Prompts
Prompt engineering and templates
boost-modules
by av
Create custom modules for Harbor Boost, an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
claude-reflect
by jeremylongshore
Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".
skill-creator
by Project-N-E-K-O
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.
prompt-lab
by Mathews-Tom
'LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.'
to-markdown
by Mathews-Tom
'Convert any file or URL to clean Markdown: PDF, DOCX, XLSX, PPTX, HTML, images (OCR), audio, CSV, YouTube. Optimised for LLM pipelines. Triggers on: "convert to markdown", "extract text from PDF", "parse this document", "ingest for RAG".'
my-skill
by LukeRenton
What this skill does and when to use it. Claude reads this to decide relevance. Include keywords users would naturally say.
Agent Repo Init Skill
by study8677
For full mode, review .context/agent_runtime_profile.md after generation.
add-model-price
by langfuse
Add new LLM model pricing entries to Langfuse's default-model-prices.json. Use when adding model prices, updating model pricing, creating model entries, adding Claude/OpenAI/Anthropic/Google/Gemini/AWS Bedrock/Azure/Vertex AI model pricing, working with matchPattern regex, pricingTiers, or model cost configuration. Covers model price JSON structure, regex patterns for multi-provider matching, tiered pricing with conditions, cache pricing, and validation rules.
image-generation
by jjyaoao
Implement AI image generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to create images from text descriptions, generate visual content, create artwork, design assets, or build applications with AI-powered image creation. Supports multiple image sizes and returns base64 encoded images. Also includes CLI tool for quick image generation.
Podcast Generate
by jjyaoao
Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).
video-understand
by jjyaoao
Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.
videocut:自进化
by Ceeon
自进化 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill
developing-with-ai-sdk
by laravel
Builds AI agents, generates text and chat responses, produces images, synthesizes audio, transcribes speech, generates vector embeddings, reranks documents, and manages files and vector stores using the Laravel AI SDK (laravel/ai). Supports structured output, streaming, tools, conversation memory, middleware, queueing, broadcasting, and provider failover. Use when building, editing, updating, debugging, or testing any AI functionality, including agents, LLMs, chatbots, text generation, image generation, audio, transcription, embeddings, RAG, similarity search, vector stores, prompting, structured output, or any AI provider (OpenAI, Anthropic, Gemini, Cohere, Groq, xAI, ElevenLabs, Jina, OpenRouter).
phoenix-cli
by Arize-ai
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, review experiments, inspect datasets, and query the GraphQL API. Use when debugging AI/LLM applications, analyzing trace data, working with Phoenix observability, or investigating LLM performance issues.
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".
geo-optimization
by fabricioctelles
This skill should be used when the user wants to improve content visibility in AI-generated responses (ChatGPT, Perplexity, Google AI Overview, Grok, Claude, Gemini), needs a GEO/AEO strategy, wants to measure citation rate, align terminology for LLMs, audit existing pages for AI discoverability, or create optimized pages such as roundups and FAQs.
wewrite
by wengzige
微信公众号内容全流程助手：热点抓取 → 选题 → 框架 → 写作 → SEO/去AI痕迹 → 视觉AI → 排版推送草稿箱。 触发关键词：公众号、推文、微信文章、微信推文、草稿箱、微信排版、选题、热搜、 热点抓取、封面图、配图、写公众号、写一篇、主题画廊、排版主题、容器语法。 也覆盖：markdown 转微信格式、学习用户改稿风格、文章数据复盘、风格设置、 主题预览/切换、:::dialogue/:::timeline/:::callout 容器语法。 不应被通用的"写文章"、blog、邮件、PPT、抖音/短视频、网站 SEO 触发—— 需要有公众号/微信等明确上下文。
wewrite
by wengzige
微信公众号内容全流程助手：热点抓取 → 选题 → 框架 → 写作 → SEO/去AI痕迹 → 视觉AI → 排版推送草稿箱。 触发关键词：公众号、推文、微信文章、微信推文、草稿箱、微信排版、选题、热搜、 热点抓取、封面图、配图、写公众号、写一篇、主题画廊、排版主题、容器语法。 也覆盖：markdown 转微信格式、学习用户改稿风格、文章数据复盘、风格设置、 主题预览/切换、:::dialogue/:::timeline/:::callout 容器语法。 不应被通用的"写文章"、blog、邮件、PPT、抖音/短视频、网站 SEO 触发—— 需要有公众号/微信等明确上下文。
gguf-quantization
by NousResearch
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
guidance
by NousResearch
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
dspy
by NousResearch
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
claude-code
by NousResearch
Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.
axolotl
by NousResearch
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
peft-fine-tuning
by NousResearch
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.