How I Built an 8-Skill Research Engineering Plugin, Stdio MCP Server & Vector Comic Studio for Google Antigravity

A developer open-sourced agy-research-kit, an eight-skill Google Antigravity plugin for auditing and visualizing machine learning papers, paired with a stdio MCP server and a vector comic studio. The skills cover interactive HTML5 equation simulators, statistical re-auditing with Wilson and McNemar tests, Crossref/OpenAlex DOI verification, figure annotation, and 1080p trajectory animations, all run through PEP 723 inline metadata via uv to avoid system TeX or FFmpeg dependencies. A Gemma 4 LoopBreaker showcase demonstrates the kit on 4-bit quantization and multi-turn agent KV cache analysis.

Reading, auditing, and explaining dense machine learning or engineering papers shouldn't stop at a wall of plain-text chat bullets—or brittle LaTeX scripts that break on half of developer workstations. Over the past week, I architected and open-sourced My-antigravity-research-skills https://github.com/RobinaMirbahar/My-antigravity-research-skills agy-research-kit , a full-stack Google Antigravity Plugin designed specifically for rigorous scientific paper auditing, interactive simulation, and visual storytelling. 🔗 GitHub Repository: https://github.com/RobinaMirbahar/My-antigravity-research-skills https://github.com/RobinaMirbahar/My-antigravity-research-skills 🎮 Live HTML5 Interactive Paper Simulator: https://robinamirbahar.github.io/My-antigravity-research-skills/ https://robinamirbahar.github.io/My-antigravity-research-skills/ Google Antigravity gives developers five composable customization layers that fit together cleanly: SKILL.md : ~50 tokens YAML frontmatter only until the agent actually needs it—preventing context bloat across 8+ specialized workflows. mcp config.json : hooks.json : rules/AGENTS.md : agy- Research Skills Every script in agy-research-kit uses PEP 723 inline /// script metadata executed via uv run , plus headless Chromium/Edge and pymupdf + imageio ffmpeg —meaning zero system TeX or global FFmpeg installation headaches across Windows, macOS, and Linux: | Skill | What It Builds | Output Artifact | |---|---|---| | agy-interactive-paper-studio | Turns closed-form paper equations into a zero-backend 60-FPS HTML5/Canvas simulator | Standalone index.html | | agy-ablation-stat-auditor | Recomputes exact Wilson 95% score CIs , Fisher's Exact , McNemar paired p-values , & leaderboard noise floors | Audit Markdown/LaTeX + JSON | | agy-citation-doi-verifier | Verifies bibliographies against live Crossref & OpenAlex REST APIs and upgrades preprints to published venues | Traffic-Light DOI Audit | | agy-figure-forensics | Adds numbered vector callouts, regime shading, and Engineering Takeaway cards onto 300-DPI paper plots | A4 Visual Anatomy PDF | | agy-math-sandbox | Color-codes equations into operator blocks and runs deterministic NumPy/SciPy Monte Carlo verification | A4 Math Verification PDF | | agy-trajectory-cinematics | Renders 1920x1080 H.264 .mp4 animations pairing a live system state monitor with 2x2 real-time telemetry curves | 1080p .mp4 + Narration .md | | agy-graphic-story | Renders pure-code A4 Vector SVG Technical Graphic Novels with custom characters, blackboards, and verbatim scoreboards | A4 Vector Comic PDF | | agy-frontier-gap-radar | Orchestrates OpenAlex + arXiv retrieval into an N x 7 capability heatmap and novelty-checked research blueprints | A4 Frontier Gap Radar PDF | Gemma 4 LoopBreaker To test all 8 skills end-to-end on a real systems research problem, the repository includes a complete showcase in examples/gemma4-loop-breaker/ https://github.com/RobinaMirbahar/My-antigravity-research-skills/tree/main/examples/gemma4-loop-breaker analyzing how 4-bit weight quantization W4A16 interacts with growing multi-turn agent KV caches 1 - 1 / 1 + C e^{-delta} . agy-graphic-story Generated 100% programmatically from Python + SVG/HTML story svg engine.py with verbatim benchmark tables and automatic PyMuPDF 2-up visual QA: 📄 Download Full Sample PDFs Directly from the Repo: agy-trajectory-cinematics Using imageio ffmpeg inside an isolated uv run micro-environment, the plugin renders a crisp 1920x1080 H.264 .mp4 sweep synchronizing an agent state monitor with four live quantitative plots: 🎬 Watch / Download the Sample 1080p .mp4 : Gemma4 LoopBreaker Explainer v1.mp4 https://github.com/RobinaMirbahar/My-antigravity-research-skills/raw/main/examples/gemma4-loop-breaker/Gemma4 LoopBreaker Explainer v1.mp4 When you install plugins/agy-research-kit , Antigravity automatically registers two guardrails that keep AI research honest: research audit mcp.py Stdio MCP Server : verify wilson ci , verify fisher exact , leaderboard noise floor , and verify doi metadata over JSON-RPC so the agent never guesses confidence intervals or p-values mentally. stdlib shadow guard.py PostToolUse Hook : numbers.py , statistics.py , or math.py in your working directory which silently crashes numpy and scipy , the hook flags it immediately. Windows PowerShell : git clone https://github.com/RobinaMirbahar/My-antigravity-research-skills.git New-Item -ItemType Directory -Force -Path "$HOME\.gemini\config\plugins" | Out-Null Copy-Item -Recurse -Force My-antigravity-research-skills\plugins\agy-research-kit "$HOME\.gemini\config\plugins\" macOS / Linux: git clone https://github.com/RobinaMirbahar/My-antigravity-research-skills.git mkdir -p ~/.gemini/config/plugins cp -r My-antigravity-research-skills/plugins/agy-research-kit ~/.gemini/config/plugins/ Run the self-contained verification suite anytime with: uv run tests/test skills structure.py If you try agy-research-kit on your own papers or Kaggle competition writeups, drop a star on RobinaMirbahar/My-antigravity-research-skills https://github.com/RobinaMirbahar/My-antigravity-research-skills and let me know what research skill you'd love to see next