review-training-data-quality
Audits a candidate or labeled training corpus for distribution collapse, ambiguity, context sufficiency, hard-negative quality, abstention behavior, leakage, and stable label defensibility. Use before scaling teacher calls or starting fine-tuning.
review-ios-ui-apple-hig
Review iOS app UI against Apple Human Interface Guidelines and iOS platform conventions. Use when asked for an Apple HIG-based iOS UI, UX, SwiftUI, UIKit, screenshot, simulator, accessibility, Dynamic Type, navigation, layout, controls, color, typography, or platform-conventions review, especially when the user wants critique or prioritized findings grounded in Apple's interface guidance instead of project-specific design docs.
proxmox-admin
Administers Proxmox VE hosts, creates and manages VMs with qm, manages LXC containers with pct, configures storage, networking, clusters, and automates provisioning tasks via the Proxmox CLI.
prepare-training-corpus
Builds and freezes deterministic train, validation, and test corpora with provenance, group-safe splits, manifests, hashes, and prompt-leakage checks. Use before teacher labeling, fine-tuning, or comparing models on generated or retrieved examples.
package-private-ml-artifacts
Inventories, hashes, scans, and verifies datasets, adapters, checkpoints, logs, and evaluation evidence before an explicitly approved private upload. Use when ephemeral jobs or handoffs require durable ML artifacts without exposing credentials or unapproved data.
orbstack-cli
>-
mikrotik-routeros
Configures and automates MikroTik RouterOS routers through the terminal, command line interface, .rsc imports, /system script repository, Scheduler, Netwatch, firewall, NAT, DHCP, DNS, bridge, VLAN, routing, VPN, device-mode, backup/export, and RouterOS scripting. Use this skill whenever the user mentions MikroTik, Mikrotik, RouterOS, WinBox terminal, router CLI, router scripts, .rsc files, or configuring MikroTik services from the command line.
ios-design-review
>
gogopowermanager
Orchestrates and ships a milestone, release, issue set, or multi-workstream engineering goal through one manager and bounded parallel workers. Use when the user asks to manage a milestone, build a dependency graph, execute independent issues in parallel, coordinate threads, sessions, subagents, or worktrees, recover a stopped delivery, or invokes /gogopowermanager.
design-resumable-model-evaluation
Designs strict model benchmarks that persist per-case evidence, resume without repeating completed work, separate first-attempt behavior from remediation, and stop early only when failure is mathematically certain. Use for slow, costly, or interruptible evaluations.
compare-models-blindly
Creates seeded blinded model-comparison packets and evaluates candidate outputs twice with reversed order to control identity and presentation bias. Use when two models or prompts produce different valid answers that require qualitative judging.
close-out-ml-experiment
Preserves positive or negative ML experiment evidence, reconciles report discrepancies, records the canonical decision and limitations, and prepares a concise handoff. Use when stopping an experiment, rejecting a prompt/model, or freezing a result before the next iteration.
awk
>
apple-cktool
Operates Apple's Xcode-bundled `cktool` command-line utility for CloudKit development automation on macOS. Use when Codex needs to run, script, explain, or troubleshoot `xcrun cktool`; manage `.ckdb` schemas with export, validate, import, or reset; discover CloudKit teams; create, query, or delete test records; configure management or user tokens in Keychain or CI; or prepare CloudKit-backed integration tests. For equivalent typed JavaScript or TypeScript automation, use `apple-cktool-js` with this skill.
apple-cktool-js
Builds and troubleshoots CloudKit automation with Apple's CKTool JS packages, including `@apple/cktool.database`, `@apple/cktool.target.nodejs`, and `@apple/cktool.target.browser`. Use when Codex needs typed JavaScript or TypeScript for CloudKit schema import, export, validation, or reset; container and team discovery; record queries, creation, updates, or deletion; Node.js or browser configuration; Promise-based API calls; CI integration; token injection; or migration from `xcrun cktool` shell scripts. Use `apple-cktool` alongside this skill for the Xcode-bundled macOS CLI.
a2ui
Generate A2UI 0.8 protocol compliant UI code. Use when building agent-driven interfaces, generating JSONL messages for surfaceUpdate/dataModelUpdate/beginRendering, creating forms, lists, cards, or any UI components that render across web/mobile/desktop platforms.
tempo
Builds applications on Tempo network using TypeScript SDK, Rust node, and Foundry. Use when working with Tempo transactions, TIP-20 tokens, stablecoins, or Tempo protocol integration.
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.
frontend-testing
Write tests that start with acceptance criteria, then add implementation tests for robustness. Use when writing unit tests (Vitest), end-to-end tests (Playwright), visual regression tests, or accessibility tests. Emphasizes user-centric testing, semantic locators, accessibility validation, and the balance between acceptance and implementation testing.
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.
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.
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.
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。
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。
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）。
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。
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。
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。
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。
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.
read-memories
>
read-file
>
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.
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.
IMSA Analyst
use to query historical data on the IMSA Weathertech seasons
query
>
install-duckdb
>
attach-db
>
Teradata ONNX Model Scoring
Score data using ONNX models (Bring Your Own Model)
Teradata Univariate Statistics
Comprehensive descriptive statistics for data exploration
td-train-test-split
Data splitting for model validation using TD_TrainTestSplit
td-tfidf
Term Frequency-Inverse Document Frequency for text analysis
td-svm
Support Vector Machine for linear and non-linear classification
td-stationarity-test
Statistical tests for time series stationarity (ADF, KPSS, PP tests)
Page 1165 of 1711 · 85506 results
