Prompts
Prompt engineering and templates
huashu-article-to-x
by alchaincyf
长文精简为X平台内容（200-500字），保留核心观点和个人风格。当用户提到"转微博"、"发小红书"、"社交媒体"、"缩短文章"时使用。
huashu-script-polish
by alchaincyf
视频脚本口语化审校，去书面腔让脚本适合说出来。当用户提到"口语化"、"太书面了"、"像说话一样"、"脚本审校"时使用。
huashu-speech-coach
by alchaincyf
演讲与分享教练。基于Patrick Winston（MIT AI教授）的How to Speak方法论，帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。
huashu-slides
by alchaincyf
从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
huashu-xhs-image
by alchaincyf
为小红书笔记生成高质量配图。默认AI生成（Gemini），仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。
huashu-proofreading
by alchaincyf
三遍审校降低AI检测率，让文章更有人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"审校"、"自然一些"时使用。
huashu-material-search
by alchaincyf
搜索个人素材库1800+条真实经历和观点，为内容增加人味。当用户提到"个人经历"、"真实案例"、"素材"、"人味"时使用。
cortex
by jeremylongshore
ML/AI engineer — LLM integrations, prompt engineering, model pipelines, evals, RAG.
cortex-prompt
by jeremylongshore
Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".
cortex-integrate
by jeremylongshore
Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost estimate. Use when asked to "add AI to this", "LLM integration", "add Claude/GPT", or "AI-powered feature".
humanizer-ru
by Vladimir-Human
"Use when: нужно очеловечить (humanize) сгенерированный ИИ текст на русском. Убирает 25 машинных паттернов, делает язык живым и естественным."
skill-creator
by bytedance
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
update-llm-model-list
by Agenta-AI
Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones, or verifying the list is correct.
prompt-analyze
by microsoft
'Compatibility alias for read-only prompt artifact review. Routes static and behavior analysis to hve-builder review mode.'
prompt-builder
by microsoft
'Compatibility alias for legacy prompt-building requests. Routes creation and improvement to the hve-builder skill.'
hve-builder-tester
by microsoft
'Test HVE artifact behavior with black-box scenarios, contained simulation or approved native execution, independent grading, and evidence reports.'
owasp-llm
by microsoft
OWASP Top 10 for LLM Applications (2025) knowledge base for identifying, assessing, and remediating large language model security risks.
guardrails-ai-setup
by a5c-ai
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
confluence-expert
by alirezarezvani
Atlassian Confluence expert for creating and managing spaces, knowledge bases, documentation, planning, product discovery, page layouts, macros, templates, and all Confluence features. Use for documentation strategy, space architecture, content organization, and collaborative knowledge management.
engineering-skills
by alirezarezvani
"23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only)."
atlassian-templates
by alirezarezvani
Atlassian Template and Files Creator/Modifier expert for creating, modifying, and managing Jira and Confluence templates, blueprints, custom layouts, reusable components, and standardized content structures. Use for building org-wide templates, custom blueprints, page layouts, and automated content generation.
context-engine
by alirezarezvani
"Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls."
senior-ml-engineer
by alirezarezvani
ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization.
senior-prompt-engineer
by alirezarezvani
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.