deep-agents-core
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
Bridge Server のリリース(バージョンbump + CHANGELOG + タグ → GH Actions で npm publish)
Prometheus/Grafana metrics analysis and PromQL queries. Use when investigating latency, error rates, resource usage, or any time-series metrics.
Splunk log analysis using SPL (Search Processing Language). Use when investigating issues via Splunk logs, saved searches, or alerts.
Honeycomb observability analysis. Use when querying Honeycomb datasets, traces, or metrics. Provides scripts and query syntax reference for high-cardinality exploration.
Log, metric, and trace analysis methodology. Use when analyzing logs, investigating errors, querying metrics, or correlating signals across observability backends (Coralogix, Datadog, CloudWatch).
Datadog log and metrics analysis. Use when querying Datadog logs, metrics, or APM data. Provides scripts and query syntax reference.
Coralogix log analysis with DataPrime query language. Use when querying Coralogix logs, metrics, or traces. Provides syntax reference and intelligent investigation scripts.
Elasticsearch/OpenSearch log analysis using Lucene query syntax and Query DSL. Use when investigating issues via ELK stack, OpenSearch, or any Elasticsearch-based logging.
Jaeger distributed tracing analysis. Use when investigating request latency, tracing errors across services, finding slow spans, or understanding service dependencies.
Infrastructure debugging for Kubernetes and AWS. Use when investigating pod crashes, deployment issues, resource problems, container failures, or cloud infrastructure issues.
AWS service troubleshooting patterns. Use for EC2, ECS, Lambda, CloudWatch, RDS issues.
Kubernetes debugging methodology and scripts. Use for pod crashes, CrashLoopBackOff, OOMKilled, deployment issues, resource problems, or container failures.
Safe remediation actions for Kubernetes. Use when proposing or executing pod restarts, deployment scaling, or rollbacks. Always use dry-run first.
Partition-first log analysis methodology. Use for log searches, error analysis, pattern finding across Datadog, CloudWatch, or Kubernetes logs.
Create HTML dashboards with KPI metric cards, bar/pie/line charts, progress indicators, and data visualizations. Use when users request dashboards, metrics displays, KPI visualizations, data charts, or monitoring interfaces.
Upgrades Helm chart dependencies (PostgreSQL, Vault) in the Chainloop project, including vendorized charts, container images, and CI/CD workflows. Use when the user mentions upgrading Helm charts, Bitnami dependencies, PostgreSQL chart, or Vault chart. CRITICAL - Major version upgrades are FORBIDDEN and must be escalated.
Multi-platform CI/CD pipeline expertise. Generate GitHub Actions, GitLab CI, Jenkins, and Azure Pipelines configurations. Analyze failures, optimize execution time, validate syntax, and configure matrix builds and caching strategies.
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.