break
When the user shows signs of fatigue or burnout during coding — including increased typos, garbled text, frustrated or irritable tone, repetitive mistakes, confusion about simple concepts, or signs of rushing. Also use when the user explicitly mentions needing a break, feeling tired, or asks about rest. This skill provides gentle, non-intrusive health check-ins.
microsoft-teams-send-as-workflow
Send messages and Adaptive Cards to Microsoft Teams via Incoming Webhook. Use when user requests to send notifications, alerts, or formatted cards to Teams channels. Triggers include requests to post to Teams, Teams webhook, Teams notification, Teams card, or any request to send messages to Microsoft Teams channels.
i18n-completeness
Comprehensive i18n consistency check with dynamic pattern detection and hardcoded string analysis. Use when working with translations, localization, i18n keys, or when the user mentions translation issues, missing keys, or language support. Auto-triggers on phrases like "check translations", "i18n consistency", "localization issues", or "translation keys".
typescript-strict
Enforce TypeScript strict mode practices and type safety in Tetris codebase. Use when writing game logic, handling errors, improving type safety, or fixing type errors. Auto-triggers on phrases like "fix type errors", "improve type safety", "handle this error", or "make this type-safe". Focuses on Result<T,E> pattern, proper type guards, and avoiding type assertions.
tdd-workflow
Test-driven development guidance for Tetris game logic. Use when writing tests, fixing test failures, improving test coverage, or implementing game mechanics. Auto-triggers on phrases like "write a test", "test this function", "improve coverage", "fix failing tests", or "add game logic". Emphasizes Result<T,E> pattern and property-based testing with fast-check.
react-component-design
Design React components following Tetris architecture guidelines. Use when creating new components, refactoring components, optimizing performance, or improving component structure. Auto-triggers on phrases like "create a component", "refactor this component", "optimize rendering", or "improve component design". Emphasizes component consolidation, unified patterns, and efficient hook usage.
architecture-compliance
Verify Tetris architecture compliance with coding rules and design patterns. Use when reviewing code, implementing features, refactoring, or validating architectural decisions. Auto-triggers on phrases like "review this code", "check architecture", "is this correct?", "refactor this", or "implement feature". Checks for prohibited patterns (classes, enums, any types, hardcoded strings) and required patterns (functional programming, Result type, proper imports).
build-pipeline
Execute complete build pipeline with dead code detection, formatting, linting, type checking, testing, and production build. Use when the user mentions building, running the full pipeline, checking code quality, or preparing for deployment. Auto-triggers on phrases like "build the project", "run all checks", "prepare for production", or "validate code quality".
codex
OpenAI Codex CLIを使用したコードレビュー、分析、コードベースへの質問を実行する。使用場面: (1) コードレビュー依頼時、(2) コードベース全体の分析、(3) 実装に関する質問、(4) バグの調査、(5) リファクタリング提案、(6) 解消が難しい問題の調査。トリガー: "codex", "コードレビュー", "レビューして", "分析して", "/codex"
instrumenting-with-mlflow-tracing
Instruments code with MLflow Tracing for observability. Triggers on questions about adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, or tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen). Examples - "How do I add tracing?", "How to instrument my agent?", "How to trace my LangChain app?", "Getting started with MLflow tracing"
agent-evaluation
Use this when you need to IMPROVE or OPTIMIZE an existing LLM agent's performance - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
querying-mlflow-metrics
Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics.
searching-mlflow-docs
Searches and retrieves MLflow documentation from the official docs site. Use when the user asks about MLflow features, APIs, integrations (LangGraph, LangChain, OpenAI, etc.), tracing, tracking, or requests to look up MLflow documentation. Triggers on "how do I use MLflow with X", "find MLflow docs for Y", "MLflow API for Z".
searching-mlflow-traces
Searches and filters MLflow traces using CLI or Python API. Use when the user asks to find traces, filter traces by status/tags/metadata/execution time, query traces, or debug failed traces. Triggers on "search traces", "find failed traces", "filter traces by", "traces slower than", "query MLflow traces".
swiftui-localize
SwiftUI / iOS / macOS 项目本地化专家 Skill，支持 scan（只读扫描）、apply（执行修改）与 lint（CI 检查）三种模式，并支持中英文输出切换。
k8s-autoscaling
KEDA event-driven autoscaling for Kubernetes. Use when installing KEDA, configuring scalers (Prometheus, RabbitMQ, Kafka, etc.), setting up HPA, or implementing autoscaling best practices.
platform-orchestrator
Orchestrates all skills for unified platform deployment. All services enabled by default. Run from bastion server.
hetzner-infra
Hetzner cloud infrastructure provisioning for Kubernetes. Use when provisioning servers, networks, load balancers, firewalls, DNS zones, or storage on Hetzner Cloud via hcloud CLI.
k8s-gitops
ArgoCD GitOps continuous delivery for Kubernetes. Use when installing ArgoCD, configuring ApplicationSets, setting up GitLab CI integration, or managing GitOps repository structure.
k8s-databases
PostgreSQL and MongoDB on Kubernetes via Percona Operators. Use when deploying databases, configuring HA clusters, setting up backups, monitoring, or performing database operations.
k8s-cluster-management
Kubernetes cluster installation via Kubespray. Always use Kubespray for cluster provisioning. Includes core addons (Cilium, Gateway API, cert-manager, LoadBalancer). Multi-cloud support.
