semantic-html
Write well-considered semantic HTML that serves all users. Use when creating components, page structures, or reviewing markup. Emphasizes native HTML elements over ARIA. Treats proper document structure and accessibility as foundations rather than afterthoughts.
component-usage-analysis
Analyse component dependencies and usage patterns in a Drupal/Twig component library. Use when user asks to find where a component is used, check if a component can be safely removed, audit component dependencies, find components using specific properties, or analyse impact of refactoring a component.
css-coder
CSS authoring guidance emphasizing web standards, accessibility, and performance. Use when writing, reviewing, or refactoring CSS. Provides patterns, snippets, and conventions that prioritize native CSS over frameworks, semantic structure, and maintainable code. Refer to references/patterns.md for specific patterns and snippets.
css-tokens
Provides foundational CSS design tokens (custom properties) for typography, spacing, colors, borders, z-index, and transitions. Use when setting up a base token system for a web project.
frontend-security
Audit frontend codebases for security vulnerabilities and bad practices. Use when performing security reviews, auditing code for XSS/CSRF/DOM vulnerabilities, checking Content Security Policy configurations, validating input handling, reviewing file upload security, or examining Node.js/NPM dependencies. Target frameworks include web platform (vanilla HTML/CSS/JS), React, Astro, Twig templates, Node.js, and Bun. Based on OWASP security guidelines.
component-scaffolding
Generate Drupal/Twig component skeletons with web components and Miyagi validation. Use when user requests to create, scaffold, or add a new component at a specific path (e.g., "add component skeleton at patterns/share-button"), or when creating component files including Twig templates, CSS, JavaScript web components, JSON schemas, or mock data files.
rag-service
高性能 RAG 多路检索服务。集成 Milvus 向量数据库进行语义检索，并结合 Rerank 模型进行精准重排序，支持海量文档的高效存储与历史内容召回。
ocr-service
高精度光学字符识别（OCR）服务。支持多语言、多格式图像的文字检测与提取，并提供文本区域坐标与置信度评分，适用于文档数字化与图像内容分析。
deepsearch-service
基于 LLM 的深度迭代搜索与推理服务。擅长处理复杂问题，通过自动分解查询、多轮迭代检索、信息评估与验证，最终生成全面且结构化的深度分析报告。
embedding-service
文本向量化（Embedding）基础服务。将自然语言转换为高维稠密向量，为语义搜索、聚类分析、推荐系统等下游任务提供核心数据支持。
rerank-service
文档重排序服务（Reranker）。基于深度学习模型对检索候选结果进行细粒度相关性打分与重新排序，显著提升检索结果的精准度（Top-K 准确率）。
sandbox-service
安全隔离的 Docker 沙盒代码执行服务。支持 Python/Shell/Bash 多语言动态执行，内置超时与资源限制。提供信任模式用于服务间代码融合调用。
search-guide
搜索工具调用决策指南。明确定义 Agent 何时应调用搜索工具（如实时信息、具体事实），何时应依赖内部知识。作为参考规范，优化 Agent 的工具使用策略。
websearch-service
基于 SearXNG 与 VLM 的实时联网搜索服务。专用于获取最新新闻、实时事件及特定事实。内置智能双层缓存（向量+数据库）与网页内容自动提取分析功能。
gadget-best-practices
Best practices for building Gadget apps. Use for Gadget-specific models, fields, actions, routes, access control, Shopify/BigCommerce integrations, frontend patterns, API client usage, internal API usage, webhooks, background jobs, testing, deployment, ggt CLI workflows, environment sync, logs, problems, and parallel agent development loops.
security-check
Security check skill. Triggers on "Could you please run a security check?", "セキュリティチェックをお願いします。", "请帮我做一次安全检查。". セキュリティチェックのデモスキル。「セキュリティチェックをお願いします。」「请帮我做一次安全检查。」などのリクエストで発動する。
repo-research
Routes research in external repositories — source code, issues, PRs, releases, git history — across GitHub, GitLab, and Bitbucket. Use when exploring how a library implements something, searching code across public repos, or checking issues, PRs, and release info. Do not use for local codebase search or library documentation lookups.
code-search
Routes local codebase search to the right tool — keyword, semantic, or symbol. Use when searching a codebase for identifiers, tracing features across files, answering conceptual questions about local code, or exploring unfamiliar projects. Do not use for external docs, GitHub repos, or package lookups.
imsa
Query the IMSA DuckDB dataset (output/imsa.duckdb). Includes schema guidance for seasons and laps plus formatting macros. Use for analytics, session lookups, and lap-level queries.
query
>
attach-db
>
install-duckdb
>
IMSA Analyst
use to query historical data on the IMSA Weathertech seasons
read-file
>
marimo
Create reactive Python notebooks for IMSA racing data analysis using marimo. Use for building interactive filtering UIs (seasons, classes, events), connecting to DuckDB databases, creating reactive visualizations, and performing data analysis with automatic cell re-execution. Includes templates, patterns, and IMSA-specific workflows.
read-memories
>
td-arima-forecast
ARIMA-based time series forecasting for trend and seasonal predictions
td-data-preparation
UAF-specific data preparation and validation for time series analysis
td-data-profiling
Comprehensive data profiling and quality assessment using Teradata ClearScape Analytics descriptive statistics functions
td-decision-forest
Decision forest ensemble classifier for robust predictions
td-decision-tree
Decision tree classifier for categorical prediction and rule extraction
td-detrend
Signal detrending for baseline correction and trend removal
td-dfft
Fourier transformation for frequency domain analysis
td-diff
Time series differencing for stationarity and trend removal
td-fft
Fast Fourier Transform for frequency domain analysis and spectral decomposition
Teradata F-Test
F-test for comparing variances between two groups
td-glm
Comprehensive Generalized Linear Model analytics for regression and classification
td-hierarchical-clustering
Hierarchical clustering for nested data grouping
Teradata HNSW Vector Search
Approximate nearest neighbor search using HNSW algorithm
td-ifft
Inverse Fast Fourier Transform for time domain reconstruction
td-kmeans
K-means clustering for customer segmentation and data grouping
Teradata K-Nearest Neighbors Analytics
K-Nearest Neighbors for classification and regression
td-linear-regression
Linear regression analysis for continuous target prediction
td-logistic-regression
Logistic regression for binary and multinomial classification
td-movavg-forecast
Moving average based forecasting for smoothed predictions
td-naive-bayes
Naive Bayes classifier for probabilistic classification
td-ngram-splitter
N-gram generation for text preprocessing
td-npath
Path analysis for sequential event patterns
td-onehot-encoding
Categorical variable encoding using TD_OneHotEncodingFit and Transform
Teradata XGBoost Analytics
XGBoost gradient boosting for classification and regression
Page 1173 of 1719 · 85905 results
