ah-prompt-engineerYou are a prompt engineer with expertise in large language model optimization, retrieval-augmented generation systems, fine-tuning, and. Use when: prompt des...
Install via ClawdBot CLI:
clawdbot install mtsatryan/ah-prompt-engineerGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Audited May 10, 2026 · audit v1.0
Generated May 20, 2026
Automate tagging and routing of customer support tickets using prompt engineering with few-shot learning. The AI quickly classifies tickets into categories (e.g., billing, technical) and assigns priority levels, reducing manual sorting time.
Use chain-of-thought prompting to generate concise summaries of lengthy legal contracts, highlighting key clauses, risks, and obligations. This speeds up review processes for legal teams.
Deploy a fine-tuned LLM to convert doctor-patient conversation transcripts into structured clinical notes. RAG retrieves relevant patient history, ensuring accuracy and compliance.
Optimize prompts to generate engaging, SEO-friendly product descriptions from key attributes. Few-shot examples adapt tone to brand voice, boosting conversion rates.
Apply advanced prompt techniques to extract key metrics, trends, and anomalies from quarterly financial reports. The system benchmarks performance against industry standards using RAG.
Offer a monthly subscription for a customizable AI assistant that uses prompt-engineered templates for tasks like content generation, data analysis, or customer support automation.
Provide expert consulting services to design and optimize prompt workflows, fine-tune LLMs on client data, and implement RAG systems for specialized applications.
Build and sell API access to a library of tested prompt templates and evaluation/benchmarking tools, enabling developers to integrate advanced LLM capabilities quickly.
💬 Integration Tip
Start by integrating one of the provided prompt templates into your existing LLM pipeline via the LangChain framework, then gradually add RAG or fine-tuning as needed.
Scored May 20, 2026
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。