arkit-rendering-context-providers
Build and debug ARKit rendering-context providers for visionOS 27: EnvironmentLightEstimationProvider, StereoPropertiesProvider, and VisualFidelityProvider. Use when matching virtual lighting to the environment, informing custom stereo rendering, coaching device fit, or tuning foveated field of view.
arkit-spatial-tracking-providers
Build and debug ARKit spatial tracking providers for visionOS 27: WorldTrackingProvider, PlaneDetectionProvider, SceneReconstructionProvider, RoomTrackingProvider, and SharedCoordinateSpaceProvider. Use when implementing world anchors, device pose queries, surface placement, mesh reconstruction, room context, or shared coordinate spaces.
realitykit-animation-physics
Implement and debug RealityKit animation, character controllers, skeletal poses, IK, body tracking, blendshapes, animation graphs, retargeting, root motion, navigation, behavior trees, collision, physics bodies, joints, forces, particles, compute simulations, and cloth on visionOS 27. Use when a RealityKit task is primarily about motion, character behavior, physical simulation, hit-test collision shape details, particle simulation, or animation/physics troubleshooting.
realitykit-audio-spatial
Implement and debug RealityKit spatial audio, ambient audio, channel audio, audio libraries, audio mix groups, reverb, grouped playback, and acoustic simulation on visionOS 27. Use when a RealityKit task is primarily about placing sound in 3D, loading or organizing audio resources, controlling channel or ambient playback, mixing groups, room acoustics, or audio behavior tied to RealityKit entities.
realitykit-ecs-systems
Design, implement, and debug custom RealityKit components, systems, ECS queries, component registration, update loops, Codable component state, and per-frame multi-entity behavior on visionOS. Use when documented RealityKit components do not represent the needed state or behavior, when behavior spans multiple entities, or when a task needs custom System and Component architecture instead of SwiftUI view logic.
realitykit-rendering-materials
Implement and debug RealityKit rendering, materials, lighting, cameras, visual effects, post-processing, render cost controls, Gaussian splats, decals, lightmaps, probes, LOD, and occlusion on visionOS 27. Use when a RealityKit task is primarily about visual appearance, mesh/material display, lights, shadows, tone mapping, bloom, camera projection, rendering performance, or choosing rendering components instead of animation, audio, interaction, or custom ECS behavior.
shareplay-developer
Build, integrate, and troubleshoot SharePlay GroupActivities features for visionOS 27, including GroupActivity definitions, activation flows, GroupSession lifecycle, messaging and journals, ShareLink and SharePlay UI surfaces, and spatial coordination.
spatial-app-architecture
Choose and refactor visionOS app architecture across surfaces, scene boundaries, state ownership, and file layout. Use when deciding window vs volume vs immersive space, splitting a feature across scenes, cleaning up a monolithic spatial root, or defining the ownership map before implementing SwiftUI or RealityKit details.
spatial-swiftui-developer
Design and implement visionOS 27 SwiftUI scenes that integrate RealityKit content. Use when building spatial UI with RealityView, Model3D, attachments, volumetric windows, ImmersiveSpace, spatial gestures, windowing, spatial layout, or when choosing SwiftUI vs RealityKit APIs for 3D presentation.
swiftui-chart3d-developer
Build SwiftUI Chart3D and Swift Charts 3D visualizations for visionOS 27 and Apple platforms. Use when implementing Chart3D, SurfacePlot, 3D PointMark, RuleMark, RectangleMark, Chart3DPose, 3D chart scales, axis labels, camera projection, or spatial data-visualization interactions.
tkr-skill-writer
Guide for creating and structuring skills with consistent formatting, clear documentation, and proper reference organization. Use when creating new skills or updating existing skill documentation.
usd-editor
Guide for modifying USD ASCII (.usda) files and command-line USD workflows, including prims, properties, composition arcs, variants, transforms, usdcat, usdchecker, usdrecord, usdtree, usdzip, and usdedit. Use when editing or reviewing .usda files by hand, validating USD/USDZ assets, or working in an asset pipeline outside runtime Swift USDKit.
usdkit-runtime-developer
Build USDKit runtime editing flows on visionOS 27, macOS 27, or iOS 27. Use when Swift code imports USDKit, opens or creates USDStage and USDLayer values, edits USDPrim attributes, observes USDStage.ObjectsDidChange, exports runtime USD packages, or bridges live stages through RealityKit USDStageComponent.
