メニュー
このリポジトリの skills
SkillsMP は Kayforkind/skill-slice から 495 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
Kayforkind/skill-slice収集済み skill 495 件中 40 件を表示しています。
Creates Godot 4.3+ editor plugins: plugin.cfg, EditorPlugin enter/exit registration, @tool scripts, custom inspectors, docks, and 3D gizmos. Use when extending the Godot editor with custom node types, inspector widgets, or project tooling. Not for runtime…
原文の言語: 英語
Designs classical game AI as three layers: decision (FSM, behavior trees, utility, GOAP/HTN), NavMesh/A-star pathfinding with funnel smoothing, and Reynolds steering/flocking plus bounded perception. Use when building or debugging enemy/NPC agents that get…
原文の言語: 英語
Implements reactive Godot 4.x cameras: delta-scaled follow, trauma shake, room zones, SpringArm3D/orbit/FPS rigs, pop-free transitions, split-screen SubViewports, and XROrigin3D locomotion. Use when the view must react to gameplay. Not for static cameras,…
原文の言語: 英語
Builds Godot 4.3+ dedicated servers: headless export, dedicated_server feature tag, lobby/match state machines, CLI config, Linux/systemd deploy. Use when exporting a headless authoritative server, lobby management, or container/VPS hosting. Not for client…
原文の言語: 英語
Integrates FMOD Studio or Audiokinetic Wwise: named events, parameters/RTPCs, banks, buses/snapshots/ducking, adaptive music, 3D spatialization, and Unreal/Unity/Godot plugins. Use when wiring FMOD, Wwise, RTPC, soundbanks, EventInstance, or AkAudioEvent. Not…
原文の言語: 英語
Architects Godot 4 local multiplayer party games: MinigameData .tres resources, PartyManager scoring, 2-4 player input mapping, 1v3 asymmetric balance, threaded minigame load/unload, and SubViewport split-screen. Use for Mario Party-style or WarioWare…
原文の言語: 英語
Implements Godot 4.3+ 2D platformers: CharacterBody2D coyote time, jump buffering, variable jump height, squash/stretch juice, checkpoints, collectibles, and assist options. Use when building a precision platformer or debugging floaty jumps and tunneling.…
原文の言語: 英語
Blueprints Godot 4 racing: VehicleBody3D and VehicleWheel3D, sequential checkpoints, rubber-banding AI, drift-boost, speed-FOV camera, lap UI, and ghost cars. Use when building arcade, kart, or sim racers, time trials, or track vehicle physics. Not for Godot…
原文の言語: 英語
Architects Godot 4 romance and dating-sim loops: multi-axis affection (attraction/trust/comfort), signal-driven TimeManager, date events, and route branching. Use when building otome, Persona-style social links, or relationship-centric Godot games. Not for…
原文の言語: 英語
Godot 4 FPS/TPS gunplay blueprint covering WeaponData resources, recoil and bloom, hitscan vs projectile, aim assist, client prediction, and hit registration. Use when building competitive shooters, battle royales, or tactical FPS in Godot 4. Not for…
原文の言語: 英語
Builds Godot 4.3+ sports sims: RigidBody3D Magnus ball physics, formation-slot team AI, contextual pass/shoot/tackle input, and broadcast cameras. Use when making soccer, basketball, hockey, racing, or arcade sports. Not for turn-based or cosmetic-physics…
原文の言語: 英語
Implements Godot 4.3+ screen-space HUDs on CanvasLayer: health bars, score, minimap, damage numbers, toasts, and interaction prompts. Use when building in-game HUD widgets that must stay fixed to the viewport. Not for Control layout and themes (godot-ui) and…
原文の言語: 英語
Wires mobile games to App Store and Google Play: StoreKit 2 / Play Billing with server-side receipt validation, AdMob/LevelPlay/MAX mediation, and Game Center / Play Games Services v2. Use when the user mentions IAP, receipt validation, App Store Connect,…
