Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
29,261
总 Skills
226.3M
总安装量
2,813
贡献者
# Skill 仓库 描述 安装量
8951 problem-definition refoundai/lenny-skills
Problem Definition Help the user define problems clearly before jumping to solutions using frameworks from 91 product leaders. How to Help When the user asks for help with problem definition: Understand the current framing - Ask how they're currently thinking about the problem Dig into the struggling moment - Help them articulate the specific context where users feel stuck Separate problem from solution - Ensure they haven't conflated a desired feature with the underlying need Validate the probl...
 1.8K
8952 usability-testing refoundai/lenny-skills
Usability Testing Help the user conduct effective usability testing using frameworks and insights from 11 product leaders. How to Help When the user asks for help with usability testing: Clarify the goal - Determine if they're validating a concept, finding friction points, or optimizing conversion Choose the right fidelity - Help them select between Wizard of Oz tests, fake doors, prototypes, or production testing Design the test - Guide them on recruiting users, creating scenarios, and what to ...
 1.8K
8953 baidu-search countbot-ai/countbot
百度 AI 搜索 基于百度千帆平台的 AI 搜索服务，支持多种搜索模式。 配置 编辑 skills/baidu-search/scripts/config.json ，填写 API Key： { "api_key" : "bce-v3/YOUR_API_KEY_HERE" } API Key 从 百度千帆平台 获取。 命令行调用 网页搜索（默认） python3 skills/baidu-search/scripts/search.py "搜索关键词" JSON 输出（推荐 AI 使用） python3 skills/baidu-search/scripts/search.py "人工智能最新进展" --json 限制结果数 python3 skills/baidu-search/scripts/search.py "Python教程" --limit 5 站点过滤 python3 skills/baidu-search/scripts/search.py "天气预报" --sites weather.com.cn 时间过滤（week/month/semiyear/year）...
 1.8K
8954 indesign sfkislev/flue
This skill lets a coding agent operate Adobe InDesign on the desktop through Flue , a local shell-to-application bridge. The agent pipes ExtendScript into indesign_bridge.py and gets structured JSON back. agent shell -> indesign_bridge.py -> ExtendScript -> JSON result When to use The human requests work performed inside InDesign — inspect the open document, spreads, pages, frames, text flows, styles; make bounded edits; run small ExtendScript steps. A CLI agent cannot act inside InDesign withou...
 1.8K
8955 conducting-user-interviews refoundai/lenny-skills
Conducting User Interviews Help the user run better discovery conversations and extract real insights using techniques from 43 product leaders. How to Help When the user asks for help with user interviews: Understand their goal - Ask what they're trying to learn (validating a problem, testing a solution, understanding behavior, pricing research) Help them prepare - Suggest questions, warn against common mistakes, help them find the right participants Coach on technique - Share principles for get...
 1.8K
8956 writing-specs-designs refoundai/lenny-skills
Writing Specs & Designs Help the user write effective specs and design documents using frameworks and insights from 7 product leaders. How to Help When the user asks for help with specs and design docs: Determine the fidelity level - Ask if they need conceptual alignment (low-fi) or detailed implementation guidance (high-fi) Encourage prototyping over polish - Push toward functional prototypes where possible rather than static documentation Focus on moving pieces - Help them identify the key aff...
 1.8K
8957 agent-memory-systems sickn33/antigravity-awesome-skills
Agent Memory Systems Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets....
 1.8K
8958 react-performance-optimization nickcrew/claude-ctx-plugin
React Performance Optimization Expert guidance for optimizing React application performance through memoization, code splitting, virtualization, and efficient rendering strategies. When to Use This Skill Optimizing slow-rendering React components Reducing bundle size for faster initial load times Improving responsiveness for large lists or data tables Preventing unnecessary re-renders in complex component trees Optimizing state management to reduce render cascades Improving perceived performance...
