Skills directory

This skill should be used when the user asks to "animate a headline", "make a kinetic typography video", "do a split-text reveal", "stagger text by character/word/line", "make a lyric or caption video", "animate a variable font weight", "pu

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are

Guide for diagnosing and improving MSBuild project evaluation performance. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, b

Select and design a navigation pattern — tabs, drawer, hierarchy, or hub — matched to product structure and user tasks. Use when choosing how users move between sections. For the underlying content structure, use `information-architecture`

Build classroom-ready lesson plans with standards-aligned arcs, student-facing materials, and observation look-fors from teacher notes or topic prompts. Use when the user asks for a lesson plan, daily plan, mini-lesson, unit slice, or says

Route event-driven onchain automation that detects activity, applies logic, and submits a transaction in response. Use for 'when X happens onchain, do Y', monitor-and-execute workflows, smart contract calls triggered by events, keepers, pro

Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data. Use when the user asks to convert a DAFT dataset, change DAFT format, change a TAO dataset format, or run `tao-daft convert`

Use this when reviewing AEM Edge Delivery Services (EDS, Franklin, Helix) code, either self-review at the end of development before opening a PR, or reviewing an existing pull request. Validates block structure, CSS and JS patterns, DOM out

Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVi

Diagnose an existing Goldsky Compose app with failing tasks, crashloops, missed events, cron not firing, HTTP 500s, wallet or gas sponsorship failures, missing secrets, bundler errors, manifest validation failures, or esbuild failures. Use

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Sk

Dynamic, vibrant style with thick borders, geometric shapes, high-contrast colors, and expressive typography conveying motion and vitality.

Generate publication-quality LaTeX tables from experimental results. Convert JSON/CSV data to booktabs-styled tables with bold best results, multi-row layouts, and proper captions. Use when creating result tables, comparison tables, or abla

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

Load and reuse 3D assets in React Three Fiber with useGLTF, useLoader, Suspense, and preloading. Use for model loading, decoder setup, caching, cloning, or loading/error UI.

Add Rapier rigid bodies, colliders, forces, sensors, and joints to React Three Fiber. Use for collision-driven movement and simulation; use animation guidance for purely visual motion.

PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inf

guidelines for creating, reviewing, updating, and searching ADK documentation - use when users ask about writing, maintaining, or auditing ADK bot docs

Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.

Activate this skill when BenchmarkDotNet (BDN) is involved in the task — creating, running, configuring, or reviewing BDN benchmarks. Also activate when microbenchmarking .NET code would be useful and BenchmarkDotNet is the likely tool. Con

When the user wants to track follower growth, understand what drives new followers, or analyze audience development. Also use when the user mentions 'follower growth,' 'followers,' 'audience growth,' 'gaining followers,' 'losing followers,'

Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable

Best practices for Android Intent security. Use this skill when auditing component configurations in AndroidManifest.xml activities, services, receivers) or source code handling incoming Intents (getIntent, getParcelableExtra) to prevent In

Apple-inspired premium aesthetic with precise spacing, modern typography, and a refined, polished visual language.

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a

中国国家统计局公开数据查询技能，当用户想查询经济、CPI、GDP、人口、房价指数等数据时触发。

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotatio

Analyzes Axiom query patterns to find unused data, then builds dashboards and monitors for cost optimization. Use when asked to reduce Axiom costs, find unused columns or field values, identify data waste, or track ingest spend.

Send messages and interactive cards to Feishu (飞书) and Lark channels via webhooks or Bot API. Create rich-text announcements, marketing updates, and team notifications. Trigger phrases: "post to feishu", "feishu message", "lark message", "f

Microsoft Sharepoint integration. Manage Sites. Use when the user wants to interact with Microsoft Sharepoint data.

Enable nullable reference types in a C# project and systematically resolve all warnings. USE FOR: adopting NRTs in existing codebases, file-by-file or project-wide migration, fixing CS8602/CS8618/CS86xx warnings, annotating APIs for nullabi

Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), several agents or chats work

Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following reposito

ALWAYS USE when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for "review" when corrected code or edits are wanted, even for one pasted ass

Use this when you need more information about an AEM Edge Delivery Services (EDS, Franklin, Helix) feature or guidance on how to implement one, and your existing web-search tools are not turning up relevant results. Searches the aem.live do

Triage and manage Coralogix Cases with the `cx cases` CLI — e.g. acknowledge, assign, resolve, or re-prioritize a case, or inspect its event timeline or notification deliveries.

Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture explainer of how something works.

Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the us

Graceful, refined aesthetic with delicate typography, minimal palettes, and polished layouts that exude sophistication.

Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construct

Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training. Use when running on EKS / GKE / AKS / on-prem clusters with the NV

Multi-platform Chinese & multilingual TTS text-to-speech via Edge/Doubao/CosyVoice/Qwen3/StepFun/GLM-TTS/Azure/Tencent/Baidu/MiniMax/Xunfei plus ElevenLabs/OpenAI/Google/Atlas Cloud — 15 backends, word-level timestamps, [PAUSE:x] pause mark

Use this when implementing code changes in AEM Edge Delivery Services (EDS, Franklin, Helix), whether new or modified blocks, core functionality (scripts.js, styles, delayed.js, etc.), or both. Creates and modifies block folders and decorat

搜索微信公众号文章技能。通过微信搜索获取文章列表，覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯；可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。

Activation requires either supplied .NET coverage reports/percentages/line, branch, or condition metrics, or an explicit request to collect .NET coverage for analysis. USE FOR: interpreting that evidence, including Cobertura data, partial c

Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, prod

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating,