发现 Skills

Generate SLURM `sbatch` job scripts and sanity-check HPC resource requests (nodes, tasks, CPUs, memory, GPUs) for simulation runs. Use when preparing submission scripts, deciding MPI vs MPI+OpenMP layouts, standardizing `#SBATCH` directives, or debugging job launch configuration (`sbatch`/`srun`).

Redesign mobile app UI to feel unmistakably Apple-like, iOS-forward, and native. Use this skill when building iOS apps, applying Apple Human Interface Guidelines, or creating native-feeling mobile interfaces with SF Pro typography, translucency, and system-like components.

Expert developer skill for implementing real-time voice and video interactions using the Google Gemini Live API. This skill should be used when implementing bidirectional audio streaming, voice conversations with interruption handling, real-time transcription, function calling in live sessions, session management, or voice customization.

ALWAYS activate this skill before implementing EVERY feature, plan, or fix.

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

Multi-level caching, invalidation patterns, and stampede protection.

Fetch API, Caching, and Revalidation strategies.

Simple and powerful reactive state management using GetX. Use when managing reactive state with GetX controllers or observables in Flutter.

Expert standards for session drivers, security headers, and middleware logic.

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

Configure Renovate Bot for automated dependency updates. Keep packages secure and up-to-date with customizable rules, grouping, and scheduling. Use for dependency management, security updates, or automated maintenance. Triggers on renovate, dependabot, dependency updates, package updates.

Hugging Face hf CLI: search, download, and upload models and datasets.

Encapsulate the plugin's built-in dataRenderer (custom UI) into a standard public widget so it can be reused by other plugins or features. Core features: (1) extract the UI logic of dataRenderer into standalone component files, (2) register the new components in common_widgets.dart, (3) add data provider functions in _provideCommonWidgets, (4) remove the old built-in renderer code.

Security pattern for implementing rate limiting and throttling. Use when protecting against brute-force attacks, DoS/DDoS mitigation, preventing resource exhaustion, or limiting API abuse. Addresses "Entity absorbs excessive resources" problem.

Data quality validation rules, quality metrics, and acceptance criteria for Somali dialect classifier datasets. Covers duplicate detection, language filtering, quality scoring, and validation protocols. Auto-invokes when discussing data quality, validation, cleaning, or quality guardrails for this project.

AI voice generation, text-to-speech, and voice synthesis via the inference.sh CLI. Models: Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, and conversational output. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility/IVR prompts, and rapid prototyping. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs alternative, natural voice, realistic speech, voice ai

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 139 proven marketing approaches organized by category.

AWS Step Functions workflow orchestration with state machines. Use when designing workflows, implementing error handling, configuring parallel execution, integrating with AWS services, or debugging executions.

· Hunt for novel vulnerabilities in source code, binaries, or live systems - reverse engineering, patch diffing, fuzzing, attack surface mapping, PoC development, and responsible disclosure. Triggers: 'zero-day', '0-day', 'vulnerability research', 'variant analysis', 'patch diffing', 'fuzz', 'exploit dev', 'CVE', 'PoC', 'reverse engineering'. Not for SAST scanning (use security-audit), post-exploitation (use lockpick), or code correctness (use code-review).

Use when you need to design, review, or improve REST APIs with Spring Boot — including HTTP methods, resource URIs, status codes, DTOs, versioning, deprecation and sunset headers, content negotiation (JSON and vendor media types), ISO-8601 instants in DTOs, pagination/sorting/filtering, Bean Validation at the boundary, idempotency, ETag concurrency, HTTP caching, error handling, security, contract-first OpenAPI (OpenAPI Generator), controller advice, and problem details for errors. This should trigger for requests such as Review Java code for Spring Boot REST API; Apply best practices for Spring Boot REST API in Java code. Part of cursor-rules-java project

Reviews a test suite for meaningful assertions, coverage, and overall quality. Run after code reviews to validate that tests are significant and effective.

Assess and refactor oversized or multi-domain skills. First determines whether splitting or references/ extraction is appropriate — then executes the correct action. Use when a skill exceeds token thresholds (SK006/SK007) or covers multiple independent domains. Performs candidate assessment before any structural changes; cohesive single-intent skills are redirected to references/ extraction instead of splitting. When splitting is warranted — domain analysis gate, split plan, new SKILL.md generation, validation, and backwards-compatible facade conversion.

Install and configure Firebase Extensions for common tasks — Stripe payments, Algolia search, image resizing, and translation services. Trigger: "firebase extension", "stripe extension", "algolia extension", "resize images"