Production-tested agents (56), commands (16), hooks (42), skills (22), and rules (19) for Claude Code and Codex CLI. All agents on Opus 4.8 — every prompt hardened by Claude Fable 5.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Frontend performance review — bundle size, lazy loading, CSS containment, web vitals, image optimization. Activate when reviewing frontend code for performance.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Color-system specialist — OKLCH, tinted neutrals, contrast, palette construction, dark/light theme selection by use context, status colors, accessibility.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Holistic design critique — NOT a code review. Judges aesthetic coherence, composition, hierarchy, intentionality. "Does this feel designed or generated?".
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Interactive-component polish specialist — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. The invisible details that compound into "feels right".
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Motion specialist — the 4-question Animation Decision Framework, easing curves, durations, springs, reduced-motion. Output in | Before | After | Why | markdown table.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
2D frontend UI umbrella review — typography, color, layout, motion, interaction. Runs a quick reflex audit, dispatches specialist sub-skills when a domain needs deep attention, consolidates findings.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Typography specialist — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType, font-loading. Called by frontend-ui-reviewer or directly for typography-focused audits.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Runtime GLB/GLTF inspection — traverse nodes, identify screen meshes, inspect UV coordinates, material property dumping, fixing exported materials at runtime. Use when textures don't map correctly to 3D models.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Go benchmarking methodology knowledge — testing.B API, benchstat comparison, sub-benchmarks, profile capture (-cpuprofile/-memprofile/-trace), reading output, dead-code elimination trap. Activate when Go code contains func Benchmark, uses testing.B, or user asks about Go benchmarks, benchstat, or performance…
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit Go concurrency — goroutines, channels, mutexes, context propagation, race conditions.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Deep audit of Go error handling — wrapping, inspection, logging, panic/recover patterns.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Upstream: https://pkg.go.dev/google.golang.org/grpc · https://grpc.io/docs/languages/go/.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Detect outdated Go patterns and suggest modern idioms — Go 1.21 through 1.24+ features.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit Go observability — structured logging, Prometheus metrics, OpenTelemetry traces, pprof, health checks.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Go performance review — profiling, benchmarks, allocation analysis, caching, connection pooling.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Review Go code for architecture patterns, error handling, SQL safety, and conventions.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Upstream: https://github.com/samber/do · v2: https://github.com/samber/do/tree/v2.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Skill "go-samber-lo" from RaNDoM6913/claude-code-superkit, covering samber/lo — generic collection utilities, what it is, high-frequency functions, transform and dedup / partition.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Skill "go-samber-oops" from RaNDoM6913/claude-code-superkit, covering samber/oops — structured errors, what stdlib doesn't give you, core api, attributes and stack traces.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Goal-backward verification — validates implementation results match stated goals using 4-level substantiation (exists/substantive/wired/data-flow).
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Project health dashboard — compilation, tests, TODOs, API spec drift, migration pairs, deps, security, docs, bundle.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Capture HTML/React components as PNG textures for 3D models — html2canvas, CanvasTexture, capture pipeline, resolution settings. Use when you need to display web UI on a 3D surface.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Opt-in shape-then-build flow for creating UI from scratch with maximum intentionality. 4-stage cycle: shape → refine → implement → polish. Invoke only when explicitly asked for "craft a UI" or "impeccable approach".
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Auto-detect and run project linters — supports Go, TypeScript, Python, Rust, and more.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: