监控
日志、指标与可观测性
performance-budget-enforcer
hopeoverture
Monitors Lighthouse scores and JavaScript bundle sizes across deployments with automated alerts when performance thresholds are exceeded. This skill should be used when setting up performance monitoring, enforcing bundle size limits, tracking Lighthouse metrics, or adding performance regression detection. Use for performance budgets, bundle size, Lighthouse CI, performance monitoring, regression detection, or web vitals tracking.
iterative-code-evolution
aaronjmars
Systematically improve code through structured analysis-mutation-evaluation loops. Adapted from ALMA (Automated meta-Learning of Memory designs for Agentic systems). Use when iterating on code quality, optimizing implementations, debugging persistent issues, or evolving a design through multiple improvement cycles. Replaces ad-hoc "try and fix" with disciplined reflection, variant tracking, and principled selection of what to change next.
cost-optimization
timequity
Cloud cost management, rightsizing, and FinOps practices.
soc-operations
SherifEldeeb
Security Operations Center workflows, alert triage, shift handovers, and operational reporting. Automate SOC documentation and standardize processes. Use for SOC-related tasks, alert management, and operational metrics.
log-forensics
SherifEldeeb
Analyze system, application, and security logs for forensic investigation. Use when investigating security incidents, insider threats, system compromises, or any scenario requiring analysis of log data. Supports Windows Event Logs, Syslog, web server logs, and application-specific log formats.
satoshi-spirit
sene1337
Guided protocol for an AI agent to discover, stress-test, and maintain a living worldview with their human (or AI director). Trigger on "worldview", "discover my principles", "what do I believe", "forge my worldview", "satoshi spirit", or when a human asks their agent to develop convictions on a domain. Do NOT use for simple opinion questions, one-off debates, or when the human just wants a quick take.
hytale-networking
MnkyArts
Handle Hytale network packets, create custom packets, and implement client-server communication. Use when asked to "create custom packets", "handle network messages", "send data to client", "receive client data", or "implement networking".
continuous-monitoring
pluginagentmarketplace
Real-time monitoring and detection of adversarial attacks and model drift in production
Toolcrib
robdtaylor
Tool inventory management for MNMUK machine shop. Tracks tooling, inserts, consumables with reorder points and usage. USE WHEN user asks 'tool inventory', 'what inserts', 'reorder', 'tool crib', 'do we have', 'tooling cost', or 'tool usage'.
hytale-plugin-basics
MnkyArts
Create and structure Hytale server plugins with proper lifecycle, manifest, dependencies, and registries. Use when asked to "create a Hytale plugin", "make a Hytale mod", "start a new Hytale plugin", "setup plugin structure", or "write plugin boilerplate".
rabbitmq-master
mOdrA40
Ultimate RabbitMQ expertise skill for production-grade message broker architecture, implementation, and operations. Top 0.01% knowledge covering: (1) Advanced messaging patterns - Dead Letter Exchanges, Delayed Messages, Priority Queues, Consistent Hash Exchange, Sharding, (2) High Availability - Clustering, Quorum Queues, Stream Queues, Federation, Shovel, (3) Performance Engineering - prefetch tuning, connection pooling, batch publishing, memory optimization, flow control, (4) Security - TLS/mTLS, OAuth2, LDAP, certificate rotation, (5) Monitoring - Prometheus metrics, custom health checks, anomaly detection, (6) Troubleshooting - memory alarms, network partitions, queue backlogs, consumer starvation, (7) Multi-tenancy - vhost design, resource limits, isolation patterns, (8) Event-driven architectures - CQRS, Event Sourcing, Saga patterns with RabbitMQ. Use when: building messaging systems, debugging RabbitMQ issues, optimizing performance, designing HA architectures, implementing advanced patterns, production hardening, capacity planning, migration strategies.
golang-mastery-skill
mOdrA40
Principal/Senior-level Go (Golang) playbook for architecture, idiomatic code, concurrency, testing, performance, reliability, security, observability, and production readiness. Use when: designing services/APIs/CLIs, doing large refactors, running code reviews, debugging races/leaks, tuning performance, hardening security, and shipping to production.
grafana-dashboard-design
taptap
创建/修改 Grafana Dashboard 时触发，提供专业的设计规范。
writing-bots
ApeWorX
Write a bot to continuously listen and respond to events on a public blockchain network.
wfc-observe
sam-fakhreddine
Translates formal system properties (SAFETY, LIVENESS, INVARIANTS, PERFORMANCE) from a PROPERTIES.md file into observability definition snippets (metric definitions, alert rule conditions, dashboard panel fragments). REQUIRES: A specification file (default: PROPERTIES.md) containing properties with quantifiable numeric bounds. USE FOR: Generating metric definition snippets, alert condition logic (PromQL), and dashboard panel JSON fragments based on formal specs. NOT FOR: Writing application instrumentation logic (inserting metrics into .py/.go files); generating high-cardinality metrics (user IDs, emails); properties enforced at compile-time (static analysis); setting up monitoring infrastructure (Terraform/Helm); incident triage.
database-connect
manastalukdar
Database MCP server integration for PostgreSQL, MySQL, MongoDB
gui-screenshot-loop
Idate96
General GUI screenshot loop via MCP. Use for any screen/window/region capture while debugging UI or visual tools.
devdocs-bugfix
ab300819
Test-first bug fixing workflow. Guide users through reproducing bugs, writing failing tests, fixing code, and committing. Use when users report bugs, need to fix issues, or mention keywords like "bug", "fix", "issue", "崩溃", "报错", "修复".
terraform-patterns
radra23
Per-backend Terraform provider patterns, resource names, auth variables, and gotchas for grafana / datadog / newrelic / dash0. Use when generating observability-backend Terraform.
windows-notify
duckytan
Send Windows balloon notifications to system tray. Use when informing user of task completion, status updates, errors or warnings. Trigger phrases: "(send show display) notification", "(task process) completed", "(operation process script) finished", "alert user", "need to notify", "send alert", "(error warning notification) message".
python-dual-mode
Victory-Hugo
将既有或新编写的 Python 脚本重构为双模式模块，用于稳定、可维护的数据处理流。
cleanproject
manastalukdar
Remove debug artifacts and temporary files safely with git checkpoint protection
kitty
XYenon
Instructions for using kitty remote control to spawn windows/tabs, send text, inspect output, and manage processes. Useful for running servers or long-running tasks in the background.
auditoria-visual
xoykor
Capture e inspecione imagens da janela ou tela quando for necessário verificar visualmente o resultado do trabalho, diagnosticar problemas de interface ou comprovar uma correção no DeepSeek Harness.