监控
日志、指标与可观测性
kgz — Execute Code on Kaggle Kernels (GPU & TPU)
mlnomadpy
Dep: websocket-client
git-comment
cuozg
Amend the last commit message to be clean and descriptive — use for 'amend commit', 'fix commit message', 'rewrite commit', 'change commit message'
error-handling
101mare
Patterns for exception handling across application layers: mapping, retry, severity, logging. Does NOT handle: exception hierarchies (use exception-builder), circuit breakers (use resilience-patterns), API errors (use api-design), logging config (use logging-builder). Use when designing error strategies, implementing retry logic, or mapping exceptions between layers. Recognizes: "error-handling", "exception handling", "retry pattern", "error strategy", "exception mapping", "error boundaries", "backoff pattern", "error propagation"
backend
mrsknetwork
Implements server-side application logic, data access layers, and background services using Python 3.12 and FastAPI. Use for building service classes, repositories, background tasks, middleware, or any Python code that runs on the server. Always ask about the existing stack before applying defaults.
ab-test-setup
ma1orek
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
error-detective
icartsh
TRACE 프레임워크(Trace, Read, Analyze, Check, Execute)를 사용한 체계적인 디버깅 및 에러 해결입니다. 에러 디버깅, 스택 트레이스(stack traces) 분석, 실패 조사, 근본 원인 분석(root cause analysis) 또는 운영 이슈 트러블슈팅 시 사용합니다.
webhooks-and-event-processing
SanctifiedOps
Design webhook/event pipelines for Solana activity with idempotency, dedupe, retries, and ordering. Use when consuming RPC/webhook feeds.
token-authority-and-risk
SanctifiedOps
Evaluate and configure SPL token authorities (mint/freeze/close) with risk implications and best practices. Use for audits, rotations, or disclosures.
logging-best-practices
trancong12102
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics
continuous-monitoring
pluginagentmarketplace
Real-time monitoring and detection of adversarial attacks and model drift in production
monitoring-and-alerting
SanctifiedOps
Monitoring plan for Solana apps: RPC health, tx success, program errors, and liquidity signals. Use to set up dashboards and alerts.
stakeholder-communication
pluginagentmarketplace
Stakeholder management, executive communication, and organizational alignment for product leaders.
zeberg-salomon-rotator
fatfingererr
用領先和同時指標建構景氣模型，並判讀兩種景氣階段：景氣擴張期 (Risk-On) 與景氣收縮期 (Risk-Off)，並根據理論給出 "撞冰山" 與 "下沉" 事件訊號。
libby-book-monitor
alexpolonsky
Track book availability on Libby/OverDrive libraries. Search library catalogues, manage a watchlist, and get notified when books are added. Use for "libby", "check libby", "libby watchlist", "is book on libby", "book available", "overdrive", "library catalogue", "ספרייה", "ספרים".
trading-bot-architecture
SanctifiedOps
Design and build Solana trading bots - execution engine, position management, risk controls, and operational infrastructure. Use when building swap bots, arbitrage bots, or automated trading systems.
spawn-worker
weegigs
Spawn headless Claude agents in isolated jj workspaces to work on beads tasks. Use when delegating tasks to parallel workers.
monitoring-skill
pluginagentmarketplace
Monitoring and observability with Prometheus, Grafana, ELK Stack, and distributed tracing.
pci-compliance
peixotorms
Use when building payment processing, handling credit card data, PAN, CVV, cardholder data environment (CDE), implementing checkout flows, tokenization, Stripe, Braintree, or any code that touches cardholder information — PCI DSS v4.0 coding patterns, SAQ selection, data classification, AES-256 encryption, TLS 1.2, audit log, data masking, Luhn validation, payment gateway integration, 3-D Secure, scope reduction, network segmentation
launch-alert-bot
SanctifiedOps
Build a bot that detects new Solana launches (mints/LPs) and sends safe alerts. Use for discovery and monitoring without shilling scams.
site-reliability-engineer
gaebalai
Production monitoring, observability, SLO/SLI management, and incident response. Trigger terms: monitoring, observability, SRE, site reliability, alerting, incident response, SLO, SLI, error budget, Prometheus, Grafana, Datadog, New Relic, ELK stack, logs, metrics, traces, on-call, production monitoring, health checks, uptime, availability, dashboards, post-mortem, incident management, runbook. Completes SDD Stage 8 (Monitoring) with comprehensive production observability: - SLI/SLO definitions and tracking - Monitoring stack setup (Prometheus, Grafana, ELK, Datadog, etc.) - Alert rules and notification channels - Incident response runbooks - Observability dashboards (logs, metrics, traces) - Post-mortem templates and analysis - Health check endpoints - Error budget tracking Use when: user needs production monitoring, observability platform, alerting, SLOs, incident response, or post-deployment health tracking.
technical-decision-making
pluginagentmarketplace
Master technical decision-making, architecture choices, technology evaluation, and technical roadmaps for engineering teams
language-fundamentals-skill
pluginagentmarketplace
Master programming languages from Python to Rust. Learn core concepts like variables, OOP, functional programming, algorithms, data structures, and competitive programming techniques. Use when exploring programming languages, learning CS fundamentals, or preparing for technical interviews.
launch-readiness-checklist
SanctifiedOps
End-to-end pre-flight checklist for launching a Solana token/app: infra, wallets, liquidity, comms, security, and rollback planning. Use before mainnet launch or major release.
monitoring-expert
paulund
Use when setting up monitoring solutions, logging, metrics, tracing, and alerting for applications and infrastructure.