Develop with Superpowers

The global registry for Agent Skills. Ship standardized SKILL.md packages to your AI agents in seconds.

480Total Skills
11.5kWeekly Downloads
10.8kContributors
quran
skill-creator
quran5d ago

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.

1.7k
apici-cd
zechenzhangAGI
long-context
zechenzhangAGI1w ago

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient...

1.7k
ci-cdgithub

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or pe...

1.7k
apigithub
zechenzhangAGI
ml-paper-writing
zechenzhangAGI1w ago

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guideli...

1.7k
apici-cd
zechenzhangAGI
tensorrt-llm
zechenzhangAGI1w ago

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),...

1.7k
apici-cd
max-sixty
writing-user-outputs
max-sixty6d ago

CLI output formatting standards for worktrunk. Use when writing user-facing messages, error handling, progress output, hints, warnings, or working with the output system.

1.6k
apici-cd
revokslab
writing-plans
revokslab1w ago

Use when you have a spec or requirements for a multi-step task, before touching code

1.6k
llmtesting
HarleyCoops
math-to-manim
HarleyCoops6d ago

This skill should be used when the user asks to "create a math animation", "animate a mathematical concept", "generate Manim code", "visualize [topic] with animation", "explain [concept] visually", "create an educational video", "build a Manim scene"...

1.6k
ci-cdgithub-actions
mikeyobrien
pr-demo
mikeyobrien6d ago

Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

1.5k
apigithub
dvdsgl
canvas
dvdsgl3w ago

**The primary skill for terminal TUI components.** Covers spawning, controlling, and interacting with terminal canvases. Use when displaying calendars, documents, or flight bookings.

1.4k
apici-cd
glittercowboy
create-mcp-servers
glittercowboy1w ago

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript ...

1.2k
apici-cd
catlog22
ccw-help
catlog226d ago

CCW command help system. Search, browse, recommend commands. Triggers "ccw-help", "ccw-issue".

1.2k
ci-cdgithub-actions
feiskyer
deep-research
feiskyer6d ago

深度调研的多Agent编排工作流:把一个调研目标拆成可并行子目标,用 Claude Code 非交互模式(`claude -p`)运行子进程;联网与采集优先使用已安装的 skills,其次使用 MCP 工具;用脚本聚合子结果并分章精修,最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于:系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合,或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场...

1.2k
apillm
XiaoMi
lark-doc
XiaoMi2w ago

Fetch Lark/Feishu document and convert to Markdown. Use this skill to get troubleshooting guides and operation instructions from Lark documents.

1.2k
llmsecurity
crowi
crowi-migration
crowi1w ago

Crowi 2.0 移行ワークフロー。Express/Swig から Next.js + ts-rest への移行時に自動適用。 キーワード: migrate, 移行, Express, Swig, legacy, 旧実装

1.1k
apillm
jeremylongshore
langfuse-sdk-patterns
jeremylongshore6d ago

Langfuse SDK best practices, patterns, and idiomatic usage. Use when learning Langfuse SDK patterns, implementing proper tracing, or following best practices for LLM observability. Trigger with phrases like "langfuse patterns", "langfuse best practic...

1.1k
apigithub-actions
jeremylongshore
splitting-datasets
jeremylongshore6d ago

Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.

1.1k
github-actionsllm
jeremylongshore
langchain-hello-world
jeremylongshore6d ago

Create a minimal working LangChain example. Use when starting a new LangChain integration, testing your setup, or learning basic LangChain patterns with chains and prompts. Trigger with phrases like "langchain hello world", "langchain example", "lang...

1.1k
apigithub-actions
jeremylongshore
optimizing-prompts
jeremylongshore6d ago

Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more ...

1.1k
llmprompting
jeremylongshore
analyzing-text-sentiment
jeremylongshore6d ago

Execute this skill enables AI assistant to analyze the sentiment of text data. it identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral. use this skill when a user requests sentiment analysis, opinion minin...

1.1k
llmobservability

Showing 141 to 160 of 480 results

Command Palette

Search for a command to run...