aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Central authority for Gemini CLI sandboxing and isolation. Covers Docker, Podman, macOS Seatbelt profiles, and security boundaries. Use when enabling sandboxing, choosing sandbox methods, configuring Seatbelt profiles, or troubleshooting sandbox issues. Delegates 100% to gemini-cli-docs for official documentation.
Melodic Software brand identity guidelines. Use when styling projects, creating marketing materials, building UI components, or ensuring brand consistency. Covers colors (#1E90FF melodic blue primary), typography (Inter font family), logo usage, brand voice ("Building software that sings"), and component patterns.
Design effective system prompts for custom agents. Use when creating agent system prompts, defining agent identity and rules, or designing high-impact prompts that shape agent behavior.
Developer environment setup guides for Windows, macOS, Linux, and WSL. Use when setting up development machines, installing tools, configuring environments, or following platform-specific setup guides. Covers package management, shell/terminal, code editors, AI tooling, containerization, databases, and more.
Design spec-based review workflows with visual proof and issue classification. Use when setting up review processes, validating against specifications, or implementing screenshot-based visual validation.
Design E2E tests following user-story-driven patterns with verification checkpoints. Use when creating end-to-end tests, validating complete user journeys, or designing Playwright/Cypress test patterns.
Design custom agents from scratch using Claude Agent SDK patterns. Use when building domain-specific agents, designing agents with full SDK control, or creating specialized agents with custom tools and prompts.
Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing priming hierarchies for agents.
Audit current context composition and identify optimization opportunities. Use when context window is overloaded, agents are underperforming, or applying the R&D framework to optimize token usage.
Design consumer-driven contract testing strategies using Pact, verify provider contracts, and manage API evolution with contract-first approaches.
Designing and implementing robust command-line interfaces using OCaml's cmdliner library, following Daniel Bünzli's design principles. Use when Claude needs to: (1) Design a new CLI or subcommand layout, (2) Implement cmdliner terms and combinators, (3) Enforce clear, predictable, orthogonal options, (4) Produce high-quality --help output and error messages, (5) Integrate cmdliner CLIs into dune-based OCaml projects.
Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when designing new agents, refactoring general agents into specialists, or optimizing agent context for a single task.
Comprehensive authentication implementation guidance including JWT best practices, OAuth 2.0/OIDC flows, Passkeys/FIDO2/WebAuthn, MFA patterns, and secure session management. Use when implementing login systems, token-based auth, SSO, passwordless authentication, or reviewing authentication security.
Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.
Comprehensive authorization guidance covering RBAC, ABAC, ACL, ReBAC, and policy-as-code patterns. Use when designing permission systems, implementing access control, or choosing authorization strategies.
Implement hooks for permission control and security in custom agents. Use when adding security controls, blocking dangerous operations, implementing audit trails, or designing permission governance.
Threat modeling methodologies (STRIDE, DREAD), attack trees, threat modeling as code, and integration with SDLC for proactive security design
Fixing odoc documentation warnings and errors. Use when running dune build @doc, resolving reference syntax issues, cross-package references, ambiguous references, hidden fields, or @raise tags in OCaml documentation.
Use when designing secret storage, rotation, or credential management systems. Covers HashiCorp Vault patterns, AWS Secrets Manager, Azure Key Vault, secret rotation, and zero-knowledge architectures.
Use when implementing circuit breakers, retries, bulkheads, or other resilience patterns. Covers failure handling strategies for distributed systems.