visionos-immersive-media-developer
Implement immersive and spatial video experiences on Apple Vision Pro (visionOS 27), including AVKit AVExperienceController, RealityKit VideoPlayerComponent setup, Apple Projected Media Profile (APMP), portal/progressive/full immersive viewing modes, transitions and events, comfort mitigation, and Apple Immersive Video authoring workflows.
visionos-widgetkit-developer
Build and debug WidgetKit widgets for Apple Vision Pro (visionOS), including mounting styles (elevated/recessed), textures (glass/paper), proximity-aware layouts via LevelOfDetail, interactive widgets with AppIntents, widget rendering modes (accented/fullColor), and timeline update troubleshooting. (visionOS widgets are pinned spatial objects, not watch complications.)
code-refactor-master
Code refactoring expert for improving code quality, readability, maintainability, and performance. Specializes in Java and Python refactoring patterns, eliminating code smells, and applying clean code principles. Use when refactoring code, improving existing implementations, or cleaning up technical debt.
add-time-space
Add standardized Javadoc time and space complexity comments to LeetCode Java solutions. Use when a directory under leetcode_java/ needs its `time = O(...)` / `space = O(...)` annotations added, normalised from inline comments, or filled in by hand where the script could not infer them.
l3-core
Report where the L3 core set stands and pick the next problems to drill from it. The set is Blind 75 plus the NeetCode 150 problems README marks MUST — 99 problems, held fixed in data/l3_core.json so its ok share means something month to month — and the verdict for each is the latest annotation in data/progress.txt, not README's status column. Use when asked what to practise today, how ready the core set is, how many of Blind 75 are solid, which problems keep coming back, or to refresh the set after a MUST marker or a list changed. Triggers - "/l3-core", "/l3-core next 5", "what should I drill today?", "how is the core set looking?", "which Blind 75 are still again?", "refresh the l3 core list".
lc-again
Move a problem's README status cell after a re-solve — promote AGAIN to OK when it was genuinely re-derived unaided, add a review pass when it was not, or demote OK back to AGAIN when a solid problem comes back. Keeps the trailing `*` run, which is the recorded pass count that the cost curve and the review planner both read, and refreshes data/again_problems.txt. Use when asked to mark a problem solid, to graduate an AGAIN marker, to record another failed pass, or to update the status column after drilling something. Triggers - "I finally got 128, mark it OK", "/lc-again 139", "promote 1143 to OK", "560 came back again", "refresh the again list".
lc-algo-demo
Add or edit an algorithm visualizer under algo_demo/ against the shared contract the other 36 pages already obey — colours read from the VIZ palette and never hardcoded, no re-implementation of the devicePixelRatio canvas wrapper, the step trace written in the three shapes createLogger renders as structure, the trace in its own full-width panel below the canvas, and `draw = VIZ.repaintable(draw)` for any draw() that takes arguments. Use when asked to add a visualizer, animate an algorithm, build a demo page, or change something that should look the same on every visualizer. Triggers - "add a visualizer for Dijkstra", "/lc-algo-demo trie", "animate the sliding window", "the trace is unreadable on the segment tree page".
lc-cheatsheet
File a LeetCode problem into the cheatsheets under doc/cheatsheet/ the way the existing sections are written — find the sheet whose Scope line owns the topic, file it under the pattern it belongs to (a worked example, a variation on an existing template, a new pattern section, or a new sheet), smoke-test every snippet, fix the heading anchors the edit moved, and re-translate the 中文 sections it invalidated. Use when asked to add or update a cheatsheet, to document a pattern just learned, to add an LC example or a template variation to a sheet, or to start a new cheatsheet. Triggers - "add LC 1650 to binary_tree as a variation", "/lc-cheatsheet 239 into sliding_window", "document the monotonic stack pattern", "update the LCA part of the binary tree cheatsheet".
lc-coach
FAANG coding-interview coach. Scores a solution the way an interviewer does on the six-point scale (SH/H/LH/LNH/NH/SNH), writes the debrief packet from the interviewer's side of the table, teaches the DSA fundamentals underneath, dry-runs code out loud, names the one line that blocks the optimal complexity, and recommends the sibling problems to drill next. Use when preparing for or debriefing a LeetCode-style SWE interview — "review my solution", "would this pass?", "what's my verdict?", "how would an interviewer see this?", "why is this O(n^2)?", "mock interview me", "what should I do after LC 239?".
