Claude Skills by gaelic-ghost

Choose the right server-side JVM project shape before implementation, including Java versus Scala language choice, Gradle/Maven/SBT ownership, framework fit, validation commands, package boundaries, Android handoffs, and documentation updates.

Run, filter, debug, and explain server-side JVM tests across Gradle, Maven, SBT, Java, Scala, JUnit, ScalaTest, MUnit, unit, integration, contract, and service-level test surfaces.

Plan, implement, test, and diagnose app sync contracts in server-side Swift services, including incremental change feeds, cursor or token semantics, idempotent writes, conflict handling, optimistic concurrency, deleted-record/tombstone behavior, background job handoffs, API-shape coordination, and Vapor or Hummingbird integration.

Plan, implement, test, and diagnose server-side Swift authentication and authorization for Vapor and Hummingbird services, including Basic and Bearer auth, JWT, sessions, OAuth or OIDC handoffs, password hashing, token lifecycle, middleware placement, request context, route protection, authorization policy, security-sensitive tests, and deployment secret handoffs.

Author and diagnose Dockerfile and OCI runtime definitions for server-side Swift while GitHub Actions exclusively builds, tests, publishes, and deploys Linux images.

Configure a GitHub Actions-only Fly.io deployment adapter for an exact prebuilt Swift service image, with protected environments, scoped credentials, health verification, and rollback.

Plan, build, run, test, and diagnose Hummingbird components under Services/ in the canonical product workspace. Hand fresh component creation and guidance alignment to the workspace service adapter.

Plan, implement, test, and diagnose Leaf-rendered Vapor sites and HTML email with typed contexts, layouts, partials, custom tags, escaping, accessibility, assets, caching, and rendering tests.

Plan, implement, test, and diagnose observability for server-side Swift services, including Swift Logging, Swift Metrics, Swift Distributed Tracing, OpenTelemetry handoffs, request correlation, trace propagation, structured log fields, metric naming, health signals, privacy-safe diagnostics, and Vapor or Hummingbird integration.

Design, generate, implement, test, and diagnose Swift OpenAPI and RPC-style server contracts using Swift OpenAPI Generator, OpenAPIRuntime, OpenAPIHummingbird, OpenAPIVapor, SwiftPM plugins, Dash docsets, official GitHub/SPI documentation, and clear handoffs to Vapor or Hummingbird workflows.

Plan, build, test, and diagnose server-side Swift persistence, database, ORM, model, migration, query, transaction, and repository work for Vapor, Hummingbird, Fluent, and SwiftPM services.

Add, review, or migrate AWS integrations in server-side Swift using Soto as the standard SDK, with one shared AWSClient per application or Lambda environment and explicit single-owner shutdown.

Plan, implement, test, and diagnose direct SwiftNIO work in server-side Swift packages, including EventLoopGroup ownership, Channel pipelines, ChannelHandlers, ByteBuffer usage, back-pressure, nonblocking I/O, protocol implementations, EmbeddedChannel tests, and handoffs back to Vapor or Hummingbird when a higher-level framework is the better fit.

Plan, build, run, test, and diagnose Vapor components under Services/ in the canonical product workspace. Hand fresh component creation and guidance alignment to the workspace service adapter.

Add or align a Hummingbird or Vapor executable under Services/ in an existing canonical Xcode workspace. Use only behind bootstrap-xcode-workspace add-component; local development is native macOS with Homebrew services, while Linux artifacts and deployments run in GitHub Actions.

Choose SwiftSyntax, compiler, SourceKit, SourceKitten, IndexStoreDB, or SourceKit-LSP by information and project model. Use before Swift tooling work when Swiftly and Xcode may resolve different binaries.

Configure or diagnose SourceKit-LSP across SwiftPM, compilation databases, and build servers. Use for completion, navigation, refactoring, diagnostics, semantic tokens, indexing, generated files, or editor-client failures.

Review, design, or repair Swift APIs for Swifty naming, call-site ergonomics, access control, typed result shapes, human-friendly errors, and consistency across sibling symbols. Use swift-error-handling-style-workflow for deeper failure-shape decisions.

Inspect Swift toolchain selection, driver jobs, diagnostics, AST, SIL, LLVM IR, dependencies, modules, and interfaces. Use for compiler behavior, lowering, build-job, or emitted-artifact investigations.

Design or repair Swift error handling style using throws, typed throws, Result, Optional, AsyncSequence failure types, domain errors, Cocoa bridging, and concise functional recovery paths.

Align SwiftFormat, SwiftLint, formatter and linter responsibility, checked-in style config, Git hooks, and CI formatting policy for Swift repositories. Use for shared Swift style and formatting before source-organization or modernization passes.

Design or repair Swift data modeling and data pipelines using functional, composable, monadic flows with Optional, Result, throws, async throws, AsyncSequence, map, flatMap, compactMap, filter, reduce, and clear imperative fallbacks when needed. Use swift-error-handling-style-workflow for deeper error carrier and diagnostic decisions.

