Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when investigating Archestra bugs or incidents — staging issues, backend 50x errors, Drizzle failed queries, DB connection pressure, deploy regressions, or Kubernetes/runtime symptoms. Orientation only; defers the process to /investigate.
Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.
Use when changing Drizzle schemas, generating migrations, editing migration SQL, creating data-only migrations, diagnosing drizzle-kit check failures, or resolving migration/generated-client conflicts.
Use when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup.
Use when asked to sweep, clean up, or revisit pnpm overrides and minimumReleaseAge exclusions in platform/pnpm-workspace.yaml — unwinding a matured temporary CVE pin once its fix has cleared the 7-day window, or removing an override the dependency graph has made redundant. This skill only sweeps existing pins; it does not author new CVE fixes.
Use when writing or editing Archestra documentation pages under docs/pages/ — new feature docs, page rewrites, tone or copy fixes, or capturing docs screenshots.
Audit Cartography's rules and compliance frameworks under `cartography/rules/data/rules/`. Surfaces TODOs that the schema can now satisfy, per-provider rules that should collapse into one ontology rule, and duplicate detections across frameworks (CIS, ISO 27001, SOC 2, NIST). Use when the user asks to "audit frameworks", "audit rules", "review rule TODOs", "find duplicate rules", "find ontology candidates", "consolidate compliance frameworks", or "map ISO/SOC2 onto CIS".
Decode an encoded message using the bundled cipher scripts. Use when handed a hex-encoded or otherwise scrambled blob and asked for its plaintext; run the scripts rather than reasoning about the bytes by hand.
Author a Cartography security rule (one or more Cypher Facts plus a Pydantic Finding output model) under `cartography/rules/data/rules/`. Use when the user asks to add a security check, detection, attack-surface query, compliance control, CIS benchmark rule, or cross-cloud detection.
Audit and improve the cubic AI-review config (`cubic.yaml`) for this repo. Reviews the custom review rules for relevance, scoping, limits, and factual accuracy, then reconciles them against the repo's cubic learnings, promoting the few high-value recurring ones into durable rules and flagging obsolete, duplicate, or contradictory learnings for cleanup (each verified against the live code). Use when asked to "audit cubic", "rework the cubic config", "review the cubic rules", "check cubic learnings", or on a recurring cadence to keep the review config sharp.