Antigravity-Skills

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration.

Build a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a product / subject / brand and wants a landing page, promo site, product showcase, marketing page, or storytelling site. Works for any language and any subject. The signature effect is mouse-driven video scrubbing — the hero video lives across the entire page as a fixed backdrop, and moving the mouse left-right scrubs the video timeline so the subject responds to the cursor. Below the hero, 4-5 fully-opaque sections each carry their own brand identity (color, typography emphasis, layout pattern) and walk the viewer through a narrative arc (e.g. longing -> joy -> nostalgia -> contemplation -> action). Do NOT use for parallax frame-scrub landings where the page itself doesn't scroll (use parallax-landing-page instead) or for video editing / captioning workflows (use video-edit).

Convert frontend code (Vite, React, etc.) to a Stitch Design by chaining static HTML extraction, design system extraction, and file upload. **ALWAYS** use this skill when the user's intent is to move existing web apps or React components into Stitch (e.g., requests to "save", "migrate", or "upload"). You must use this skill even for simple "save" operations, as it is the only way to ensure the design system is extracted and assets are properly linked.

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. Use this for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work goes to context-optimization, conversation summarization goes to context-compression, and project-shape decisions go to project-development.

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.

Generate a concise 4-5 page equity research earnings preview for a single company. Analyzes the most recent earnings transcript, competitor landscape, valuation, and recent news to produce a professional HTML report.

This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.

Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo — even if they just say "what does this app look like?" or "pull out the design from this code."

Extract self-contained static HTML from a built web application or React components by inlining CSS and images. Use this skill whenever you need to capture a specific UI state, share a static version of a page, or prepare assets for Stitch upload, even if the user just asks to 'save the HTML' or 'mock the view'.

This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.

Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional UI/UX terminology, design tokens and theme system capabilities.

This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.

Database management, forms, reports, and data operations with LibreOffice Base.

Spreadsheet creation, format conversion (ODS/XLSX/CSV), formulas, data automation with LibreOffice Calc.

Vector graphics and diagram creation, format conversion (ODG/SVG/PDF) with LibreOffice Draw.

Presentation creation, format conversion (ODP/PPTX/PDF), slide automation with LibreOffice Impress.

Document creation, format conversion (ODT/DOCX/PDF), mail merge, and automation with LibreOffice Writer.

Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.

Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.

Convert Stitch HTML designs to React Native components with StyleSheet

Best practices for Remotion - Video creation in React

Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks

IAM policy review, hardening, and least privilege implementation

Automate AWS secrets rotation for RDS, API keys, and credentials

Comprehensive AWS security posture assessment using AWS CLI and security best practices

Send and receive iMessage, SMS, and RCS from application code via the Sendblue HTTP API — text, media, group messages, send styles, reactions, typing indicators, status callbacks, and inbound webhooks.

Send iMessage and SMS from the shell via the @sendblue/cli npm package — outbound sends, contact management, and account setup with no API client or webhook server required.

Text the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound, optionally wired to a Claude Code Stop hook for automatic fire.

Text Claude from your phone — set up the njerschow/textme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number whitelist.

Creates professional investment banking strip profiles (company profiles) for pitch books, deal materials, and client presentations. Generates 1-4 information-dense slides with quadrant layouts, charts, and tables.

This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming conventions, actionable error recovery messages, MCP server design, tool-set consolidation, and deciding when to add or remove an individual tool. Use this when the unit of work is a single tool or a set of tools. Route project-shape, pipeline architecture, and task-model-fit decisions to project-development; route deciding whether to introduce sub-agents to multi-agent-patterns.

Upload local assets (images, mockups, extracted HTML) to a Stitch project. ALWAYS use this skill when you need to upload visual assets or full HTML pages to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.

Guide React and Next.js view transitions, shared element animations, route transitions, transition types, and reduced-motion-safe UI state animation.

Edit any video into a captioned showcase. Transcribe, present a review screen for the user to fix mishears, then build a HyperFrames composition with liquid-glass caption pills, background removal, and render the final video. Renders both 16:9 and 9:16 vertical modes from the same source. Pauses for user approval on the transcript before final render. Pairs with hyperframes, hyperframes-cli, and yuv-design-system.