浏览 NeverSight 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
149收录技能的仓库 Stars 合计
9,834仓库 Forks
2,831平均每个技能的仓库 Stars
66同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Guide for Windows kernel security research including driver development, system callbacks, security features, and kernel exploitation. Use this skill when working with Windows drivers, PatchGuard, DSE, or kerne...
CRITICAL: Use for unsafe Rust code review and FFI. Triggers on: unsafe, raw pointer, FFI, extern, transmute, *mut, *const, union, #[repr(C)], libc, std::ffi, MaybeUninit, NonNull, SAFETY comment, soundness, und...
Add Temps analytics to React applications with comprehensive tracking capabilities including page views, custom events, scroll tracking, engagement monitoring, session recording, and Web Vitals performance metr...
Explore and analyze TUI applications to document their features for cloning. Use when asked to reverse-engineer, analyze, document, or understand a terminal UI like Claude Code, OpenCode, Codex, lazygit, or any...
Critically review terminal user interfaces for UX quality, responsiveness, visual design, and interactivity. Use when asked to "review my TUI", "test my TUI UX", "audit my terminal UI", "check TUI responsivenes...
GitLab search operations via API. ALWAYS use this skill when user wants to: (1) search across GitLab globally, (2) find issues/MRs/code/commits, (3) search within a group or project, (4) find users or projects...
GitLab vulnerability operations via API. ALWAYS use this skill when user wants to: (1) list security vulnerabilities, (2) view vulnerability details, (3) confirm/dismiss/resolve vulnerabilities, (4) view vulner...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Checks a GitHub pull request for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and o...
Teaches LLM agents how to create effective Griffin API monitors for endpoints in a codebase. Use when the user wants to add or design API monitors, health checks, or scheduled endpoint tests; when evaluating wh...
Expert guidance for systematic bug hunting, root-cause analysis, and regression testing. Use this skill when the user reports a bug, unexpected behavior, or when you need to troubleshoot complex issues in the c...
Analyzes a project's codebase to generate a comprehensive summary including tech stack, features, and REST services, outputting the result to PROJECT_SUMMARY.md. This skill has assets directory that MUST be use...
Expert guidance for explaining project features. Use this skill when you need to provide a comprehensive explanation of how a specific feature works, including summaries, deep dives, usage examples, and sequenc...
This skill should be used when the user says "save checkpoint", "checkpoint", "continue", "resume", "resume work", "save my progress", "clear checkpoint", or "clear all checkpoints". Saves and resumes named ses...
Review or refactor React / Next.js code for performance and reliability using a prioritized rule library (waterfalls, bundle size, server/client data fetching, re-renders, rendering). Use when writing React com...
Production incident response procedures for Python/React applications. Use when responding to production outages, investigating error spikes, diagnosing performance degradation, or conducting post-mortems. Cove...
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss...
（中文）Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Centralizes persona-driven code reviews (Fowler, Torvalds, Carmack, React core, etc.) so Claude can pick or combine expert viewpoints when the user asks for a code review or perspective-specific critique.
Create effective debugging prompts—include error messages, stack traces, expected vs actual behavior, logs, and attempted solutions
Comprehensive Bun runtime expertise covering all major features. Use when working with Bun projects, migrating from Node.js, or leveraging Bun-specific APIs. Activates for: Bun.serve, Bun.file, bun:test, bun:sq...
Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag healt...
Coverage Gaps audit worker (L3). Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justifi...
PROACTIVELY analyze completed Beads issues to identify patterns, tech debt, and gaps. Suggests new OpenSpec proposals based on discovered work. Use after closing issues or when user asks "what should we work on...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。