监控
日志、指标与可观测性
slurm-gpu-training
dongzhuoyao
Use when running ML training on HPC clusters with Slurm, including job submission, environment setup, monitoring, and failure triage. Applies to any GPU training workload on Slurm-managed clusters. Triggers: "sbatch", "srun", "Slurm", "SBATCH", "job submission", "HPC", "cluster", "walltime", "squeue"
gpu-training-acceleration
dongzhuoyao
Use when optimizing PyTorch training speed or memory on CUDA GPUs — global flags, torch.compile, fused optimizers, mixed precision, gradient checkpointing, kernel fusion, memory layout, or latent-space training. Applies to any PyTorch training workload. Triggers: "torch.compile", "TF32", "fused optimizer", "mixed precision", "bf16", "fp16", "gradient checkpointing", "Triton kernel", "CUDA flags", "GPU slow", "GPU memory"
wandb-experiment-tracking
dongzhuoyao
Use when integrating W&B experiment tracking into ML training pipelines, including logging strategy, run configuration, and online/offline mode management. Triggers: "W&B", "wandb", "weights and biases", "experiment logging", "wandb.log", "wandb.init", "training dashboard"
algorithms
Tyler-R-Kendrick
Use when selecting algorithms, analyzing complexity, or reasoning about data structure choices. Covers Big-O notation, space vs time tradeoffs, amortized analysis, and algorithmic problem-solving strategy based on Knuth's "The Art of Computer Programming." USE FOR: algorithm selection, Big-O analysis, complexity comparison, choosing data structures, algorithmic problem-solving strategy DO NOT USE FOR: specific algorithm implementations (use sub-skills), system architecture (use dev/architecture), design patterns (use dev/design-patterns)
Failure Postmortem
Sounder25
Structured logging and analysis of execution failures to prevent recurrence.
wecom-cs-mano
JZQiang
"企业微信智能客服 V4（全自动版）- mss截图 + PIL红点检测 + EasyOCR + DeepSeek AI + pynput打字，全自包含无需外部API视觉模型"
writing-assistant
VegetaPn
Comprehensive writing workflow from ideation to publication. Guides users through creating polished articles by collecting ideas, asking clarifying questions, researching content, polishing drafts, adding images, and publishing to platforms like WeChat or X. Use when users want to write articles, blog posts, or long-form content, especially when starting from a topic idea, rough materials, or initial draft. Also use when users mention writing, publishing, or content creation workflows.
aio-mermaid
aiocean
This skill should be used when the user asks to "share a mermaid diagram", "generate diagram URL", "create diagram link", or mentions mermaid, minimalmermaid, shareable mermaid. Also use whenever the user wants to share or embed a diagram, asks to "draw", "diagram", or "visualize" something, even without mentioning Mermaid. Generates shareable MinimalMermaid diagram URLs using LZ-String compression.
git-conflict
ssiumha
Resolves Git conflicts (rebase, merge, cherry-pick, stash). Use when encountering merge conflicts during any Git operation.
Lint Hunter
udapy
Debugging compiler errors and tracing lifetimes.
observability
kcns008
Observability Agent (Pulse) — handles Prometheus/PromQL metrics, Thanos queries, Loki/ELK log analysis, Grafana dashboards, alert triage and tuning, SLO/SLI management, incident response, and post-incident reviews for Kubernetes and OpenShift.
database-administrator
nahisaho
Copilot agent that assists with database operations, performance tuning, backup/recovery, monitoring, and high availability configuration Trigger terms: database administration, DBA, database tuning, performance tuning, backup recovery, high availability, database monitoring, query optimization, index optimization Use when: User requests involve database administrator tasks.
site-reliability-engineer
nahisaho
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.
xcodebuildmcp
third774
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
update-focus
mseok
"Update current-focus.md with a structured session summary. Preserves the document's rich structure: weekly focus, session history rotation, open loops, mental state. Use at end of work sessions or when a session-end reminder appears."
file-watcher
AIDotNet
监视文件和目录变化，支持事件回调和过滤。
log-analyzer
AIDotNet
解析和分析日志文件，支持模式匹配、过滤、统计和错误检测。
arcgis-utility-networks
SaschaBrunnerCH
Work with ArcGIS Utility Networks for modeling and analyzing connected infrastructure. Use for network tracing, associations, and utility asset management.
arcgis-smart-mapping
SaschaBrunnerCH
Auto-generate renderers, calculate statistics, and create data-driven visualizations. Use for class breaks, unique values, heatmaps, dot density, relationship maps, and getting histogram/summary statistics.
sentry-setup-logging
getsentry
Setup Sentry Logging in any project. Use when asked to add Sentry logs, enable structured logging, capture console logs, or integrate logging libraries (Consola, Loguru) with Sentry. Supports JavaScript, Python, and Ruby.
arcgis-authentication
SaschaBrunnerCH
Implement authentication with ArcGIS using OAuth 2.0, API keys, and identity management. Use for accessing secured services, portal items, and user-specific content.
arcgis-portal-content
SaschaBrunnerCH
Manage portal content including saving WebMaps/WebScenes, bookmarks, slides, and portal items. Use for content persistence, WebMap/WebScene configuration, and navigation presets.
arcgis-interaction
SaschaBrunnerCH
Handle user interaction with map views including hit testing, feature highlighting, sketching, and event handling. Use for interactive map applications with feature selection and custom interactions.
sentry-fix-issues
getsentry
Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.