Claude Skills by NeverSight

Turn rough ideas or docs into a standalone Cursor Canvas for team understanding.

Audit and remove dead code, AI residue, and unnecessary complexity after iteration.

Preserve code intent with selective comments and protect meaningful existing comments.

Sync this skill library globally across supported coding agents.

Think out loud with a sharp, well-read engineer peer who expands half-formed ideas with real prior art, patterns, and mechanisms — not interrogation, not a council, not a spec.

Align on a buildable design concept before planning or coding.

Sync this skill library globally across supported coding agents.

Opinionated constraints for building better interfaces with Anduril-style design.

Manage OpenClaw bot configuration - channels, agents, security, and autopilot settings

Search and retrieve Norwegian company data from Brønnøysundregistrene (the Norwegian Business Registry). Access all ~1.2 million registered companies in Norway.

Manage OpenClaw bot configuration - channels, agents, security, and autopilot settings

Comprehensive operational knowledge for ZeroClaw, the fast, small, fully autonomous AI assistant infrastructure built in Rust. Covers CLI, 30 providers, 14 channels, config, hardware, deployment, and security.

Builds a Verifiers (PrimeIntellect) variant of an RL environment. Use whenever someone asks to scaffold a Verifiers env, port to Verifiers, build an in-process toolkit, set up a `vf.ToolEnv` with a Rubric, or wire up a TRL `GRPOTrainer` rollout. Verifiers is the right framework when the user wants in-process tools (no HTTP server), structured tool calling driven by plain Python functions, composable reward rubrics with multiple grader functions, fast iteration with no Docker, or the cleanest ...

Use this skill when the application is slow and you need to find the bottleneck, memory usage is growing over time in the bot daemon, SQLite queries are taking too long, embedding generation needs optimization, or you want to establish performance baselines before and after changes. This covers CPU profiling with py-spy and cProfile, memory profiling with tracemalloc and scalene, SQLite query analysis with EXPLAIN QUERY PLAN, bot daemon memory leak detection, and before/after measurement disc...

Use this skill when reviewing code changes before committing to main — any request to review a diff, audit recent changes, or validate that modifications follow project conventions. This includes blast radius analysis (which modules import the changed code), security scanning (SQL injection in SQLite queries, credential exposure, unsafe eval), test coverage delta with pytest, breaking change detection (DB schema migrations, config key removals, ICOR hierarchy changes), and performance impact ...

Use when measuring and improving import throughput, preview latency, memory usage, and export performance against project SLOs.

Use when implementing or validating RAW decode and color/edit processing order, including non-destructive parameter application and visual regression checks.

Use when preparing builds, versioning, packaging, and release validation for macOS-first desktop delivery, then extending to cross-platform targets.

Use when implementing or debugging wgpu rendering and shader stages for preview or export pipelines, including GPU/CPU parity checks and performance tuning.

Use when the agent needs to claim CHIP tokens and place a bet on an existing basket via vara-wallet. This is the primary agent action. Do not use for basket creation, querying, or claiming payouts.

Use when the agent needs to claim payout from a settled basket via vara-wallet. Do not use before settlement is finalized.

Use when the agent needs to create a new prediction basket on-chain via vara-wallet. Do not use for betting, querying, or settlement.

Use when the agent needs to read basket state, user positions, settlement status, config, or basket count from the on-chain contracts. All queries are free (no gas, no account needed). Do not use for state-changing operations.

Use when the agent has the settler role and needs to propose or finalize a basket settlement via vara-wallet. Do not use without settler role permissions. Do not use for regular user actions.

Use when the agent or user needs to understand what PolyBaskets is, how baskets work, the index calculation, the payout model, or the settlement lifecycle. Do not use when the task is to execute an on-chain action.

Use when an agent needs to interact with PolyBaskets prediction market baskets on Vara Network — create baskets, place bets, query state, claim payouts, or understand the protocol. Do not use for building Sails programs or general Vara development (use vara-skills for that).

Archive completed milestone and prepare for next version

Systematic debugging with persistent state across context resets

Coexistence audit with RankMath SEO — schema-output collision (RankMath's schema is more aggressive than Yoast), meta-tag duplication, title-tag conflicts, sitemap merging, REST endpoint conflicts. Use when the user says "RankMath compat", "RankMath conflict", or coexisting with RM.

WPML compatibility audit — translatable strings via icl_t / wpml_register_string, custom-post-type translation, taxonomy translation, language switcher hooks, current-language detection, sitemap-per-language, and the wpml-config.xml registration file. Use when the user says "WPML compat", "WPML translate strings", "translation plugin", or before customer asks "does this work with WPML?".

Detect flaky Playwright tests — runs each spec N times, flags any that pass-then-fail-then-pass, ranks by flakiness rate, suggests root causes (timing, network, parallelism, state leak). Use when the user says "flaky tests", "intermittent failure", "CI flaky", "test passes locally fails in CI".