lc-discussion
Search recent LeetCode Discuss posts (leetcode.com/discuss/) by keyword — a company, a level, a round — read the ones that describe real interview questions, map each question to an LC number, check every one against README and the practice log, and write the result as a 繁體中文 summary doc under doc/ws/. Use when asked what a company has been asking lately, to scan LC discuss for interview experiences, to turn recent posts into a drill list, or to summarise discussion threads into a doc. Triggers - "/lc-discussion google", "/lc-discussion meta e4 --days 30", "scan LC discuss for recent Google L3 questions", "what is Amazon asking lately?", "summarise the latest interview posts into a doc".
lc-faq-add
File an interview question and answer into doc/faq/ in the shape the other 49 FAQs use — the sheet its Scope line owns, the numbered section it belongs under, tagged code fences — and write the matching 繁體中文 overlay section in the same pass, because that tree is 100% translated and a new English answer leaves a hole the moment it lands. Use when asked to add an FAQ entry, document an interview question, answer a backend/Java/SQL/Kafka question into the notes, or start a new FAQ file. Triggers - "add a question about virtual threads to the java FAQ", "/lc-faq-add kafka rebalancing", "document this interview question", "start a FAQ for gRPC".
lc-java
File a LeetCode **Java** solution into this repo the way the existing ones are filed — put it in the package its pattern owns, write the file-level javadoc header (`<number>. <Title>` then difficulty then the statement), mark the solution blocks `// V0` / `// V0-1` / `// V1-1` so the markers match the method names, add the `time =` / `space =` javadoc, compile and run it, write every block as the standard, readable approach with explanatory comments and no clever syntactic sugar, file each other good approach as `// V1`, `// V2`, …, then add the `[Java]` link to the README row the problem already has. Use when asked to "add LC <number> in Java", to file a draft out of `ws/Workspace26.java`, to port an existing Python solution to Java, or to close part of the Java coverage gap. Triggers - "add LC 25 to LinkedList in java", "/lc-java 239 SlideWindow", "file my workspace draft", "port LC 207 to java".
lc-log
Append today's practice session to data/progress.txt — the daily log that is the only source for the review plan. Writes the day's line in the log's own shape (the YYYYMMDD date, the bucket labels, the `|` session separators), carries forward the buckets still open from yesterday, and gets the annotations right, because `again` / `again!!!` / `ok` / `ok*` / `todo` are what the whole spaced-repetition schedule keys on. Use when asked to log practice, record what was solved today, update the progress file, or mark a problem as done or still shaky. Triggers - "log today's practice", "/lc-log 23 ok, 24 again!!", "record that I did 141 and 142 clean", "update progress".
lc-python
File a LeetCode **Python** solution into this repo the way the existing ones are filed — find the problem's real slug, write the Python file in the house layout (problem docstring, V0 with an IDEA block and a time/space line; the standard, readable approach with explanatory comments and no clever syntactic sugar; every other good approach filed as V1, V2, …), smoke-test it against the examples, and insert the README row. Use when asked to "add LC <number>" in Python, to file a problem just solved in a weekly contest, to turn a pasted draft into a committed solution, or to wire an existing solution file into README. For the Java counterpart use lc-java instead. Triggers - "add LC 4038 to Hash_table", "/lc-python 239 slide_window", "add this python solution and update the README", "file yesterday's contest Q1".
lc-site-data
Add a topic to the Study Roadmap (data/roadmap.json) or a question to the Complexity Quiz (data/complexity_quiz.json), satisfying the build-time validators in one pass — a row strictly below every prereq, no cycle and no edge the graph already implies, sheet slugs and LC numbers that exist, no duplicate quiz id, accept always an array, and every answer parseable by site/complexity.js's single-letter identifiers. Use when asked to add a roadmap topic, wire a topic's prerequisites, add a complexity question or drill, or fix a build that a roadmap or quiz entry failed. Triggers - "add monotonic stack to the roadmap", "/lc-site-data quiz for LC 239", "add a complexity question", "the roadmap build is failing".
lc-zh-translate
Translate cheatsheet or FAQ sections into 繁體中文 as a sparse overlay under i18n/zh/, using script/zh.js's sync → todo → write → sync → status loop. Keeps every <!--CODE--> marker in order, takes structure and heading order from the English document, leaves link targets and API names in English, and adapts the entries a sync parked rather than starting them from nothing. Use when asked to translate a cheatsheet or FAQ, to work the translation backlog, to fill in the untranslated sections of a sheet, or to refresh the progress docs. Triggers - "translate dp_loop_order", "/lc-zh-translate heap", "work the zh backlog", "what is still untranslated?", "refresh the translation progress".
