FidusGate

Agent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.

Delivers a verified corporate handoff through ADR-scoped implementation and independent site verification.

SME for data flows, modular architectural designs, API specs, and ADR design modeling.

SME for backend routes, database optimization, indexing, and Prisma schema designs.

Enforce end-to-end DevOps best practices, environment standardization, security audits, and state-gated pipeline verification for Antigravity projects.

SRE for container configurations, Kubernetes, CI/CD pipeline automation, and context drift check-ins.

SME for screen rendering, visual premium palettes, responsiveness, and accessibility ARIA rules.

Enforce Integrated Business Planning (IBP) principles across Strategy, Finance, and Operations, ensuring cross-functional synthesis and budget alignment in agentic pipelines.

Enforce end-to-end Product Lifecycle Management (PLM) and Product Development Lifecycle (PDLC) guardrails, covering requirements traceability, API drift prevention, and SemVer release gating.

SME for requirement engineering, prioritization, and user-aligned backlog verification.

SME for test specs, Playwright E2E testing, unit tests, and performance load scripts.

SME for secure access rules, JWT authentication, SAST auditing, and threat analysis.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.

Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.

Architect and scaffold greenfield repositories with a modular flex architecture. Allows dynamic transitioning (flexing) between modular blended monoliths and enterprise monorepos (Turborepo/Nx) depending on project scope.

Generate production-ready mise.toml setups for local development, CI/CD pipelines, and toolchain standardization.

Plan and execute large refactors with dependency-aware work packets and parallel analysis.

To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.