原文の言語: 英語
Implements Godot 4.3+ visual particle FX with GPUParticles2D/3D, ParticleProcessMaterial, emission shapes, subemitters, trails, attractors, and collision recipes (fire, smoke, sparks). Use when the effect is visual flavor the simulation does not depend on.…
原文の言語: 英語
Drives the Gemini side panel inside Gmail, Docs, Sheets, Slides, and Drive via browser automation: thread summaries, Help me write drafts, Sheets =AI(), Slides images, and questions about Drive files. Use when Gemini should act on live Workspace content…
原文の言語: 英語
Analyzes vector geospatial data with GeoPandas: load GeoJSON, spatial filter or join, and metric distances after projecting off EPSG:4326 (EPSG:4087 or UTM). Use when calculating distances between features, filtering points in polygons, or working with…
原文の言語: 英語
Sets up versioned Git hooks with Husky + lint-staged, the Python pre-commit framework, or core.hooksPath: pre-commit lint/format, commitlint, pre-push tests. Use when the user mentions pre-commit, commit-msg, Husky, lint-staged, commitlint, or githooks. Not…
原文の言語: 英語
End-to-end Git for agents on Windows/PowerShell: status triage, branching, staging, commits, rebase/merge, conflict resolution, stash, cherry-pick, bisect, and safety gates before destructive ops. Use when the user asks for git, commit, branch, rebase, merge,…
原文の言語: 英語
Designs, debugs, and hardens GitHub Actions: reusable workflows, matrices, OIDC, SHA-pinned actions, caching, environments, and release automation. Use when authoring .github/workflows, fixing a failing pipeline, or hardening CI. Not for…
原文の言語: 英語
Reviews local git diffs and open GitHub PRs: checklists, inline comments, approve or request-changes via gh or REST. Use when reviewing code before push, reviewing PR #N, or posting a formal GitHub review. Not for opening or merging PRs (github-pr-workflow)…
原文の言語: 英語
Implements frosted-glass panels via CSS backdrop-filter, SwiftUI ultraThinMaterial, Flutter BackdropFilter+ClipRRect, React Native BlurView, or Compose haze fallbacks. Use when the user wants glassmorphism, frosted glass, blurred translucent cards, or a…
原文の言語: 英語
Drives Google Search AI Mode (google.com/ai) in the browser: Deep Search cited multi-page reports, Search Labs agentic tasks such as reservations, and Ultra information agents. Use when the user wants a Search-grounded cited report or those agentic/monitor…
原文の言語: 英語
Creates structured Google Vids (vids.new) work videos via Help me create: prompt plus attached Docs/Sheets/Slides become outline, scenes, stock media, script, AI voiceover, 8s Veo clips, and avatars. Use when the user wants an explainer, launch, or training…
原文の言語: 英語
Drives Gmail, Calendar, Drive, Docs, Sheets, and Contacts through the gws CLI or the bundled Python OAuth wrapper (setup.py / google_api.py). Use when the user wants to search or send mail, manage events, upload or share Drive files, or edit Sheets/Docs. Not…
原文の言語: 英語
Integrates GSAP into Vue 3, Nuxt 4, Svelte, and SvelteKit via onMounted/onMount, gsap.context scoped selectors, and ctx.revert() cleanup. Use when writing or reviewing GSAP in those non-React frameworks, including ScrollTrigger plugin registration. Not for…
原文の言語: 英語
Implements coordinated GSAP 3 motion (timelines, ScrollTrigger, Flip, MotionPath, Draggable, SplitText, ScrollSmoother, SSR hydration, prefers-reduced-motion). Use when designing, debugging, or refactoring JS-driven web animation (gsap.to, useGSAP,…
原文の言語: 英語
