Claude Skills by majinmagros

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Use when f# testing patterns with xUnit, FsUnit, Unquote, FsCheck property-based testing, integration tests, and test organization best practices. Only for F# — not for other languages. Triggers on \"fsharp-testing\", \"fsharp testing\", \"testing\".

Watch your funnel 24/7, diagnose CRO causes and escalate to a human. Use when monitoring conversion, page speed, or funnel breakage daily. Use quando monitorar funil/CRO todo dia, diagnosticar queda de conversão, detectar página lenta ou etapa quebrada.

Use when orchestrating multiple models as architect + builders — debate, collaborate, cost tracking, software factory. Triggers on "fusion harness", "multi-model orchestration", "architect builder pattern", "model debate collaboration", "cost-aware agent routing", "software factory agents".

Use when integrating LLMs into game NPCs with persistent memory, personality, world state sync, and multi-player coordination. Triggers on \"game-npc-ai-integration\", \"NPC com IA\", \"game NPC LLM\", \"personagem nao-jogador\".

Use when building high-quality applications autonomously with a GAN-inspired Generator-Evaluator agent harness. Based on Anthropic's March 2026 harness design paper. Triggers on \"gan-style-harness\", \"gan style harness\", \"harness\".

Use when fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents. Triggers on \"gateguard\".

Use when a task needs an exceptional/impressive result and you can afford many tokens and time — large creative builds (games, apps, sites, 3D scenes) with subagents. Triggers on "gauntlet loop", "gauntlet-loop", "resultado de outro nível", "impressionar", "arquitetura de agentes", "subagentes em paralelo", "julgamento às cegas". Same family as graph-engineering/score-loop but adds BLIND judgment (verifier never sees the creation context) and the "impress the supervisor" acceptance bar. Do NO...

Use when working with Gemini CLI / Gemini Spark agent capabilities — Agent Skills (create/install skills), MCP apps and extensions, scheduled recurring tasks (Spark), Gemini Notebook (formerly NotebookLM), cheap Gemini Flash models, Lyria 3.5 music in Google Flow Music, and Google AI Studio (import from GitHub + publish free on a *.ai.studio subdomain). Triggers on "gemini cli", "gemini spark", "ai studio", "gemini skills", "notebooklm".

Use when commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers. Use only for advanced packaging/optimization (... Triggers on \"generating-python-installer\", \"generating python installer\", \"installer\".

Monitora desenvolvimentos de regulação de IA (leis, decretos, atos, registros oficiais) e traduz impacto prático para uso de IA. Gatilho: usuário pergunta "tem nova lei de IA", "como a regulação X afeta meu uso", "o que mudou no AI Act", ou precisa acompanhar cenário regulatório de IA de forma recorrente. Não-gatilho: não é consultoria jurídica (encaminhe ao oficial/advogado); não é análise de política geral sem ligação com IA. Outcome: delta regulatório (o que entrou em vigor / mudou) + clas...

Use when git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes. Only for Git — not for other VCS. Triggers on \"git-workflow\", \"git workflow\", \"workflow\".

GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git commands.

Use when integrating GLM/Z.ai as budget coding agent — browser automation, C/C++ strength, long task persistence, $18/mo quota. Triggers on "glm integration", "z.ai coding agent", "glm browser automation", "glm c coding", "glm budget tier", "glm trial quota".

Use when the user runs /goal to set a durable objective with an acceptance check for a long-running session. Triggers on "meta", "objetivo", "goal", "critério de aceite". Pins the objective, keeps working toward it, and does NOT declare completion until the acceptance criteria actually pass (real test runs, not vibes).

Use when idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications. Only for Go — not for other languages. Triggers on \"golang-patterns\", \"golang patterns\", \"patterns\".

Use when go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices. Only for Go — not for other languages. Triggers on \"golang-testing\", \"golang testing\", \"testing\".

Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.

Use when building graphs for agent orchestration — code-as-graph (dynamic workflow) or LLM-as-graph (skill + SOP + scripts), with I/O schemas, state management and verifier/planner separation. Triggers on "graph engineering patterns", "code as graph", "llm as graph", "dynamic workflow templates".

