The cross-validation skill enables the cross-validation agent to validate consistency between agent outputs and their sources. It provides the rules registry and validation runner that check pairwise consistency across the agent pipeline.
Break the specification into logical architectural components. Use when identifying system components, data flows, external dependencies, and boundaries.
Identify the components required to implement the design. Use when mapping architecture to concrete services, modules, pipelines, and GitOps components.
Validate Kubernetes-related design decisions. Use when checking resource requirements, deployment patterns, network design, and secret usage in the design.
Provide CLI commands that scaffold new components, pipelines, tests, and GitOps structures. Use when scaffolding new services, pipeline-spec.yaml, GitOps overlays, or test suites.
Ensure the Fawkes CLI provides a clean, intuitive developer experience. Use when validating command naming, help text, error messages, or interactive prompts.
Provide a reproducible, standardized development environment for all Fawkes projects using devcontainers. Use when validating devcontainer.json, Dockerfile.dev, required tools, or Coder compatibility.
Ensure all required tools for Fawkes development are installed and correct versions. Use when validating Node, Python, kubectl, kustomize, or Fawkes CLI versions.
Simulate PIPE, OBS, GitOps, and cluster behavior locally for fast feedback loops. Use when running local pipeline simulations, GitOps updates, or cluster deployments.
Simulate GitOps updates locally without pushing to remote repos. Use when cloning GitOps repo locally, applying OBS updates, or validating manifest correctness.
Automate initial project setup for developers. Use when installing dependencies, generating environment files, configuring Git hooks, or bootstrapping local clusters.
Install all project dependencies in a reproducible way. Use when installing Node/Python dependencies, validating lockfiles, or checking reproducibility.
Full user research methods for uFawkes product decisions. Use when the 15-minute discovery exercise is insufficient — when the riskiest assumption is untested, when user segments disagree, or when a major capability is being designed from scratch. Tier 3: Phase 2.
15-minute JTBD + acceptance criterion exercise. Use before any spec session. Produces a discovery-brief.md that anchors the entire increment to a real user need and a measurable DORA outcome. Implements DORA AI Capability 6.
Enforce minimum documentation standard across uFawkes repos. Use when auditing a repo before release, onboarding a new repo to the suite, or implementing roadmap item 0.6 (cross-repo README links). Directly supports DORA AI Capability 3 and the 2023 DORA finding that documentation quality amplifies all technical…
Compute the four DORA delivery metrics from uFawkesObs (Prometheus + Loki). Use when producing monthly DORA snapshots, validating post-release metric trends, or generating ROI evidence. Requires uFawkesObs running. Implements DORA AI Capabilities 2 and 7.
Validate that the deployed application behaves correctly after reconciliation. Use when validating rollout status, health checks, logs, metrics, or trace propagation.