Operates IMAP/SMTP mailboxes from the terminal with the Himalaya CLI (list, search, compose, reply, flags, attachments, JSON). Use when reading or sending mail non-interactively via himalaya. Not for Resend/React Email app integration (email) and not a Hermes…
原文の言語: 英語
Builds no-engine browser games with Canvas2D (raw WebGL2 only when Canvas stalls), a fixed-timestep loop, sprites, AABB, scenes, and WebAudio unlock-on-gesture. Use when the user wants a lightweight HTML5 canvas game without Phaser or Three.js. Not for Phaser…
原文の言語: 英語
Operates the Hugging Face Hub via the hf CLI (replaces huggingface-cli): download/upload models datasets spaces, auth, cache, buckets, jobs, inference endpoints, collections, papers, and webhooks. Use when the task is Hub file or repo operations from a…
原文の言語: 英語
Runs local GPU evaluations of Hugging Face Hub models with inspect-ai or lighteval and vLLM, Transformers, or accelerate backends (uv scripts). Use when choosing an eval framework, running a smoke test, or picking a local inference backend. Not for remote…
原文の言語: 英語
Calls the Hugging Face Dataset Viewer HTTP API (datasets-server.huggingface.co) to validate datasets, paginate, search, or filter rows, and list parquet shards. Use when inspecting or extracting rows from Hub datasets without loading them fully. Not for…
原文の言語: 英語
Adds Hugging Face model-card evaluation scores: Hub .eval_results YAML, legacy model-index EvalResult, README table extraction, and Artificial Analysis imports. Use when publishing benchmark numbers on a model repo or mapping vLLM/lighteval/inspect-ai scores…
原文の言語: 英語
Reads Hugging Face paper pages as markdown and queries the papers API for authors, linked models/datasets/spaces, GitHub, and project URLs. Use when the user shares an hf.co/papers or arXiv URL or ID, or asks to summarize an AI paper on that index. Not for…
原文の言語: 英語
Publishes a Gradio Hugging Face Space that runs inference with a user-provided LoRA on ZeroGPU (diffusers pipelines for Qwen-Image, LTX, FLUX, SDXL, and similar). Use when the user wants a browser demo or playground for a LoRA. Not for training LoRAs, local…
原文の言語: 英語
Creates, deploys, and debugs Hugging Face Spaces (Gradio, Docker, or Static SDKs, ZeroGPU, buckets, inference providers). Use when hosting an app on Spaces, porting a repo, fixing Space builds, or configuring ZeroGPU. Not for LoRA/QLoRA training (peft). Never…
原文の言語: 英語
Trains and runs Hugging Face tokenizers (Rust core): BPE, WordPiece, Unigram, offset alignment, padding/truncation, and PreTrainedTokenizerFast wrap. Use when the user needs fast tokenization, custom tokenizer training, or token-to-text offsets for NER/QA.…
原文の言語: 英語
Builds and debugs Gradio Spaces on Hugging Face ZeroGPU: @spaces.GPU, python_version pins, requirements without pinning spaces, duration/quota, pickle process isolation, CUDA wheels, and concurrency. Use when writing or reviewing ZeroGPU Space code. Not for…
原文の言語: 英語
Builds Inngest serverless functions: typed EventSchemas, step.run checkpoints, step.sleep, step.sendEvent fan-out, cron, concurrency limits, and a Next.js/Vercel serve() handler. Use when the user mentions Inngest, serverless background jobs, durable steps,…
原文の言語: 英語
Writes and runs k6 load tests for HTTP APIs, WebSockets, and browser scenarios, covering smoke/load/stress/spike/soak profiles, thresholds, and CI regression. Use when validating SLA budgets or comparing release behavior under synthetic load. Not for WebGL…
原文の言語: 英語
Integrates Langfuse traces, spans, generations, prompt versions, datasets, and LLM-as-judge scores with LangChain, LlamaIndex, OpenAI, and Vercel AI SDK. Use when adding LLM observability, cost tracking, or prompt A/B. Not for generic APM…
原文の言語: 英語