Loading...
Loading...
Found 219 Skills
P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.
Prompting techniques for AI image generation and editing models on Replicate. Use when writing prompts for image models or building image generation features.
Compress LLM responses to pure signal — Rocky's early notation style. Drop articles, filler, hedging. Best for pipelines and coding.
Analyze and optimize system prompts using a structured prompting guidelines framework — AI-powered analysis and rewriting. Use when a prompt needs improvement, experiment results show quality gaps, or you want a structured review of an existing system prompt. Do NOT use when production traces show failures (use analyze-trace-failures first to identify patterns). Do NOT use to build evaluators (use build-evaluator).
Generate aesthetics-prioritized image generation prompts tailored for the Chinese manhua drama market. It supports various genres including xianxia, wuxia, ancient Chinese style, urban fantasy, urban romance, hot-blooded combat, post-apocalyptic wasteland, mystery & detective, and campus youth, paired with painting styles like ink wash painting, gongbi painting, cel-shading, impasto, watercolor, semi-realism, and flat illustration. Triggered when users need to create beautiful manhua drama image prompts, descriptions of Chinese manhua characters/scenes/objects, or mention keywords such as "manhua drama", "Chinese manhua", "generate character", "xianxia scene", "ancient-style character", "urban manhua", "draw one".
Invokes Codex CLI as a second opinion. Use for reviewing plans, code, architectural decisions, or getting an independent perspective from OpenAI's reasoning models.
Generate images using FAL.ai nanobanana pro. Use when creating product shots, social graphics, brand assets, or any visual content. Integrates with automation system for direct asset generation in Claude Code.
Measure and improve how well your AI works. Use when AI gives wrong answers, accuracy is bad, responses are unreliable, you need to test AI quality, evaluate your AI, write metrics, benchmark performance, optimize prompts, improve results, or systematically make your AI better. Covers DSPy evaluation, metrics, and optimization.
Provides a prompt template and best practices for building Claude Code agent teams. Covers team composition, teammate spawn prompts, task breakdown, file ownership, communication protocols, and delegate mode. Use when creating an agent team, spawning teammates, parallelizing work across multiple Claude Code instances, or deciding whether an agent team is the right approach.
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.
AI image generation and editing capabilities, implemented based on Nano Banana (Gemini Image) to support text-to-image, image-to-image, and image editing. Suitable for scenarios such as creative design, marketing materials, social media content, and presentation illustrations. Supports multiple styles, high-resolution output (up to 4K), text rendering, and character consistency preservation.
Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts. Covers token efficiency, compliance techniques, and discovery optimization.