全部能力

Military-grade adversarial analysis that deploys 32 parallel expert agents (engineers, architects, pentesters, interns) to stress-test ideas, strategies, and…

基于配置和需求生成 Next.js 项目，支持 --quick 快速模式跳过 PRD 阶段

safe-file-reader — an installable skill for AI agents, published by cisco-ai-defense/skill-scanner.

Executes optimization hypotheses with keep/discard testing loop. Use when applying validated performance improvements.

MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.

This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated…

ui-to-vue — an installable skill for AI agents, published by affaan-m/everything-claude-code.

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers…

Static code analysis and complexity metrics

Expert skill for integrating cloud AI APIs (Claude, GPT-4, Gemini). Covers secure API key management, prompt injection prevention, rate limiting, cost…

Expert patterns for game economies including currency management (multi-currency, wallet system), shop systems (buy/sell prices, stock limits), dynamic pricing…

Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure. Use…

Dashboard UI patterns with widget composition, real-time data updates, responsive grid layouts, and data tables for React applications. Use when building…

Guide fee disclosure compliance across advisory, brokerage, fund, and retirement plan contexts. Use when the user asks about Form ADV Item 5 fee schedules,…

Route durable graph-building requests into one honest mode: assistant-native install, local Python build, incremental refresh, graph query follow-up, or a graphify-style structural fallback for markdown-heavy corpora. Use when the user wants `GRAPH_REPORT.md`, `graph.json`, `graph.html`, repo/corpus relationship tracing, mixed code+docs+asset graphing, or graph-backed architecture understanding that should persist across sessions. Route simple locate/reference work to `codebase-search`, narrative knowledge-base work to `llm-wiki`, and project-memory handoff to `opencontext`.

Route repo-navigation requests to the right search packet before editing anything. Use when the user needs to find where something lives, who references it, which files own a config/content surface, what must be inspected before a change, or how to narrow a large repo without drifting into debugging or refactoring. Choose one packet: exact-text, symbol/indexed, structural, config/content, hosted search, or graph/path trace. Triggers on: where is this defined, who uses this, find call sites, config ownership, entry point, impact before refactor, shortcode/frontmatter search, scene/asset reference hunt, repo archaeology.

This skill should be used when interacting with the YouMind API to manage content such as boards, crafts, notes, picks, and materials. It provides installation…

Citadel ID integration. Manage data, records, and automate workflows. Use when the user wants to interact with Citadel ID data.

Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.

Manages OrchestKit learning system including feedback status, usage pattern tracking, and privacy/analytics consent. Supports pause/resume learning, data…