markdown-doc-writer
Technical documentation writer specializing in creating clear, well-structured markdown documents for algorithms, system design, interview preparation, and code documentation. Use when writing README files, algorithm explanations, system design docs, or technical guides.
system-architecture
System design and architecture expert for creating scalable distributed systems. Covers system design interviews, architecture patterns, and real-world case studies like Netflix, Twitter, Uber. Use when designing systems, writing architecture docs, or preparing for system design interviews.
nuxt-agent-ready-best-practices
Nuxt agent-readiness guidelines for making a site operable by autonomous AI agents — not just cited by them. Covers the isitagentready.com standards: Markdown content negotiation, RFC 8288 Link headers, RFC 9727 API catalogs, Agent Skills discovery indexes, WebMCP browser tools, MCP Server Cards, OAuth/OIDC agent auth discovery, and DNS-AID. Triggers on tasks involving agent-ready, isitagentready, MCP, WebMCP, model context protocol, agent skills, API catalog, well-known discovery, agent auth, DNS-AID, A2A, or agentic commerce.
nuxt-best-practices
Nuxt 4 performance optimization and architecture guidelines (current through Nuxt 4.5) for building fast, maintainable full-stack applications. This skill should be used when writing, reviewing, or refactoring Nuxt code to ensure optimal patterns. Triggers on tasks involving data fetching, server routes, auto-imports, rendering modes, layouts, named views, or Nuxt-specific features.
nuxt-geo-best-practices
Nuxt GEO (Generative Engine Optimization) guidelines for getting cited by ChatGPT, Perplexity, Claude, Google AI Overviews, and Gemini. Covers AI crawler access (llms.txt, GPTBot/ClaudeBot/PerplexityBot allowlisting), content extractability for RAG retrieval, entity clarity via JSON-LD, and the evidence-backed +40% visibility levers (statistics, citations, quotations) from the GEO arxiv paper. Triggers on tasks involving GEO, AEO, AI search, LLM visibility, llms.txt, AI crawlers, ChatGPT citations, Perplexity, AI Overviews, generative engines, or AI mentions.
nuxt-seo-best-practices
Nuxt SEO optimization guidelines for Cloudflare-deployed applications. Covers dynamic OG image generation on CF Workers, page SEO composables, JSON-LD structured data, SSR externals, and Nitro configuration. Triggers on tasks involving SEO, meta tags, OG images, Open Graph, Satori, social sharing, or Cloudflare Workers deployment.
vue-best-practices
Vue.js performance optimization guidelines for building fast, maintainable applications. This skill should be used when writing, reviewing, or refactoring Vue.js code to ensure optimal performance patterns. Triggers on tasks involving Vue components, reactivity, Composition API, state management, or performance improvements.
remove-ai-comments
Removes redundant, obvious, or "AI-flavored" comments from code to improve signal-to-noise ratio. Use when the user asks to "clean up comments", "remove AI comments", or makes a general request to refactor verbose code documentation.
ray
Teaches how to interact with the Ray application. This skill should be used when users want to interact with Ray through a coding agent or LLM with skills capabilities.
evolvable-software
>-
prompt-guard
600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.
react-useeffect
React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
rigorous-coding
Apply rigorous coding standards. Use when writing, implementing, or reviewing code.
planning-with-files
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
moai
>
design-lab
Conduct design interviews, generate five distinct UI variations in a temporary design lab, collect feedback, and produce implementation plans. Use when the user wants to explore UI design options, redesign existing components, or create new UI with multiple approaches to compare.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
plan-mode
完整复刻 Claude Code Plan Mode 架构。增强版：强制代码落地 + 显式暂停询问机制。
java-dev
Comprehensive Java development skill based on Alibaba Java Coding Guidelines (Songshan Edition). Use when writing, reviewing, or refactoring Java code to ensure compliance with industry best practices. Triggers on: (1) Writing new Java code (.java files), (2) Reviewing existing Java code, (3) Refactoring Java projects, (4) Database design with MySQL, (5) API design and implementation, (6) Unit testing, (7) Concurrent programming, (8) Security implementation, or any Java development tasks requiring adherence to coding standards.
Page 574 of 1646 · 82255 results