发现 testing security llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Convert MCP servers to Claude Code skills with progressive disclosure. Use when creating a skill from an MCP server, updating an existing MCP skill, or converting MCP documentation to skill format. Accepts MCP...
Hierarchical memory architecture combining short-term, long-term, and episodic memory layers. Based on Mem0 research showing 26% accuracy improvement. Use for persistent knowledge, context management, and RAG o...
情報収集担当エージェント「Gemini」を起動します。中級者のリサーチエージェントとして、WEB検索・外部ドキュメント調査・API情報収集を担当します。
Deep research synthesis with audio overview generation
Use Databuddy LLM observability for Vercel AI SDK. Use when implementing LLM analytics, tracking AI model usage, monitoring token costs, or observing AI application performance.
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities...
Generates three distinct expert challenger personas for multi-perspective debate. Each persona critiques from a different angle.
Structured repository scanning and agent evaluation skill for discovering agents from the AI ecosystem
Prime Intellect GPU cloud API reference. Use when working with Prime Intellect pods, GPUs, clusters, disks, SSH keys, inference, or any PI compute resources.
Automate Google NotebookLM - create notebooks, add sources, generate podcasts/videos/quizzes, download artifacts. Activates on explicit /notebooklm or intent like "create a podcast about X"
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, prog...
Integrate Scorable LLM-as-a-Judge evaluators into applications with LLM interactions. Use when users want to add evaluation, guardrails, or quality monitoring to their LLM-powered applications. Also use when us...
Enforces Visual Communication Standards. Use this skill when explaining complex logic, architectures, workflows, or when the user asks for diagrams.
Produce natural, high-quality human-like text. Avoids common AI markers (repetitive patterns, fluff words, false neutrality) in favor of specificity, directness, and genuine voice. Use this skill when the user...
Guide for adding AI presenter avatars to demos using HeyGen. Use when you want to make demos look like they were recorded by a human presenter (Loom-style).
Convert academic research papers into engaging, SEO-optimized blog posts. Use when asked to (1) create a blog post from a research paper/preprint, (2) summarize research for general audiences, (3) promote publi...
Use this skill when advising on post structure, timing, media selection, and account health to align with the HeavyRanker's scoring weights and anti-spam heuristics.
Generate optimized prompts for AI image and video generation. Triggers on "generate a prompt for", "write me a prompt", "create an image prompt", "create a video prompt", "optimize this prompt".
Write documents in a natural, human style. Use when writing essays, papers, documentation, reports, articles, or any prose content. Avoids common AI writing patterns.
Use when transcribing audio/video to text with timestamps, speaker labels, and chapters. Supports YouTube URLs and local files. Produces structured markdown output.
This skill should be used when needs to search for unknown information, verify understanding, or avoid hallucination. or when detects knowledge gaps during task execution. Also trigger when the user asks to "se...
Review AI output critically before accepting it. Use when the user invokes /verify or wants to check AI-generated content for errors, assumptions, and claims requiring validation.
Adversarial fact-checking and verification of LLM output against uploaded attachments using DeepCitation. Use when you need to verify claims, find contradictions, or perform devil's advocate analysis on AI-gene...
Use this skill to decode the "DNA" of the recommendation engine. These signals are the foundational data structures used to retrieve candidates (before ranking) and as features for the Heavy Ranker (during rank...
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。