Dev & Coding

Inventories everything an agent injects into each request besides the user's message and flags what to cut, move, or de-precision to protect the prompt cache.

A full-sweep refactoring skill that catalogs hidden coupling, needless dependencies and surplus code, then redesigns the system from first principles.

A framework for scoring AI agent output quality against fixtures and baselines so regressions are caught before they ship.

Turns an app URL into a validated Homebrew Cask and walks you all the way to a submitted pull request.

Builds reusable Convex components with defineComponent, their own schema, a typed client wrapper, and an npm publishing setup.

A disciplined TDD skill that executes exactly one bounded RED→GREEN experiment and returns factual check evidence without expanding scope.

A strict TDD execution skill that runs exactly one bounded RED→GREEN experiment, returning derived manifests and check receipts without committing or expanding scope.

Guides wiring third-party auth providers' JWTs into InsForge RLS and adding OKX x402 onchain pay-per-use billing.

A bridge skill that delegates prototyping, debugging, and code review to the Claude Code CLI headlessly with session continuity.

Delegate prototyping, debugging, code review and live web/X research to xAI's Grok CLI from Claude Code, with structured JSON results and multi-turn sessions.

A bridge skill that lets Claude Code delegate prototyping, debugging, code review, and cross-model second opinions to Codex CLI.

Configures a robot's onboard computer to launch its full ROS2 stack on boot using systemd services, layered launch files, udev rules and health checks.

A battle-tested playbook for containerizing ROS2 workspaces and running robot software stacks with Docker Compose.

A production-grade best-practices skill for camera/LiDAR/depth calibration and building multi-sensor robot perception pipelines.

A reference skill that teaches Claude AgentDB's advanced side: QUIC sync, hybrid vector+metadata search, multi-DB sharding, MMR and production patterns.

Applies abstract interpretation with interval, sign, congruence, octagon, and polyhedra domains to infer variable ranges and loop invariants without running the code.

A strictly read-only reviewer for changes to reusable Terraform modules that returns structured findings.

Documents the load-bearing design decisions, enforced invariants, and known weak points of the claude-night-market repo for judging design changes.

Repo-specific skill that classifies changes and enforces the gate, PR and release process when landing code or amending rules.

Rebuilds the claude-night-market dev environment from a bare machine and verifies it in under an hour, with a documented traps table.