Run complete modernization and repair passes over existing Swift code, sequencing formatting, source inventory, file splitting, API cleanup, error handling cleanup, functional pipeline cleanup, concurrency cleanup, tests, docs handoffs, and validation.

Query Swift types, USRs, documentation, occurrences, references, and relationships with SourceKit, SourceKitten, index stores, and IndexStoreDB. Use for file-local semantics or project-wide symbol questions.

Organize Swift source trees and files by concern, feature, and layer; split oversized files, extract extension files, normalize MARK sections, file headers, and TODO/FIXME ledgers with stricter split defaults. Use after formatting baseline is clear.

Parse, inspect, generate, or transform source with SwiftParser and SwiftSyntax while preserving fidelity. Use for Swift codemods, structural linting, generators, syntax-aware edits, or macro trees without inferred types.

Work at the Expo SDK 56+ inline native module boundary with current Expo docs, live project inspection, TypeScript interface generation, and explicit Apple Dev Skills handoffs.

Reproduce and evaluate refusal-direction ablation on controlled checkpoints. Use when estimating refusal representations, applying activation or weight orthogonalization, measuring behavior change, or comparing ablated artifacts.

Decode and analyze suspicious scripts and active documents without triggering them. Use for shell, AppleScript, JavaScript, Python, PowerShell, shortcuts, Office files, PDFs, profiles, macros, embedded objects, and staged payloads.

Route Apple app-extension work across extension points, targets, isolation, entitlements, shared containers, lifecycle, privacy, testing, signing, distribution, and handoffs. Use when the extension point is not settled.

Route an Apple communication request to iMessage collaboration, communication notifications, Push to Talk, VoIP calling, default-app, or macOS companion workflows before implementation.

Assess whether suspicious evidence indicates a real threat and explain it plainly. Use for confidence, protective actions, uncertainty, impact, and advice after artifact, endpoint, identity, or incident evidence.

Prioritize a vulnerability using actual asset exposure and impact. Use when versions, reachability, prerequisites, privileges, data, exploit maturity, mitigations, detection, business criticality, and urgency matter beyond CVSS.

Assess a suspected macOS threat using exact host and artifact evidence. Use for suspicious apps, processes, downloads, profiles, extensions, alerts, persistence, privacy, or network activity while keeping protections distinct.

Turn validated security behavior into tested detection content. Use for Sigma, osquery, YARA-X, endpoint or SIEM queries, cloud detections, correlation, alert enrichment, and fixtures with explicit telemetry and false-positive controls.

Author, test, tune, and document YARA-X rules from validated artifact evidence. Use when suspicious files, scripts, documents, or binary features need local detection with stable patterns, fixtures, performance checks, and regression tests.

Benchmark model runtimes across latency, throughput, memory, energy, load time, size, and stability. Use when comparing Core AI, Core ML, MLX, ExecuTorch, PyTorch, quantization, devices, or packaging.

Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.

Design, implement, test, and package an ACP agent/server. Use for protocol negotiation, sessions, streaming updates, tool rendering, permissions, authentication, SDK choice, and registry submission.

Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.

Build or modify a Falco web application in idiomatic F#, using functional routing, request and response helpers, explicit ASP.NET Core integration, security boundaries, and focused tests.

Build or modify a Giraffe web application in idiomatic F#, using composable HttpHandler functions, explicit ASP.NET Core integration, configuration, authentication, and focused endpoint tests.

Build Hermes Agent skills, Python plugins, specialized providers, messaging adapters, memory and context engines, secret sources, desktop or dashboard extensions, MCP integrations, hooks, and programmatic hosts.

Build a local-first Java or Kotlin Google ADK agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.

Build or modify an Oxpecker web application in idiomatic F#, using endpoint routing, functional EndpointHandler and EndpointMiddleware composition, ASP.NET Core metadata, and focused endpoint tests.

Check reputation for a suspicious artifact, signer, hash, URL, domain, certificate, package, or vendor. Use when threat intelligence informs triage while privacy, stale data, false positives, and behavior limits stay explicit.

Choose A2A, ACP, MCP, a native host integration, a terminal thread, or a Hermes programmatic interface. Use when the direction of agent, editor, tool, or host control is unclear.

Compare and select Core AI, Core ML, MLX, MLX Swift, MLX LM, ExecuTorch Apple delegates, or Foundation Models. Use when an Apple model workflow needs a runtime choice and implementation handoff.

Choose an F# web application framework before implementation, comparing ASP.NET Core Minimal APIs, Giraffe, Falco, Oxpecker, and Saturn by application shape, composition model, dependencies, testing, and deployment boundaries.

Route Hermes Agent work to the correct operator, extension-development, messaging-gateway, Nous services, or Socket compatibility workflow. Use when a request spans surfaces or its extension boundary is unclear.