发现 Skills

Review Flutter/Dart code for security vulnerabilities: secure storage, network hardening, log redaction, and data protection

GoRouter guard patterns, deep links, redirect safety, tab preservation, and restoration best practices

Use when building NestJS services that need strong module boundaries, dependency injection, DTO validation, guards or interceptors, auth boundaries, transport-aware module design, and production-safe TypeScript backend structure.

Compatibility alias skill. Deprecated: use react-best-practices.

Use this when writing or updating OpenAPI specifications, defining request/response schemas, or configuring the Stoplight Elements (Swagger-style) documentation UI.

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Parse, analyze, and process SARIF (Static Analysis Results Interchange Format) files. Use when reading security scan results, aggregating findings from multiple tools, deduplicating alerts, extracting specific vulnerabilities, or integrating SARIF data into CI/CD pipelines.

Use when the task is specifically SQLite or libSQL/Turso-style SQLite: local-first schema design, WAL/concurrency tradeoffs, embedded deployments, and lightweight migration strategy.

Use for Tailwind CSS v4 architecture, CSS-first theme setup, utility composition, container-query usage, design-token hygiene, and dark-mode strategy.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Canonical Vercel AI skill covering AI Gateway and AI SDK integration, routing, resilience, and observability.

Orchestrates end-to-end interview preparation for senior ML/AI engineers targeting Anthropic and peer companies. Use for prep timeline generation, story coherence across rounds, mock scheduling, and debrief analysis. Activate on "interview prep", "interview loop", "Anthropic interview", "prep timeline". NOT for resume writing, career narratives, or individual round-type practice.

Designs and orchestrates a realistic interview simulation platform with voice AI, whiteboard evaluation, gaze-tracking proctoring, and mobile spaced repetition. Use for building mock interview infrastructure, configuring sessions, and adaptive difficulty. Activate on "interview simulator", "mock interview", "practice session", "voice mock". NOT for individual round-type coaching, resume writing, or prep timeline coordination.

name: websocket-streaming license: Apache-2.0 description: Implements real-time bidirectional communication between DAG execution engines and visualization dashboards via WebSocket. Covers connecti...

Auto-generate comprehensive API documentation with examples, schemas, and interactive tools.

Comprehensive Godot 4 C# game development skill with Test-Driven Development (TDD) using GdUnit4/xUnit/NUnit, Behavior-Driven Development (BDD) with Reqnroll and Gherkin feature files, SOLID principles, design patterns (State Machine, Component/Entity-Component, Observer, Command), and Godot C# API best practices. Use this skill when building Godot games with C# to produce maintainable, testable, and robust projects.

Control a vehicle using natural language. Use this skill when the user wants to warm up or cool down the car, lock or unlock doors, start or stop the engine, check battery, fuel, location or status, or manage charging. It translates phrases like "warm up the car" into precise mcs CLI commands.

Run deployed PyGPUBench candidate/final benchmark mode for a kernel with a standardized artifact that includes repo git hash, kernel diff, command output, and JSON result, then append Codex analysis.

Query Cylera devices by attribute label and export results to CSV. Optionally filter by a last-seen window. Use when the user wants to find devices with a specific attribute (e.g., 'TeamViewer', 'remote access', 'end of life'), optionally seen in the last N days or last week.

Guides advanced persistent threat (APT) analysis—nation-state and sophisticated criminal campaigns, long-dwell intrusions, campaign lifecycle tracking, MITRE ATT&CK TTP mapping, infrastructure and malware correlation, attribution with explicit confidence levels, intel fusion for hunts and IR, detection-engineering handoffs, and executive strategic briefings. Use for APT, advanced persistent threat, nation-state threat, state-sponsored campaign, long-dwell intrusion, APT attribution, campaign tracking, APT infrastructure, strategic threat briefing, sophisticated intrusion analysis—not routine SOC alert triage (soc-analyst), generic proactive hunt playbooks only (threat-hunter), CTI feed and source management only (cti-analyst), incident command (incident-responder), penetration testing (penetration-tester), or AI/LLM red team (ai-redteam).

Automatically save and restore development context to minimize cognitive load when resuming work. Use when switching tasks, taking breaks, or returning after interruptions. Captures mental state, file locations, and next steps. Designed for ADHD developers with high context-switching costs.

Wraps any prompt with a reminder to respect CLAUDE.md files

This skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system.

Inspects and refines AI-generated texts (articles, blog posts, codelabs, READMEs) to remove or rewrite typical "AI slop" language, ensuring a human, authentic, and professional tone. Use when asked to review an article, improve wording, or make a text better.