network-security
VPN access and firewall rules. Headscale VPN on bastion for admin access to private services.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
minio-storage
MinIO S3-compatible object storage on Kubernetes. Use when deploying MinIO, configuring buckets, setting up integrations with GitLab/Loki/backups, or managing S3-compatible storage infrastructure.
brocoders-boilerplate-setup
Full-stack setup with Brocoders NestJS backend and Extensive React frontend boilerplates.
gitlab-selfhosted
GitLab CE self-hosted deployment on Kubernetes. Use when installing, configuring, upgrading, or managing GitLab instances including runners, container registry, backups, and external database integration.
crypto-data
Free crypto market data APIs for trading agents. Provides Fear & Greed Index, trending coins, market data, and coin prices using CoinGecko (free tier) and Alternative.me APIs. No API key required for basic usage.
k8s-secrets
Vault + External Secrets Operator for secrets management.
k8s-observability
VictoriaMetrics + Loki + Grafana. Light or full mode.
trader-agent-v4.1
Advanced autonomous AI trading agent for Hyperliquid perpetual futures. Features multi-indicator confirmation (RSI/MACD/BB/StochRSI/ADX/Ichimoku/Supertrend), sentiment analysis, on-chain metrics, 4 unified trading modes (Directional, Mean-Reversion, Passive, Arbitrage), regime detection, session timing, Kelly Criterion sizing, correlation-based heat, execution algorithms (TWAP/VWAP), manipulation detection, and order flow analysis. Use when user wants to trade crypto with sophisticated analysis.
trader-agent-v2
Autonomous AI trading agent for Hyperliquid perpetual futures exchange. Use when user wants to trade crypto, set up trading automation, monitor positions, analyze markets, or manage a Hyperliquid account. Trigger on any trading-related message like "I want to trade", "What's my balance?", "Start trading", "Close positions", etc.
trading-agent
Autonomous AI trading agent for Hyperliquid perpetual futures exchange. Use when user wants to trade crypto, set up trading automation, monitor positions, analyze markets, or manage a Hyperliquid account. Trigger on any trading-related message like "I want to trade", "What's my balance?", "Start trading", "Close positions", etc.
trader-agent-v3
Autonomous AI trading agent for Hyperliquid perpetual futures exchange. Use when user wants to trade crypto, set up trading automation, monitor positions, analyze markets, or manage a Hyperliquid account. Trigger on any trading-related message like "I want to trade", "What's my balance?", "Start trading", "Close positions", etc.
aeo-core
Main AEO skill - calculates confidence scores and decides execution path. Auto-loads on /aeo command.
aeo-architecture
Analyze and protect code architecture. Detects circular dependencies and layer violations.
aeo-qa-agent
Internal code reviewer with veto power. Reviews changes before commit, blocks security issues.
aeo-failure-patterns
Recognize common errors and apply known fixes automatically. Hybrid: core patterns + project-specific learning.
aeo-spec-validator
Validate that tasks are sufficiently defined before execution. Returns score 0-100.
aeo-cost-governor
Track token usage and enforce budget limits. Optional skill for cost-conscious projects.
aeo-escalation
Human-AI interface for when to interrupt and involve humans. Presents clear options and records decisions.
llm-tldr
Summarize and navigate this repo with the llm-tldr CLI (tree/structure/context/semantic search). Use when you need LLM-ready summaries of files or symbols, fast codebase orientation, or behavior-based search before editing.
skill-acquisition
Create, document, or revise Codex skills, including deciding when to add scripts/references/assets, structuring SKILL.md content, enforcing the 500-line rule, and updating repo references (AGENTS.md, kanban evidence).
transcript-reflow
Clean and reorganize transcript .txt files for clearer English grammar, punctuation, and paragraph flow. Use when asked to fix line breaks, merge fragments into sentences, normalize punctuation, or produce a reflowed transcript saved as a new file.
youtube-chapter-clipper
Generate chapter clips from YouTube videos with yt-dlp and ffmpeg. Use when asked to download YouTube videos/subtitles, generate fine-grained chapters, cut precise clips, or generate per-chapter English SRTs.
semantic-video-clipper
AI analyzes subtitles to identify optimal split points, then clips video segments using FFmpeg based on AI-provided cue indices. Use when asked to segment videos (e.g., .mp4) based on .vtt/.srt subtitles.
en-zh-bilingual-json
Convert English .txt articles into a JSON array of sentence-level English/Chinese (zh) pairs. Translate English into Chinese and generating bilingual {en, zh} entries via the model (no external translation API), then saving to a JSON file.
en-to-zh-translator
Translate English text files (.txt, .md) to Chinese for language learning and translation practice. Use when the user asks to translate a text file to Chinese, create a Chinese version of an English document, or generate bilingual materials for translation training. The translation preserves sentence structure and combines broken sentences into complete lines.
react-query-best-practices
React Query v4 (TanStack Query) best practices, patterns, and troubleshooting. Use when working with useQuery, useMutation, query invalidation, caching, WebSocket integration, or any async state management in React. Based on TkDodo's comprehensive blog series.
feature-workflow
Feature planning, specification, phased implementation, progress tracking, per-phase PRs, and archival workflow. Use when starting a new feature, creating spec documents, breaking work into phases, tracking progress, managing PRs, or archiving completed specs.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Page 1606 of 1696 · 84767 results
