提示词

tensorrt-llm

davila7

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

gepetto

davila7

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

req-change-workflow

yunshu0909

Standardize requirement/feature changes in an existing codebase (especially Chrome extensions) by turning "改需求/需求变更/调整交互/改功能/重构流程" into a repeatable loop: clarify acceptance criteria, confirm current behavior from code, assess impact/risk, design the new logic, implement with small diffs, run a fixed regression checklist, and update docs/decision log. Use when the user feels the change process is chaotic, when edits tend to sprawl across files, or when changes touch manifest/service worker/OAuth/storage/UI and need reliable verification + rollback planning.

langfuse-integration

a5c-ai

LangFuse LLM observability integration for tracing, analytics, and cost tracking

referral-program

OpenClaudia

Design referral programs and viral growth loops. Use when asked to create referral systems, viral mechanics, word-of-mouth campaigns, or growth loops. Trigger phrases: "referral program", "viral loop", "refer a friend", "word of mouth", "viral coefficient", "referral incentive", "growth loop", "invite system", "ambassador program".

active-interleave

plurigrid

Interleaves context from recently active Claude/Amp threads into current activity via random walk.

openai

vm0-ai

OpenAI API via curl. Use this skill for GPT chat completions, DALL-E image generation, Whisper audio transcription, embeddings, and text-to-speech.

langchain-architecture

HermeticOrmus

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

sglang

davila7

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

drug-photo

ClawBio

Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance

skill-prompt-convert

xstongxue

在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。

autogen-setup

a5c-ai

Microsoft AutoGen multi-agent configuration for conversational AI systems

create-prd

phuryn

"Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use when writing a PRD, documenting product requirements, preparing a feature spec, or reviewing an existing PRD."

ljg-skills

lijigang

claude-code-skill

Enderfga

Control Claude Code via MCP protocol. Execute commands, read/write files, search code, and use all Claude Code tools programmatically with agent team support.

skill-creator

iOfficeAI

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.

octocode-prompt-optimizer

bgauryy

This skill should be used when the user asks to "optimize this prompt", "improve this SKILL.md", "make this prompt more reliable", "fix my agent instructions", "review this AGENTS.md", "strengthen this prompt", "my agent keeps skipping steps", "add enforcement to instructions", or needs to transform weak prompts into reliable, enforceable agent protocols. Uses a 6-step gated flow (with Fast/Full modes), command strengthening, gate injection, and failure mode analysis.

crewai-multi-agent

davila7

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

grid-sticker-generator

guanyang

A universal 4x4 grid sticker generator. uses strict visual guidelines (No Text, Transparent BG) and supports loading theme templates from resources.

khazix-writer

KKKKhazix

数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。

hv-analysis

KKKKhazix

横纵分析法（Horizontal-Vertical Analysis）深度研究Skill。由数字生命卡兹克提出，融合了索绪尔的历时-共时分析、社会科学的纵向-横截面研究设计、商学院案例研究法与竞争战略分析的核心思想。 当用户想要系统性研究一个产品、公司、概念、技术或人物时使用。核心是双轴分析：纵轴追踪从诞生到当下的完整生命历程（以叙事故事呈现），横轴在当下时间截面上与竞品/同类进行系统性横向对比，最后交叉两条轴产出独到洞察。最终产出一份排版精美的PDF研究报告。 触发词包括但不限于：横纵分析、研究一下、帮我分析、深度研究、做个研究、调研一下、竞品分析、帮我看看这个东西怎么样、这个产品/公司/概念是怎么回事、帮我摸清楚、帮我搞懂、帮我做个deep research。 即使用户只是说"帮我了解一下XX"或"XX是什么来头"，只要上下文暗示需要系统性的深度研究（而非简单的概念解释），都应该触发。也适用于用户丢来一个产品名、公司名、技术名词说"帮我研究一下这个"的场景。 不要用于简单的名词解释（用户只是问"XX是什么"）、不要用于公众号写作（那个用khazix-writer）、不要用于纯标题摘要生成（用wechat-title）。

book-cover-design

inference-sh

"Book cover design with genre-specific conventions, typography rules, and AI image generation. Covers fiction and non-fiction genres, sizing, thumbnail testing, and iteration workflows. Use for: self-publishing, ebook covers, print covers, audiobook covers, cover mockups. Triggers: book cover, cover design, ebook cover, book art, novel cover, self publishing cover, kindle cover, audiobook cover, book jacket, cover illustration, fiction cover, nonfiction cover"

python-sdk

inference-sh

"Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python"

plugin-structure

aiskillstore

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.