Componente de engenharia do harness de Drum'n Bass — produzir candidatos de áudio, verificar em paralelo (graph) e iterar até a nota mínima (loop). É companheira do `dnb-production` e uma aplicação específica da `engenharia-de-grafos` (a canônica). Use junto com `dnb-production`; para a teoria genérica de grafos/orquestração, consulte `engenharia-de-grafos`. Triggers on "graph engineering", "grafos", "verificar em paralelo", "loop engineering", "gerar candidatos", "rankear", "nota 80", "pipel...

Use when answering questions about a large/legacy codebase burns tokens or hallucinates, or when onboarding to a new repo. Triggers on "graphify", "grafo de conhecimento", "mapa do repositório", "entender a arquitetura", "consome muitos tokens", "como X conecta com Y", "onboarding em projeto". Turns a repo into a queryable knowledge graph.

Use when the user runs /grill-with-docs to stress-test an idea AND record settled decisions in project docs. Triggers on "grila e documenta", "decisões no docs". Same one-question-at-a-time interview as /grill, but after each answer writes a structured decision record (decision, rationale, rejected alternatives) into a DECISIONS file. Does NOT implement.

Use when the user runs /grill to stress-test an idea, plan or design before building. Triggers on "grila", "testa a ideia", "pressão-teste", "interroga o plano". Interviews the user ONE decision-forcing question at a time, grounded in the workspace, until goals, non-goals, constraints, risks and validation criteria are sharp. Does NOT implement.

Stress-test a plan and its implementation with repeated and adversarial runs (edge cases, extreme inputs, concurrency, load) before the solution is executed or finalized. Use when a plan or code patch must be proven highly reliable before completion.

Use when building teams of single-job bots with shared templates, dual memory, unified computer, teach-by-recording, routines, and visible handoffs. Triggers on \"bot team\", \"grokbot\", \"teach-a-task\", \"dual memory\", \"bot routines\", \"group chat bots\". Non-triggers: single human-plus-agent workspace (use buzz-workspace-teaming), one-off file task automation (use claude-cowork-patterns). Outcome: a bot team with roles, templates, memory policy, routines, approvals, and full logs.

Use when use after a complex task, failure, or when reviewing what was learned. Teaches how to write growth logs that extract reusable patterns — not diary entries. Triggers on \"growth-log\", \"growth log\".

Use when applying GSAP/ScrollTrigger best practices — scroll-linked animations, interactive effects, buggy GSAP logic fixes. Triggers on "gsap", "scrolltrigger", "scroll animation", "pinning", "scrub", "greensock", "animation performance", "timeline sequencing".

Compare AI agent harnesses third-party on the same task and model via Harness Arena. Use when choosing between harnesses or validating a harness change. Use quando comparar harnesses (Claude Code, Codex CLI, OpenCode...), ler battle-log/leaderboard, submeter benchmark próprio.

Coach de bem-estar a partir de dados de wearables com coleta recorrente. Use quando o usuário pedir análise de treino, sono, recuperação, rotina saudável, conectar garmin/strava/google health. Triggers PT: coach de treino, analisar meu sono, dados do garmin, rotina de bem-estar. Triggers EN: wearable coach, analyze my sleep, training data, strava analysis.

Use when clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Triggers on \"healthcare-cdss-patterns\", \"healthcare cdss patterns\", \"patterns\".

Use when eMR/EHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Triggers on \"healthcare-emr-patterns\", \"healthcare emr patterns\", \"patterns\".

Use when verifying healthcare app deployments for patient safety: CDSS, PHI, data integrity gates. Triggers on \"healthcare-eval-harness\", \"healthcare eval harness\", \"harness\".

Use when protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors. Triggers on \"healthcare-phi-compliance\", \"healthcare phi compliance\", \"compliance\".

Convert local Hermes operator workflows into sanitized ECC skills and release-pack artifacts. Use when preparing a Hermes workflow for public ECC reuse without leaking private workspace state, credentials, or local-only paths.

Use when design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. Triggers on \"hexagonal-architecture\", \"hexagonal architecture\", \"architecture\".

