decorators, interior designers, spatial studios, architecture-adjacent studios, staging brands, furniture/decor showrooms, luxury home stylists, or gallery-like spatial brands. Activated by "brand audit", "position this interior designer", "make this decorator feel premium", "brand world", "perception gap", "founder lore", "premium signal", or "why does this design site feel generic". Do NOT use for backend/API/security/database work or for visual execution without positioning evidence.

Use this skill when planning or implementing cinematic motion for high-end interior decorator, spatial design, architecture, gallery, showroom, furniture, decor, or luxury home websites. Activated by "add GSAP", "scroll animation", "make this cinematic", "room walkthrough", "parallax interior scene", "before/after reveal", "object spine", "curtain reveal", "image sequence", "WebGL", "canvas", "gallery procession", or any spatial storytelling motion task. Do NOT use for generic product dashboards, backend/API/security/database work, or decorative motion that is not tied to a room, material, threshold, object, proof, or inquiry moment.

Use this skill when planning cinematic interior designer websites, video-led portfolios, AI-generated room films, scroll-driven showroom pages, or full spatial web experiences where brand diagnosis must become scene sequence, image/video prompts, portfolio proof, and website choreography. Activated by "cinematic showroom", "video-to-website", "AI room video", "cinematic portfolio", "scroll-driven interior website", "Awwwards interior site", or when `spatial-experience-design` needs prompts and section choreography. Do NOT use for generic video backgrounds, product launch pages, backend work, or decorative motion without brand/spatial proof.

Use this skill when browsing, comparing, selecting, or applying prebuilt animation and transition references by communication job. Activated by "/motion-library", "/effect", "/apply-motion", "find a transition", "show me effects", or "what animations do we have". Do NOT use the library to force motion into a still-led concept or to choose an effect before its job and constraints are known.

Use this skill when an approved experience depends on authored scroll timing, pinning, transitions, persistent continuity, or media choreography, or when an existing site feels disconnected because sections were designed independently. Activated by "storyboard the scroll", "map scroll beats", "plan the pinned sequence", "how should the scroll feel", or a need to coordinate viewport-by-viewport narrative behavior. Do NOT use for ordinary page sequencing, copywriting, static editorial layouts, or as a universal precondition for design and implementation.

Use this skill when creating the narrative, emotional journey, copy direction, visual direction, or section sequence for high-end interior decorator, interior design, spatial design, architecture, staging, furniture, decor, showroom, gallery, or luxury home websites. Activated by "story", "position this interior brand", "portfolio narrative", "make it feel seductive", "spatial storytelling", "copy direction", "visual thesis", or any task where rooms, materials, transformations, proof, and inquiry must become a coherent website experience. Do NOT use for backend/API/security work or for writing final long-form copy without first defining the spatial narrative.

Design, audit, or implement usable frontend experiences for applications, SaaS products, dashboards, marketing sites, and optional spatial-brand surfaces. Use when a task involves user flows, information architecture, components, interaction states, forms, navigation, responsive behavior, accessibility, UX writing, visual hierarchy, or interface verification. Load spatial references only when the active profile or request is explicitly interior, showroom, gallery, furniture, decor, staging, luxury-home, or architecture-adjacent. Do not use for backend-only, API-only, database-only, or infrastructure-only work.

Use this skill when designing, creating, or modifying API endpoints; defining contracts between services; evaluating protocol choices (REST, GraphQL, gRPC, WebSockets); versioning or deprecating an API; designing error responses or pagination; or reviewing an existing API for consistency, security, or ergonomics. Signal phrases: "design the API", "create an endpoint", "REST", "GraphQL", "gRPC", "API versioning", "backward compatible", "breaking change", "error response", "pagination", "rate limiting", "API contract", "OpenAPI", "Protobuf", "webhook", "idempotency", "deprecation", "endpoint structure".

Use this skill when the user wants to apply a pre-built CSS transition or animation from the loading.io transition.css library to a specific element. Activated by "/apply-transition", "apply ripple", "apply loading.io transition", or when the user asks to animate an element using a CSS class effect.

Use this skill when designing system boundaries, data flows, component interfaces, or making structural technology decisions. Activated when the user is initializing a new project, service, or major feature; designing data flow between components; breaking apart a legacy system; defining folder structures or project organization; evaluating core technology or framework choices; or when the current system fails to scale. Examples: "how should I structure this?", "should this be a microservice?", "design the architecture for X", "what's the best way to organize this codebase?", "how should data flow between these components?".