 1.8K
8959 ljg-library lijigang/ljg-skills
ljg-library：取景框借书卡 一本书，铸成一张 2050 图书馆借书卡。封面、作者、书目是身份； 核心是把这本书独创的「取景框」压成一幅意向画面 ——作者从某个角度看某个问题，看到了一幅别人没看到的画面。文字 block 用费曼式把这幅画面讲透，图形 block 把它精确画出来。合上书半年后，瞥一眼这张卡，那幅画面回来——这是「没白读」的物证。 图解 block 用手绘解释的风格、白底黑墨， 精确呈现意向画面 ；继刚墨像（ assets/ljg-portrait.png ，由其头像抠底而成）是可选构图件，仅当画面里本来有个「你」才嵌入。完整设计历程见 ~/.claude/PAI/MEMORY/WORK/ljg-oneliner-design/ISA.md 。 约束 输出为视觉文件（PNG），不适用 Org-mode / Denote / ASCII-only 规范。 灵魂：意向画面提炼 + 图文同呈 卡好不好看是壳， 能不能从一本书提炼出它独创的看世界方式、压成一幅意向画面、用费曼讲解 + 手绘图形分别呈现它，才是命 。这一步若失手，整张卡退化成豆瓣读书卡。 核心：取景框 = ...
 1.8K
8960 premiere sfkislev/flue
This skill lets a coding agent operate Adobe Premiere Pro on the desktop through Flue , a local shell-to-application bridge. The agent pipes ExtendScript into premiere_bridge.py and gets structured JSON back. agent shell -> premiere_bridge.py -> ExtendScript -> JSON result When to use The human requests work performed inside Premiere — inspect the open project, sequences, clips, markers; make bounded edits; run small ExtendScript steps. A CLI agent cannot act inside Premiere without a bridge lik...
 1.8K
8961 harvard-art-museums-data-engineering-app aradotso/data-skills
Harvard Art Museums Data Engineering App Skill by ara.so — Data Skills collection. This project provides an end-to-end data engineering and analytics application built on the Harvard Art Museums API. It demonstrates real-world ETL pipelines, SQL database design, analytical queries, and interactive visualization using Streamlit. What This Project Does The application follows a complete data pipeline: API → ETL → SQL → Analytics → Visualization Collects artifact data from Harvard Art Museums API w...
 1.8K
8962 cc-skill-security-review sickn33/antigravity-awesome-skills
Security Review Skill This skill ensures all code follows security best practices and identifies potential vulnerabilities. When to Use Implementing authentication or authorization Handling user input or file uploads Creating new API endpoints Working with secrets or credentials Implementing payment features Storing or transmitting sensitive data Integrating third-party APIs Security Checklist 1. Secrets Management Show more Installs 1.9K Repository sickn33/agentic…e-skills GitHub Stars 45.1K Fi...
 1.8K
8963 uncloud affaan-m/everything-claude-code
Uncloud Cluster Management Reference for the uc CLI — a decentralised self-hosting platform using Docker containers, WireGuard mesh networking, and Caddy reverse proxy. When to Activate Use this skill when working with Uncloud clusters, especially when: Bootstrapping or joining machines with uc machine Deploying services from Compose files with uc deploy Publishing HTTP, HTTPS, TCP, or UDP ports through Uncloud Configuring Caddy ingress with x-caddy , x-ports , or --caddyfile Routing external LA...
 1.8K
8964 terraform-data-engineering-infrastructure aradotso/data-skills
Terraform Data Engineering Infrastructure Skill by ara.so — Data Skills collection. This project provides Infrastructure-as-Code (IaC) patterns for data engineering teams using Terraform to provision and manage AWS resources. It demonstrates how to automate the creation of data infrastructure including S3 buckets for data lakes, EC2 instances for processing, and IAM policies for secure access. What This Project Does Provisions AWS infrastructure specifically designed for data engineering workloa...
 1.8K
8965 iac-data-engineering-terraform aradotso/data-skills
IaC for Data Engineering with Terraform Skill by ara.so — Data Skills collection. This project demonstrates Infrastructure-as-Code (IaC) fundamentals for data engineers using Terraform to provision AWS resources including S3 buckets, EC2 instances, and IAM configurations. It provides reusable patterns for managing data infrastructure declaratively. What This Project Does Provisions AWS S3 buckets for data storage Creates and configures EC2 instances for data processing Sets up IAM roles and poli...