HIPAA-specific entrypoint for healthcare privacy and security work. Use when a task is explicitly framed around HIPAA, PHI handling, covered entities, BAAs, breach posture, or US healthcare compliance requirements.

Use when readiness checklist for homelab VLAN segmentation, local DNS filtering, and WireGuard-style remote access before changing router, firewall, DHCP, or VPN configuration. Triggers on \"homelab-network-readiness\", \"homelab network readiness\", \"readiness\".

Use when practical home and homelab network planning for gateways, switches, access points, IP ranges, DHCP reservations, DNS, cabling, and common beginner mistakes. Triggers on \"homelab-network-setup\", \"homelab network setup\", \"setup\".

Use when pi-hole installation, blocklist management, DNS-over-HTTPS setup, DHCP integration, local DNS records, and troubleshooting broken DNS resolution on a home network. Triggers on \"homelab-pihole-dns\", \"homelab pihole dns\".

Use when segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and wireless SSID mapping. Triggers on \"homelab-vlan-segmentation\", \"homelab vlan segmentation\", \"segmentation\".

Use when wireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a home network from mobile and laptop clients. Triggers on \"homelab-wireguard-vpn\", \"homelab wireguard vpn\".

Use when this skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs guidance on hookify rule syntax and patterns. Triggers on \"hookify-rules\", \"hookify rules\", \"rules\".

Use when the user wants text that does not sound AI-generated — emails, posts, WhatsApp, e-commerce copy, replies. Triggers on "humanizar", "texto com cara de IA", "escrita parece IA", "texto robotizado", "AI slop", "reescreve pra não parecer IA". Detects and removes AI-typical writing patterns, keeps meaning and brand tone. Para UI/interface, use taste.

Use when working with the Hyper3D Rodin API — credits system, model versions, download formats, MetaHuman export, credit optimization. Triggers on "hyper3d rodin api", "rodin api credits", "rodin model versions", "rodin download formats", "rodin credit optimization", "hyper3d rodin api key".

Use when generating 3D faces with Hyper3D ChatAvatar/Rodin — text-to-face, image-to-3D, weights/seeds prompt engineering, model versions, FBX/GLB/USDZ and MetaHuman export. Triggers on "hyper3d rodin pipeline", "chatavatar pipeline", "text to face 3d", "image to 3d face", "rodin seed control".

Use when editing video with an AI coding agent (Codex, Claude Code) through Hyperframes HTML-to-video: transcript-first beats, HTML/CSS/JS motion graphics, Studio preview, screenshot verify loop. Triggers on \"hyperframes\", \"codex edit video\", \"html to video\", \"motion graphics with ai\", \"transcript beats\". Non-triggers: React-based programmatic video (use remotion-video-creation); raw silence-cut only (use video-cut-pipeline). Outcome: a rendered MP4 plus a reusable skill that repeat...

Use when scaffolding Hyperledger Fabric blockchain networks — CA → peers → orderers → channels → chaincode → Explorer → Caliper → API Node.js. Based on Pavan Adhav video "Custom Hyperledger Fabric Network Code Generator". Only for Hyperledger Fabric — not for other blockchains. Triggers: "hyperledger fabric generator", "fabric network scaffolding", "fabric CA peers orderers", "chaincode deployment", "fabric explorer caliper", "blockchain network generator".

Use when converting a static image into optimized Three.js/WebGL code from scratch — geometry, materials, lighting, interactive scene. Triggers on "imagem para 3D", "img2threejs", "image to threejs", "gerar threejs de imagem", "static image to interactive 3D", "webgl from image".

Fix front-end sem graça with Impeccable (44k stars, 23 commands, live mode). Use when UI needs 3 live versions to pick and save to code. Triggers on \"impeccable\", \"impecable\", \"live design\", \"23 commands\", \"front-end sem graça\"

Legacy-project style inheritance skill. Use when the user types /inherit-legacy-style, or when onboarding an AI coding agent onto a hand-written legacy project and you need to prevent "style drift" (the model imposing its pretrained mainstream idioms onto the project). Language- and framework-agnostic — it aligns meta-architecture only, not syntax. Once run, it becomes a behavioral constraint on all subsequent coding tasks. Do NOT use for pure research or one-off questions unrelated to code-s...