Mutation testing for PHP via Infection — measures TEST quality (not code quality). Mutates each line of code (e.g. `<` → `<=`, `&&` → `||`) and runs the test suite. If tests still pass, the mutation "survived" = the test missed the bug. Higher kill rate = better tests. Use when the user says "mutation testing", "Infection PHP", "test quality", "are my tests good".

Migrate web applications from Netlify to CreateOS. Parses netlify.toml, maps build settings, environment variables, redirects, headers, and functions. Use this skill when the user mentions migrating from Netlify, leaving Netlify, moving off Netlify, switching from Netlify, netlify.toml, Netlify alternatives, replacing Netlify, Netlify is too expensive, Netlify downtime, or deploying a Netlify project elsewhere. Do NOT use this skill for brand-new projects that have never been on Netlify — use...

"Deploy apps, manage projects, configure environments, and add domains

Guidelines for adding, updating, auditing, and removing dependencies while preserving lockfile integrity and supply chain safety

This skill should be used when the user asks to "create a character sheet", "build a character reference", "design a consistent character", "generate character angles", "lock character appearance", or mentions character consistency, multi-angle references, or reusable character designs for AI video or image generation.

This skill should be used when the user asks to "generate an AI video prompt", "create a cinematic video prompt", "plan AI video scenes", "build a character sheet for video", "break down a storyboard", "animate an image", "write a video generation prompt", or mentions AI filmmaking, video generation workflows, or character consistency across video clips. Provides structured filmmaking methodology for AI video tools.

Assembles a virtual design team to produce production-quality UI, UX, visual, social media, email, and data output. A Design Manager staffs the right specialists (Product Designer, UX Designer, UI Designer, UX Researcher, Content Designer, Design System Lead, Motion Designer, Creative Director, Social Media Designer, Social Media Strategist, Social Media Copywriter, Growth/Analytics Specialist, Email Designer, Email Copywriter, Data Viz Designer, Dashboard Architect, Presentation Designer, Br...

Assembles a virtual design team to produce production-quality UI, UX, visual, social media, email, and data output. A Design Manager staffs the right specialists (Product Designer, UX Designer, UI Designer, UX Researcher, Content Designer, Design System Lead, Motion Designer, Creative Director, Social Media Designer, Social Media Strategist, Social Media Copywriter, Growth/Analytics Specialist, Email Designer, Email Copywriter, Data Viz Designer, Dashboard Architect, Presentation Designer, Br...

Structured decision-making frameworks for better choices

Actually learn from user feedback and corrections

Auto-sort and organize files

Build habits, track goals, maintain accountability, achieve success

Signal Messenger integration - Send and receive Signal messages. Requires signal-cli or signal-cli-rest-api installed.

Calculates financial business cases for applicable modernization scenarios. Computes per-application and portfolio-level costs, savings, and ROI using scenario finance configurations and complexity-based multipliers. Use when calculating modernization costs, estimating ROI, or building financial justification for transformation initiatives.

Generate and update project documentation under docs/. Uses Mermaid for diagrams. Invoked explicitly when the user requests documentation work.

用于在 VS Code 中对 **Node.js 的 stdio MCP Server** 做断点调试（Attach 到 Node Inspector）。只要用户提到：MCP stdio、@modelcontextprotocol/inspector、node --inspect/--inspect-brk、VS Code attach 调试、断点不命中、sourcemap、调 build/dist 构建产物、端口 9229 冲突/被占用、launch.json 配置等，都要使用本 skill。输出应直接给出可复制粘贴的 launch.json 片段、可运行的 inspector 启动命令（含换端口版本）、以及按优先级排序的排障清单。

Research top-performing Xiaohongshu (小红书 / XHS) image posts, analyze titles/content/comments for patterns and emotional resonance, enrich background via Firecrawl MCP, then write and publish an XHS note via Xiaohongshu MCP. Enforce hard limits: title <= 20 characters, body <= 1000 characters. Use when the user asks for 小红书笔记/种草文案/爆款标题/发布到小红书.

Builds an ad brief for any platform. Researches the user's product, audience, market, and KPIs proactively, then asks the user to confirm and fill gaps. Saves the result as .agents/ad-brief.md for future sessions. Not for writing ad copy, choosing platforms, configuring campaigns, or analyzing results.

Reference for the AdKit CLI (`adkit-cli` on npm, `adkit` command). Maps commands to ad operations: creating campaigns, ad sets, and ads on Meta, managing drafts, uploading media, searching interests. Load when the user wants to execute ad operations through the terminal or when `adkit` is installed and the user is ready to publish. Not for strategy, copywriting, creative advice, or learning about ads.