Use this skill when writing, modifying, or generating code of any kind. Activated when the user asks to build features, implement functions, create components, write endpoints, set up forms, wire things together, or produce any working implementation. Trigger phrases: "build this", "implement", "write the code for", "create a function that", "add this endpoint", "make it work", "update this code to", "wire this together". Do NOT use for: pure architectural decisions before implementation starts (use architecture skill), root-cause debugging of existing broken code (use debugging skill).

Use this skill when selecting, auditing, or implementing color palettes for any brand, website, app, marketing asset, or design project. Activated by "choose a color palette", "color scheme", "brand colors", "color psychology", "what color should I use", "color harmony", "complementary colors", "color contrast", "accessible colors", "color roles", "functional color", "action color", "CTA color", "color for this brand", "color audit", "palette generation", "monochromatic", "analogous", "triadic", "tetradic", "split complementary", "color meaning", "what does this color convey", or any task where color decisions affect brand perception, usability, or emotional response.

When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep dive,' 'who are my competitors,' 'competitor landscape,' 'competitor dossier,' 'competitive audit,' or 'research these competitors.' Input is a list of competitor URLs. Output is structured competitor profile markdown files.

Use when the task requires context formatting guidance. Specialized rules for repairing Markdown lint errors in Gold Context files (MD025, MD060, MD024).

Use when a long or complex task needs a safe session boundary, durable resume state, or separation into focused follow-up sessions.

When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.

Use when writing or rewriting persuasive marketing copy for websites, landing pages, pricing pages, product pages, email, or modal messages. Trigger on requests for headlines, CTAs, value propositions, page copy, email copy, or stronger messaging. Use copy-editing when the task is primarily polishing existing prose, and page-cro when structure or conversion diagnosis is the main problem.

Use this skill when designing schemas, writing queries, planning migrations, or evaluating data model decisions. Activated when the user mentions creating or modifying database tables, writing SQL, data integrity issues, slow queries, indexing, data migrations, ORM behavior, or choosing a database technology. Signal phrases: "design the schema", "create the tables", "add a column", "migration", "database is slow", "query optimization", "indexing", "normalize / denormalize", "data model", "foreign key", "relationship between", "N+1 queries", "data integrity", "ORM", "access pattern". Also activate for any work involving data that crosses service boundaries or any data integrity concern.

Use this skill when investigating errors, crashes, unexpected behavior, or system failures. Activated when the user reports a bug, shares a stack trace or error message, describes tests failing unexpectedly, notices a regression (a feature that used to work no longer does), or when production telemetry alerts have fired. Examples: "this is broken", "I'm getting an error", "the tests are failing", "this stopped working after my last change", "the system is down". Do NOT use for general implementation work (use coding skill) or architecture decisions (use architecture skill).

Use this skill when the user wants to activate full deep-thinking mode before receiving an answer. Forces reading and applying all three core reasoning files: system-thinking.md, expert-cognitive-patterns.md, and first-principles.md. Activated when the user says "deep think", "think deeply about this", "/deep-think", "apply deep thinking", "reason through this carefully", "full cognitive analysis", "think hard about this", "I need you to really think", "first principles analysis", "challenge my assumptions", "don't give me a quick answer", or any request that demands visible, structured, rigorous reasoning before a response.

Design, inspect, or troubleshoot Deriv Bot XML and block-based trading strategies. Use for DBot imports, exported XML, block logic, demo validation, or migration errors; do not use for unrelated trading software.

Use this skill when the work involves infrastructure provisioning, deployment pipelines, observability, monitoring, incident response, or operational reliability. Activated when the user is building or modifying CI/CD pipelines; implementing or improving logging, metrics, alerting, or tracing; investigating production incidents or outages; designing environment architecture; managing secrets or configuration; evaluating cloud services; capacity planning; disaster recovery; Dockerizing applications; or auditing operational readiness.

Use when the task requires dox guidance. Evaluates and updates hierarchical AGENTS.md documentation to enforce folder-level contracts and prevent cascade effects during modifications.

