Claude Skills by nuroctane

Hand-drawn, sketch-like style with doodles, handwritten fonts, and imperfect lines for a playful, informal feel.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

High-contrast, theatrical design with bold layouts, immersive visuals, and unconventional compositions that command attention.

Generate, regenerate, and validate 2D DXF drawings from Python ezdxf sources. Use for DXF files, `.dxf.py` generators, gen_dxf() sources, 2D profiles, outlines, templates, gaskets, panels, flat patterns, laser/plasma/waterjet cut layouts, and 2D drawing exports of CAD geometry.

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

Magazine-inspired editorial layout with refined serif typography, structured grids, and elegant reading experiences.

Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to orchestrate research, coding, and testing while cheaper subagents do bounded heavy lifting.

Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate research, coding, and testing to cheaper subagents while keeping planning, synthesis, and final review with the expensive model.

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Generates 2-3 social post drafts about engineering work in the current repository. Reads the repository's code and git history, asks targeted questions to fill gaps, and saves a markdown draft locally. Use when you want content about what was built without exposing transcripts or pushing anywhere.

Dark-themed cloud-platform aesthetic with modular grids, glass-like panels, and strong data hierarchy for productivity dashboards.

Vercel environment variable expert guidance. Use when working with .env files, vercel env commands, OIDC tokens, or managing environment-specific configuration.

eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building pr...

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

Executor MCP gateway — one catalog for OpenAPI/GraphQL/MCP integrations shared across agents. Use for external APIs, multi-agent tool routing, policies.

Use when the user provides a transaction hash (0x...) with a chain name, asks to investigate an on-chain incident or exploit, or points to an incident brief file.

Vibrant, personality-driven design with bold colors, playful graphics, and dynamic layouts that balance creativity with structure.

Refactoring pass — extracts repeated Tailwind class combos and markup into components, and lifts magic values into design tokens. Use when the codebase has obvious duplication, hardcoded hex values or pixel sizes, or when the user says \"clean this up\" / \"extract components\" / \"tokenize styles\". Invoke when the user asks for extract on their UI, or mentions 'extract' alongside design / UI / frontend work.

Explain a codebase or build plan like the listener is 10 years old - household analogies, mermaid diagrams, zero unexplained jargon. Two factory checkpoints (after planning - "here's what we're about to build"; after review - "here's how what got built actually works") plus standalone on any codebase. Explanations accumulate into factory/GUIDE.md, a plain-language owner's manual. Understanding is a first-class output of the factory, not a byproduct. Triggers - "explain like I'm 10", "how does...

Stage 4 of the Software Factory - walk the user through exactly what the coding loop will be told (a plain-language read-and-sign, minutes not an interview), then compile BRIEF.md + PLAN.md into factory/HANDOFF.md - one self-contained markdown file that runs as an overnight loop in Cursor or Claude Code. Encodes loop-engineering best practices - builder/checker roles, circuit breaker, on-disk state, restart permission, tier-gated tests. Triggers - "handoff", "get this ready for the loop", "fa...

Fractal-first overnight software factory from HANDOFF.md (Unix preferred).

Stages 1-2 of the Software Factory - a relentless one-question-at-a-time interview that sharpens a loose idea into a brief (factory/BRIEF.md), then breaks the brief into a staged, dependency-ordered task list (factory/PLAN.md). This is the skill that CREATES the task list. Built for semi-technical and non-technical builders - plain language, a recommendation with every question. Use standalone or via /factory. Triggers - "plan my build", "turn this idea into tasks", "factory plan".

Stage 6 of the Software Factory - the fresh-eyes review after the overnight loop says "done". Reads ONLY the contract and the code changes (never the loop's chat or reasoning), re-runs every acceptance criterion, and actively tries to prove the build does NOT meet the contract. Reports in plain language - what's solid, what's broken, what was quietly skipped. Escalates genuine open decisions back to the user; everything else is verified fact. Triggers - "review the build", "did the loop actua...

Stage 3 of the Software Factory, and a standalone skill - turn tasks, features, or a whole component into acceptance criteria and tests that PROVE the work is correct, so a coding loop can check itself instead of asking you to trust it. Behavior + evidence formula, four test tiers, mandatory error paths. Works on a factory PLAN.md, a single task, or any feature description. Triggers - "define tests", "acceptance criteria", "how do I know it works", "factory tests".

Software Factory — the conductor. One command that walks a semi-technical or non-technical builder through the whole software assembly line - grill the idea sharp, plan it as tasks, define tests that prove each task works, hand off to an overnight coding loop, then review, prove it on video, and explain it in plain language. Reads factory/STATE.md to know where you are and always tells you what's next. Invoke as /factory in Claude Code or Cursor. Triggers - "factory", "software factory", "sta...

