Automation
Task automation and scripting
iterative-retrieval
by affaan-m
Pattern for progressively refining context retrieval to solve the subagent context problem
amazon-asin-lookup-api-skill
by browser-act
"This skill helps users extract structured product details from Amazon using a specific ASIN (Amazon Standard Identification Number). Use this skill when the user asks to get Amazon product details by ASIN, lookup Amazon product title and price using ASIN, extract Amazon product ratings and reviews count for a specific ASIN, check Amazon product availability and current price, get Amazon product description and features via ASIN, enrich product catalog with Amazon data using ASIN, monitor Amazon product price changes for specific ASINs, retrieve Amazon product brand and material information, fetch Amazon product images and specifications by ASIN, validate Amazon ASIN and get product metadata."
optimizing-attention-flash
by NousResearch
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
strategic-compact
by affaan-m
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
pytorch-lightning
by NousResearch
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
modal-serverless-gpu
by NousResearch
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
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.
huggingface-accelerate
by NousResearch
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
watchers
by NousResearch
Poll RSS, JSON APIs, and GitHub with watermark dedup.
amazon-reviews-api-skill
by browser-act
"This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a competitive product, tracking sentiment of recent Amazon reviews, extracting verified purchase reviews for quality assessment, summarizing user experiences from Amazon product pages, monitoring product performance through customer reviews, collecting reviewer profiles and links for market research, gathering review titles and descriptions for content analysis, scraping Amazon reviews without requiring a login."
google-news-api-skill
by browser-act
"This skill helps users automatically extract structured news data from Google News via BrowserAct API. Agent should proactively apply this skill when users express needs like searching for news about a specific topic, tracking industry trends, monitoring public relations or sentiment, collecting competitor updates, getting latest reports on specific keywords, monitoring brand exposure in media, researching market hot topics, summarizing daily industry news, tracking media activities of specific individuals, retrieving hot events from the past 24 hours, extracting structured data for market research, monitoring global breaking news."
research-paper-writing
by NousResearch
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.
feishu-cli-task
by riba2534
任务管理。当用户请求创建任务、查看任务、完成任务或管理任务时使用。支持创建/查看/更新/删除/完成任务等操作。
handoff
by Chachamaru127
"PMへの完了報告やエージェント間バトンタッチ。スムーズな引き継ぎを実現。Use when user mentions '/handoff', completion report, handoff to Cursor/OpenCode, auto-fix, or reporting to PM. Do NOT load for: casual completion statements, progress chat, informal status updates."
google-maps-api-skill
by browser-act
"This skill helps users automatically scrape business data from Google Maps using the BrowserAct Google Maps API. Agent should proactively trigger this skill for needs like finding restaurants in a specific city, extracting contact info of dental clinics, researching local competitors, collecting addresses of coffee shops, generating lead lists for specific industries, monitoring business ratings and reviews, getting opening hours of local services, finding specialized stores (e.g., Turkish-style restaurants), analyzing business categories in a region, extracting website links from local businesses, gathering phone numbers for sales outreach, mapping out service providers in a specific country."
nature-writing
by Yuan1z0825
Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, results narrative, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose.
nature-citation
by Yuan1z0825
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF.
continue-claude-work
by daymade
Recover actionable context from local .claude session artifacts and continue interrupted work without running claude --resume. This skill should be used when the user provides a Claude session ID, asks to continue prior work from local history, or wants to inspect .claude files before resuming implementation.
apex-class
by forcedotcom
Generate production-ready Apex classes for Salesforce following enterprise best practices. Covers service classes, selectors, domain classes, batch/queueable/schedulable, DTOs, utilities, interfaces, abstract classes, and custom exceptions. Not for triggers or unit tests. Use this skill whenever the user asks to create, write, build, generate, or scaffold any Apex class — including when they describe functionality that would require an Apex class without explicitly saying "Apex class." Trigger on phrases like "build a service for," "create a handler," "I need a class that," "write Apex to," "scaffold a batch job," "create a queueable," or any request involving Salesforce server-side logic. Also use when the user asks to refactor, improve, or restructure existing Apex classes. Even if the request is vague like "I need something that processes Opportunities nightly," use this skill if the solution would involve an Apex class.
handoff
by Chachamaru127
"PMへの完了報告やエージェント間バトンタッチ。スムーズな引き継ぎを実現。Use when user mentions '/handoff', completion report, handoff to Cursor/OpenCode, auto-fix, or reporting to PM. Do NOT load for: casual completion statements, progress chat, informal status updates."
amazon-product-api-skill
by browser-act
"This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to search for products on Amazon, find the best selling brand products, track price changes for items, get a list of categories with high ratings, compare different brand products on Amazon, extract Amazon product data for market research, look for products in a specific language or marketplace, analyze competitor pricing for keywords, find featured products for search terms, get technical specifications like material or color for product lists."
modal-serverless-gpu
by NousResearch
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
skill-prompt-convert
by 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。
writing-plans
by obra
Use when you have a spec or requirements for a multi-step task, before touching code