Use this skill when auditing, designing, or refactoring website layouts, copywriting posture, inquiry paths, CTA structures, portfolios, case studies, or sales-to-onboarding transitions for professional services, agencies, creators, and high-end brands. Activated when analyzing positioning strategy, revising vendor copy, setting minimum engagements, or diagnosing buyer self-assessments. Examples: "audit my positioning", "WWP copy critique", "expert posture", "qualification gates", "paid diagnostic offer". Do NOT use for general copy editing (use copy-editing) or standard UI styling (use ui-ux).

Use when the task requires fallow guidance. Codebase intelligence for JavaScript and TypeScript. Free static layer reports quality, changed-code risk, cleanup opportunities (unused files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, feature flag patterns, and opt-in security candidates. Runtime coverage merges production execution data into the same health report for hot-path review, cold-path deletion confidence, and stale-flag evidence, with a single local capture available by default and continuous/cloud runtime monitoring available as an optional mode.

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context.

Use when diagnosing or improving conversion performance on marketing pages, signup flows, forms, onboarding steps, popups, or modals. Trigger on CRO, low conversion rate, high bounce or abandonment, unclear CTAs, signup friction, or a shared URL requesting conversion feedback. Use copywriting when the primary request is a fresh copy draft rather than conversion diagnosis.

Use this skill when diagnosing or resolving performance problems, optimizing slow systems, or proactively preparing for load. Activated when the user mentions slow response times, high resource consumption, timeouts, memory leaks, or anticipates increased traffic. Signal phrases: "it's slow", "optimize this", "bottleneck", "memory leak", "high CPU", "query is slow", "Core Web Vitals", "lighthouse score", "cache this", "timeout", "throughput", "latency", "load testing", "can it handle X users", "scale this", "performance is degrading". Also activate for capacity planning and performance-aware code review. Do NOT optimize without profiling evidence.

Use this skill when evaluating whether a feature is worth building, scoping work against business goals, identifying assumptions behind a proposal, or connecting engineering decisions to measurable outcomes. Activated when the question of WHAT to build or WHY to build it is open. Signal phrases: "should we build this?", "is this worth building?", "what's the MVP?", "scope this", "what should we prioritize?", "what problem does this solve?", "business impact", "success metric", "jobs to be done", "outcome", "assumption", "experiment", "why are we building this?", "requirements are unclear", "nobody is using this".

Use this skill when generating, writing, or refining prompts for AI image or video generation models (Midjourney, DALL-E, Stable Diffusion, Runway, Kling, Sora). Activated when the user asks for "high-detail prompts", "better image prompts", "create a prompt for", or complains that existing prompts are "rubbish", "generic", or "not professional". Do NOT use for text-to-text LLM prompt engineering.

Use this skill when improving code structure without changing external behavior, reducing technical debt, deciding between refactor vs rewrite, or planning legacy system modernization. Activated when the user mentions cleaning up code, reducing complexity, making code maintainable, improving a module that keeps breaking, deleting dead code, or performing a strangler fig migration. Signal phrases: "refactor", "clean this up", "technical debt", "legacy code", "rewrite vs refactor", "too hard to change", "no one understands this module", "we keep breaking this", "make this maintainable", "dead code", "code smell", "this area slows us down", "modernize", "migrate".

Use this skill when comparing tools, technologies, frameworks, or approaches, or when conducting technical feasibility analysis. Activated when the user asks "Should I use X or Y?", requests pros and cons, needs a build vs. buy evaluation, asks "What is the best way to..." where the answer depends on context, or needs research into industry norms, standards, or technical alternatives. Examples: "compare Redis and Memcached", "should we build this or use a SaaS?", "what are the tradeoffs of GraphQL vs REST for our case?", "research options for background job processing".

Use when you need to resolve an in-progress git merge/rebase conflict. Signal phrases: "resolving conflicts", "merge conflict", "rebase conflict", "git merge --continue", "git rebase --continue", "conflict hunks". Never abort a merge or rebase without explicit user consent. Always preserve both intents where possible, and verify with automated checks.

Use this skill when evaluating existing code for correctness, security, maintainability, or architectural alignment. Activated when the user asks for a code review, a pull request (PR) review, asks "Is this code good?", "What's wrong with this?", or needs an audit of a legacy codebase for technical debt or modernization. Also activated at the self-review phase (Phase 7: Critique) of any significant implementation. Examples: "review this PR", "audit this module", "what issues do you see in this code?", "check this before I merge". Do NOT use for implementation work (use coding skill). Always apply security lens during every review.