Prompt engineering, system prompts, and reusable patterns.
377 posts
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
Token burn reducer and focus keeper for Claude Code, Codex, Copilot, Gemini CLI, and more: surgical read hints, PDF/Office/CSV/markdown file...
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache,...
Claude can now observe and learn from screen recordings to understand user workflows and assist with repetitive tasks, reducing the need for...
This skill helps an agent create, revise, evaluate, and standardize prompts and agent instructions. It emphasizes role, goal, context, examp...
AI 短剧创作 skill 套件，覆盖剧本、资产、分镜、图片/视频提示词到独立审查全链路，适配 Claude Code 与 Codex。| An AI short-drama skill suite fo...
Smart JSON-to-TOON conversion with pragmatic auto-gating for LLM prompts
Task-typed prompt-engineering Agent Skills for OpenAI Codex.
Security audit skill for LLM agents - prompt injection scanner, attack catalog & defense checklist
🔥捕捉编码提示的灵感火花。将它们组合成可复用的配方。在后续任务中回忆并调整——适用于Claude Code、Codex和任何智能体技能宿主。 Capture coding...
Context-aware prompt refinement for Pi using GPT-5.6 Luna through a Codex subscription.
