Build falling leaves that read as leaves, with each one tumbling on its own axis so it presents a face, thins to an edge, and opens out again, and with its sideways slip driven by that same tumble. Covers the 2-D canvas build and the instanced-3-D variant, where leaves are recycled from, density-versus-count maths, depth layering, colour under a tone-mapped composite, reduced motion, and visibility pausing. Use for autumn maple, sakura petals, blossom, ash, snowfall shapes, or any drifting foliage where a generic particle field reads as confetti.

Create, integrate, or audit production-ready rigged 3D characters and monsters with a main model, skeleton, animation library, sockets, collision contracts, separate character equipment, optimized runtime files, catalog media, and an interactive moveset inspector. Use when generating or importing FBX/GLB game actors; defining character-versus-monster asset requirements; separating swords, shields, helmets, armor, or stowed gear; adding idle, walk, run, attack, hit, dodge, block, cast, or death clips; wiring an asset into gameplay; or adding action and equipment controls plus deterministic tests to a game asset catalog.

Package a finished local project into an intentional GitHub repository, create a strong README and visual preview, push it safely, configure a public GitHub Pages URL when the project is compatible, and verify the deployed result. Use when a user asks to upload, publish, open-source, share, or turn a local HTML/CSS/JavaScript experiment or small web project into a documented GitHub repository with a live demo.

Diagnose and fix problems in an AG-UI .NET app built on the AG-UI SDK — when streaming chat, tools, state, interrupts, or the transport misbehave. USE FOR: the agent forgetting earlier turns / history truncated; update.ConversationId always null; state or lifecycle updates that never arrive; a tool throwing at runtime or producing AOT/trim warnings; an unknown-tool error mid-run; 406 Not Acceptable from the endpoint; an interrupt or approval that won't resume; and inspecting the raw AG-UI event stream (curl SSE frames, RawEvent on ChatResponseUpdate.RawRepresentation) to see what's actually on the wire. DO NOT USE FOR: first-time setup or the happy path (use agui-dotnet-streaming-chat); implementing a specific feature cleanly (use the matching agui-dotnet-* skill).

Expose client-side (frontend) tools to an AG-UI agent with the AG-UI .NET SDK — C# functions that run in the CLIENT app (read local state, GPS, UI, device APIs), where the client executes the call and returns the result so the run continues. USE FOR: declaring an AIFunction in the client and passing it via ChatOptions.Tools to AGUIChatClient; having the client execute a tool the model requested and feed the result back automatically; understanding why no UseFunctionInvocation is needed on the client (AGUIChatClient already invokes functions); what the server must do (UseFunctionInvocation + TerminateOnUnknownCalls) so it forwards an unknown/client tool instead of erroring. DO NOT USE FOR: tools that run on the server/backend (use agui-dotnet-server-tools); pausing for human approval/input before acting (interrupts / human-in-the-loop); plain chat (use agui-dotnet-streaming-chat); shared state, generative UI, multimodal, or protobuf.

Use when the user wants to extract project vision, decisions, and preferences from his head into clear documentation (README + ADRs) through a back-and-forth Q&A loop. Triggers on "brain-to-docs", "build out the docs", "extract the vision", "let's document this project".

Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.

Watch a PR's CI, diagnose every failing check, fix what's actually broken, resolve CodeRabbit's major findings, and keep iterating until the PR is green. Use when the user says "handhold the PR", "check CI", "get CI green", "resolve any issues until green", or asks why a PR's checks are failing.

Deploy static pages to nexu.space. Use when user says deploy, publish, ship, or go live with a static site/page. Uploads files from workspace to <project-slug>.nexu.space via Wrangler + Cloudflare Pages. Supports first deploy and redeploy.

Analyze all vault tags: find unused, orphan, near-duplicate, over-used, and under-used tags. Suggest merges and cleanup actions. Triggers: EN: "tag garden", "clean up tags", "tag cleanup", "tag audit". IT: "tag garden", "pulizia tag", "revisione tag". FR: "jardinage des tags", "nettoyer les tags". ES: "jardín de tags", "limpiar tags". DE: "Tag-Garten", "Tags aufräumen". PT: "jardim de tags", "limpar tags".

Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the cheapest model capable of the task.

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

Trigger when the user asks for an architecture diagram, says "draw the system", "update the architecture diagram", "give me an excalidraw of this codebase", or "/excalidraw-architecture". Generates or updates an Excalidraw JSON file at docs/architecture.excalidraw by reading the codebase's key entry points.

Use this skill when the user asks about a specific topic, subject area, or wants to explore curated topic pages on BestBlogs. Triggers include "BestBlogs 有什么主题 / 查一下 AI 编程主题 / 给我看 Claude 主题页 / 大模型相关主题", "BestBlogs topic list", "show me topics about AI", "what topics does BestBlogs have", "topic details for vibe-coding", "browse topic pages". Invokes the `bestblogs` CLI.

Use this skill when the user wants to deep-read a specific BestBlogs resource (article / podcast / video / tweet) — fetch its metadata + markdown so a local LLM or reader can consume it, and automatically report the read behavior back to BestBlogs. Triggers include "深度阅读这篇 / 拉这篇内容的 markdown / bestblogs read / 给我看看 RAW_xxx 的正文", "deep read this BestBlogs article", "pull markdown for resource RAW_...". Invokes the `bestblogs` CLI.

Use this skill when the user wants to understand the "why" behind BestBlogs recommendations — view their interest profile summary, see which followed sources are driving their daily brief, or inspect the score breakdown of a specific resource. Triggers include "BestBlogs 为什么推这条 / 看我的画像 / 我关注的源哪些最有价值 / 这篇文章评分多少", "why did BestBlogs recommend this", "which of my followed sources contribute most", "show score for this resource". Invokes the `bestblogs` CLI.

Use this skill when the user wants to find today's most worth-reading content from BestBlogs, browse personalized feeds, check trending items, search specific topics, or explore curated newsletters. Triggers include "今天有什么值得读的 / BestBlogs 推荐 / 本周 BestBlogs 热趋 / 搜一下 AI coding / 看关注源的最新 / 最近有什么好周刊", "what's worth reading today", "bestblogs trending this week", "bestblogs discover", "search BestBlogs". Invokes the `bestblogs` CLI.

Maintain CodexMonitor and Codex app-server protocol parity. Use when asked to audit supported or missing app-server notifications/requests, trace event routing, diagnose schema drift in app-server payloads, or update docs/app-server-events.md after upstream Codex changes.

Collaborative document authoring workflow for proposals, technical specs, decision docs, README sections, ADRs, and long-form prose that must work for fresh readers. Use when asked to "write the docs", "draft a proposal", "write a spec", "write an RFC", "write the README", or when a document needs to be understandable by someone without this session's context. Three stages: gather context, iterate on structure, reader-test for a stranger.