Ground truth for FiveM/GTA V development. 24 offline data layers built from your own GTA V install and FiveM server: natives with apiset resolution and a Lua linter, archetypes, world placements, vanilla animation names, skeleton bone tags, vehicles, weapon components, peds, MLO interiors, embedded lights, weather timecycles, and your server's framework API. It checks your own files before the game sees them, decodes and edits prop lights against a measured vanilla reference, and covers parallax shaders and vanilla interior measurements. Nothing is guessed; a file that could not be inspected is never reported as clean.
Teaches the agent when and how to reach for the scout CLI. Ships as an umbrella skill plus one dedicated sub-skill per subcommand (scout-types, scout-files, scout-pattern, scout-loc, scout-build-settings) — config file shapes, output JSON shapes, cross-commit analysis, and the footguns that come with checking out historical commits
Adversarial multi-model code review with dual Optimizer/Skeptic agents across Sonnet and Opus. Finds issues, challenges its own findings, and only auto-fixes what survives cross-model consensus.
Adversarial multi-agent pipeline for Claude Code. Generators produce artifacts, discriminators validate them, and adversarial feedback loops drive convergence.
Use for Rust-specific ownership/API, async cancellation, unsafe/FFI soundness, feature/toolchain compatibility, diagnostics, packaging or profiling problems in a real crate.
Finds the TypeSafe docs, patterns, cookbook and blog sections that answer a Jev question, by keyword and by meaning, and tells your coding agent (Claude or Codex) to read them before any claim.
Every jev-mode skill in one plugin: Jev Sources, Jevaluate Publish, Jevaluate Private, Jevaluate Report, Jevaluate Harness and Jevaluate Eval. Install this or the single plugins, not both.
ABAP development through SAP ADT for AI agents: 173 tools over one or many SAP systems, with server-side policies, ATC, unit tests, transports and ABAP Cloud readiness checks.
WordPress on the Roots stack for AI assistants: detects Sage theme, Acorn mu-plugin or Radicle, routes to profile-aware skills, runs everything through Lando, reads official docs from a versioned corpus
Universal development assistant. Detects the project stack and routes work to specialist agents for architecture, implementation, debugging, review and research, enforcing design-system guardrails on every UI change.