发现 Skills

Edit and compose video with Python using MoviePy. Use when a user asks to programmatically edit videos, create video montages, add text overlays, build automated video pipelines, composite multiple clips, apply video effects, generate social media videos from templates, concatenate clips, extract audio, create GIFs, build slideshows, add transitions, resize and crop videos, or integrate video editing into Python applications. Covers MoviePy 2.x for compositing, effects, text, and rendering.

Extract text from scanned PDFs using optical character recognition. Use when a user asks to OCR a PDF, read a scanned document, extract text from an image PDF, digitize a scanned file, convert a scanned PDF to text, or read text from a photograph of a document. Supports multiple languages and handles low-quality scans.

When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro.

Detect and exploit SQL injection with sqlmap. Use when a user asks to test for SQL injection, extract database contents, bypass authentication via SQLi, automate injection testing, or dump database schemas.

Configure and manage status pages for incident communication and service health transparency. Use when a user needs to set up Atlassian Statuspage or open-source alternatives, manage components and incidents, automate status updates, or integrate with monitoring and alerting tools.

Build cross-browser extensions with WXT — the modern framework for Chrome, Firefox, Safari, and Edge extensions. Use when someone asks to "build a browser extension", "Chrome extension with React", "WXT framework", "cross- browser extension", "manifest v3 extension", "build Firefox extension", or "browser extension with TypeScript". Covers content scripts, background workers, popup/options pages, storage, messaging, and publishing.

LaTeX tables with the tabularray package. TRIGGERS - LaTeX table, tabularray, fixed-width columns, table alignment.

Core Cloudera AI guidance for project setup, app runtime conventions, and secure defaults. Invoke before Cloudera AI app or Agent Studio implementation.

Discover all installed plugins, skills, and commands available in this environment

Code Quality Tools. Use when setting up quality tools or CI.

Expert blueprint for sports games (FIFA, NBA 2K, Rocket League, Tony Hawk) covering physics-based ball interaction, team AI formations, contextual input, and broadcast camera systems. Use when building soccer, basketball, hockey, racing sports, or arcade sports games. Keywords: ball physics, Magnus effect, formation AI, team tactics, contextual controls, steering behaviors.

Expert blueprint for inventory systems (Diablo, Resident Evil, Minecraft) covering slot-based containers, stacking logic, weight limits, equipment systems, and drag-drop UI. Use when building RPG inventories, survival item management, or loot systems. Keywords: inventory, slot, stack, equipment, crafting, item, Resource, drag-drop.

Extracts actionable tasks from emails and prioritizes them using the Eisenhower Matrix. Use this skill whenever the user wants to triage emails, extract tasks, create priority lists, or generate daily briefs.

BDD orchestrator for feature-level work. Use when the user says 'add', 'implement', 'build', 'feature', 'iteration', 'story', 'phase', 'resume', 'continue', or references a ticket/iteration/story. Also use when work touches 3+ files with new state/flows, or when the user runs /bdd. Do NOT use for bug fixes, typos, config changes, or small (1–2 file) tasks.

Use next/dynamic for lazy-loading heavy components. Apply when importing large components like editors, charts, or rich text editors that aren't needed on initial render.

Guide for creating and enhancing skills. Use when users want to create a new skill, update/improve an existing skill, or audit skill quality. Supports both creation from scratch and enhancement of existing skills with audit rubric scoring.

RSpec testing patterns, factories, mocks, and test best practices

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Comprehensive, measurement-driven performance optimization for latency, throughput, memory/GC, and tail behavior. Use when the user asks to optimize/speed up, reduce latency (p95/p99), increase throughput/QPS, lower CPU/memory/allocations/GC pauses, profile hot paths, or run a benchmarked perf pass (including JSONL/query-heavy code). Requires before/after measurement on a runnable workload (or an explicit `UNMEASURED` plan) plus a correctness gate. Zig-only CLI iteration where `bench_stats`/`perf_report` are proven before shipping.

Execute the next pending task from a planned PRD implementation session. Reads memory for context continuity, implements the task, updates status and memory. Requires a session ID.

公众号爆款标题生成器。基于12大爆款模型批量生成高点击率标题，一次输出10个标题（5单模型+5混合模型）。触发词：爆款标题、微信标题、标题优化。

Build, debug, and optimize RealityKit scenes for visionOS, including entity/component setup, rendering, animation, physics, audio, input, attachments, and custom systems. Use when implementing RealityKit features or troubleshooting ECS behavior on visionOS.

Guide for modifying USD ASCII (.usda) files, including prims, properties, composition arcs, variants, and transforms. Use when editing or reviewing .usda files by hand.

Natural language search through Claude Code session history. Search for previous prompts, conversations, topics, file modifications, and context from past sessions. Useful for finding earlier work and understanding project continuity.