监控
日志、指标与可观测性
root-cause-tracing
timequity
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack to identify source of invalid data
kubernetes-orchestration
spjoshis
Master Kubernetes with pods, deployments, services, ingress, ConfigMaps, secrets, and production cluster management.
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.
learn
kevinslin
learn from the current session
cost-optimization
timequity
Cloud cost management, rightsizing, and FinOps practices.
agile-metrics
spjoshis
Master agile metrics with velocity, burn-down charts, cycle time, and team health indicators for data-driven improvement.
risk-management
spjoshis
Master risk management with identification, analysis, mitigation strategies, and monitoring techniques for proactive project risk handling.
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.
campaign-execution
Zuttam
Execute LinkedIn outreach campaigns by sending connection requests and messages. Use when user wants to run a campaign, execute outreach, check campaign status, send messages, or track campaign progress. Can be invoked with optional campaign_id and action (run, status, pause, resume).
monitoring-observability
1Mangesh1
Observability patterns and monitoring best practices. Use when user asks to "set up monitoring", "structured logging", "distributed tracing", "metrics collection", "observability", "APM setup", "log aggregation", "metrics dashboards", "error tracking", "performance monitoring", or mentions observability stack and monitoring strategy.
autoresearch
chrisliu298
Autonomous experiment loop faithful to Karpathy's autoresearch. Set up a branch, establish a baseline, then loop forever: edit, commit, run, measure, keep or revert. Use when asked to "run autoresearch", "optimize X in a loop", or "start experiments".
cloud-monitoring
liauw-media
"Cloud monitoring with Prometheus, Grafana, and cloud-native tools. Use when setting up metrics, alerts, dashboards, or troubleshooting performance issues."
root-cause-tracing
Crumbgrabber
Use when errors occur deep in execution and you need to trace back to
decision-log
mkdir700
"MANDATORY pre-commit workflow for vibe coding. ALWAYS trigger when user says 'commit', 'git commit', or any commit-related command. Forces diff review and decision log generation BEFORE allowing commit to proceed."
pdf-processing-pro
Crumbgrabber
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.
work-management
ajshedivy
"Query, monitor, and analyze jobs on IBM i using SQL table functions via ibmi-mcp-server. Use when user asks about: (1) finding jobs by status, user, subsystem, or type, (2) monitoring active job performance (CPU, I/O, memory), (3) detecting long-running SQL statements, (4) analyzing lock contention, (5) checking job queues, (6) replacing WRKACTJOB, WRKUSRJOB, WRKSBSJOB, WRKSBMJOB commands, or (7) any IBM i work management task."
enterprise-java
ProjAnvil
企业级 Java 开发技能，涵盖 Spring 生态系统、微服务、设计模式、性能优化和 Java 最佳实践。使用此技能构建企业级 Java 应用、使用 Spring Boot、实现微服务，或需要 Java 架构和性能调优指导时使用。
git-advanced
1Mangesh1
Advanced Git operations including rebase, cherry-pick, bisect, reflog, and recovery. Use when user asks to "rebase branch", "cherry-pick commit", "find bug with bisect", "recover lost commit", "squash commits", "fix git history", "interactive rebase", or any advanced git tasks.
tg
Garfield1002
Use tg to send Telegram messages, attach files, and listen for replies from the command line. Trigger when the user wants to send notifications, share files, or receive messages via Telegram.
root-cause-tracing
liauw-media
"Use when symptoms don't reveal the cause. Trace backward through call chains to find where problems originate. Follow: Observe symptom → Find immediate cause → Identify caller → Keep tracing → Locate trigger."
SKILL.md — ClawOS Agent Capability
Shepherd217
Silent watch active. Ready for live deployment.
artifact-collection
SherifEldeeb
Collect and preserve digital forensic artifacts from systems and devices. Use when responding to incidents, collecting evidence for investigation, or preserving volatile data. Supports Windows, Linux, macOS artifact collection with chain of custody.
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".