Game-inspired fantasy aesthetic with bold, premium visuals, rich color palettes, and immersive thematic elements.

Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects. Use when the task involves organizing project structure with FSD layers, deciding where code belongs, placing static assets (images, icons, fonts, PDFs), grouping closely related slices, defining public APIs and import boundaries, resolving cross-imports or evaluating the @x pattern, deciding whether to create or remove an entity, evaluating whether the entities layer is needed at all, deciding ...

A playful, energetic, cartoonesque interface inspired by friendly children's-book illustrations — warm cream backgrounds, big bold custom display typography, saturated brand color blocks, thick black outlines, generously rounded shapes

Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.

Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Locates and loads the right Google product skill on demand from a remote catalog index, instead of preloading every skill. Use at the START of any request touching a Google product, API, or developer platform - including Google Cloud (GKE, Cloud Run, IAM, BigQuery, Vertex AI, Spanner), Google Ads, Google Analytics, Google Workspace (Gmail, Drive, Admin SDK), Chrome and Chrome extensions, Android, Firebase, YouTube, Google Maps, Gemini and the Gemini API, Google Play, and Flutter. Consult the ...

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Provides foundational Firebase CLI setup, CLI installation, version checks (`firebase-tools@latest --version`), CLI login (including --no-localhost), project creation, project selection (`firebase use`), and app config file downloads (`google-services.json`, `GoogleService-Info.plist`). Use ONLY for CLI login, project creation/switching, or downloading app config files. Don't use for Firebase Hosting deploy, Firestore, Auth, App Hosting, Data Connect, Crashlytics, or Remote Config.

Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags.

Flags SDK and Vercel Flags expert guidance. Use when declaring feature flags with flag(), wiring provider adapters (Vercel, Statsig, LaunchDarkly, PostHog, and others), managing flags with the vercel flags CLI, implementing the precompute pattern for static A/B tests, or integrating the Flags Explorer.

Guide for feature flags and A/B tests with the Flags SDK (`flags` npm package) and Vercel Flags. Use when: declaring flags with `flag()`, using `vercelAdapter` or `vercel flags` CLI (add, list, enable, disable, inspect, archive, rm, sdk-keys), setting up providers/adapters (Vercel, Statsig, LaunchDarkly, PostHog, GrowthBook, Hypertune, Global Config, OpenFeature, Split, Flagsmith, Reflag, Optimizely, or custom adapters), implementing precompute patterns for static pages, setting up `identify`...

Two-dimensional minimalist style with vibrant colors, clean typography, and no 3D effects for fast, user-friendly interfaces.

Hierarchical agent loops with recursive self-organization.

Approachable, intuitive design with rounded elements, ample whitespace, and soft pastel color palettes.

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Forward-looking design with tech-inspired typography, modern layouts, and a sleek, innovation-driven aesthetic.

Protect prompt-cache hit rate when routing a coding agent (Claude Code, Codex, nur) through your own gateway/proxy. Use when configuring a custom base_url/gateway, debugging exploding token costs or slow first-token latency behind a proxy, or evaluating an "OpenAI/Anthropic-compatible" gateway. Watch the cache hit rate — most proxies silently break it.

Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructing, proposing, describing, or executing any gcloud CLI commands - including when answering questions about gcloud syntax, or formatting flags. Don't use when writing Google Cloud client library code or raw REST/gRPC API requests.

Generate, inspect, dry-run, and statically validate plain FDM `.gcode` from 3D mesh files by orchestrating real slicer CLIs. Use when Codex needs to slice `.stl`, `.obj`, unsliced `.3mf`, `.ply`, `.glb`, or `.gltf` into printer-profiled G-code, discover local slicer backends, inspect whether a mesh is slice-ready, or validate generated G-code before any printer-specific handoff.

Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.

Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inputs, tools, media generation, caching, batch prediction, and Live API.

Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.

Generates a Gemini LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini Enterprise LiveAPI websocket endpoint, handles session setup/resumption, bearer token refresh, and sending/receiving `ClientMessage`/`ServerMessage` protos. Don't use for general (non-live, non-bidirectional) Gemini API usage such as one-shot `generateContent`, embeddings, image/video generation, or fine-tuning...

Generate multiple original brand campaign worlds from a supplied visual reference while controlling how close the new work feels without copying protected signature elements. Use when a user provides a brand identity image, poster, editorial campaign, moodboard, or generated concept and asks for inspired alternatives, several distinct brands in one visual family, a closer-to-reference V2, exact wordmarks inside images, or originality-safe image-generation prompts and outputs.