Agent skills

Step-by-step complex reasoning for multi-variable problems.

Semantic code understanding with IDE-like symbol operations.

Analyzes AI hardware stocks and supply chain bottlenecks using reverse supply chain investment research methodologies.

Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal, with optional lease-backed…

Monitors serial port communications and analyzes embedded firmware logs to identify boot issues and runtime behavior.

Optimize SerpApi performance with caching, async searches, and result

Handle SerpApi rate limits and credit-based usage quotas.

Plan, build, test, and diagnose server-side Swift persistence, database, ORM, model, migration, query, transaction, and repository work…

Audits Linux servers for configuration vulnerabilities, inspects exposed services, and applies safe, reversible hardening measures.

Map service delivery across frontstage actions, backstage processes, and supporting systems.

Wires every side effect and native channel as an injectable interface behind a Provider that throws UnimplementedError until the…

Build a service catalog — schema, starter entries, and governance model.

Scans the current Go project and identifies the Service → Module → Resource hierarchy for tenant-manager registration.

Implement service mesh (Istio, Linkerd) for service-to-service communication, traffic management, security, and observability.

When to activate: service mesh, Istio, Linkerd, mTLS, traffic management, circuit breaker, retry, canary, sidecar, DestinationRule…

This skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance.

Skill for the Services area of Securacy. 113 symbols across 25 files.

Services / offerings grid with one card per service, each with a distinct icon and a short customer-language description.

Claude Code session analysis, tool call patterns, efficiency metrics, and anti-pattern detection

Compare two sessions side-by-side using Agent Monitor data — per-model token usage (input/output/cache_read/cache_write + compaction…

Use when an agent session ran outside the repo whose commits should record it — e.g. launched from a higher-level folder, a non-Entire…