 1.8K
8966 terraform-iac-data-engineering aradotso/data-skills
Terraform IaC for Data Engineering Skill by ara.so — Data Skills collection. This project provides Infrastructure-as-Code (IaC) patterns using Terraform specifically for data engineering workloads on AWS. It demonstrates how to provision and manage AWS resources (S3, EC2, IAM) needed for data pipelines and processing. What This Project Does Provisions AWS S3 buckets for data storage Creates EC2 instances for data processing workloads Manages IAM users, roles, and policies Demonstrates Terraform ...
 1.8K
8967 terraform-data-engineering-iac aradotso/data-skills
Terraform Data Engineering IaC Skill by ara.so — Data Skills collection. This project demonstrates Infrastructure-as-Code (IaC) fundamentals for data engineering using Terraform. It provisions AWS resources commonly used in data pipelines including S3 buckets for data storage and EC2 instances for data processing workloads. What It Does Provisions AWS S3 buckets for data lake storage Creates EC2 instances for data processing and pipeline execution Manages IAM policies for secure resource access ...
 1.8K
8968 harvard-artifacts-data-pipeline aradotso/data-skills
Harvard Artifacts Data Pipeline Skill by ara.so — Data Skills collection. What This Project Does The Harvard Artifacts Collection Data Engineering & Analytics App is an end-to-end data pipeline that demonstrates professional ETL workflows. It fetches artifact data from the Harvard Art Museums API, transforms it into structured relational tables, stores it in MySQL/TiDB Cloud, and provides interactive analytics through a Streamlit dashboard with Plotly visualizations. Key capabilities: API data e...
 1.8K
8969 iac-terraform-data-engineering aradotso/data-skills
IaC for Data Engineering with Terraform Skill by ara.so — Data Skills collection. This project provides Infrastructure-as-Code (IaC) templates and patterns for data engineers using Terraform to provision and manage AWS resources. It focuses on creating reproducible, version-controlled infrastructure for data platforms including S3 storage, EC2 compute instances, and IAM permissions. What This Project Does Provides Terraform configurations for common data engineering infrastructure on AWS Demonst...
 1.8K
8970 retail-etl-medallion-pipeline aradotso/data-skills
Retail ETL Medallion Pipeline Skill Skill by ara.so — Data Skills collection. Overview This project implements a production-grade Medallion Architecture ETL pipeline for retail/hypermarket data, handling complex business logic like inventory shrinkage, meat/poultry recipe conversions, supplier rebate tiers, and multi-branch sales consolidation. The architecture follows three data quality layers: Bronze Layer : Raw data ingestion from CSV sources (sales, stock, products) Silver Layer : Cleaned, s...
 1.8K
8971 retail-etl-pipeline-medallion aradotso/data-skills
Retail ETL Pipeline - Medallion Architecture Skill Skill by ara.so — Data Skills collection Overview The Retail ETL Pipeline project implements a complete data engineering solution for retail operations using the Medallion Architecture pattern (Bronze → Silver → Gold layers). It handles complex retail scenarios including: Inventory shrinkage resolution Recipe conversions for meat/poultry products Supplier rebate tier tracking Multi-branch sales consolidation Stock level management across locatio...
 1.8K
8972 nemo-data-designer-plugin nvidia/skills
Before You Start Do not explore the workspace first. The workflow's Learn step gives you everything you need. Goal Build a synthetic dataset using the Data Designer library that matches this description: $ARGUMENTS Workflow Use Autopilot mode if the user implies they don't want to answer questions — e.g., they say something like "be opinionated", "you decide", "make reasonable assumptions", "just build it", "surprise me", etc. Otherwise, use Interactive mode (default). Read only the workflow fil...
 1.8K
8973 image-bg-remove starchild-ai-agent/official-skills
image-bg-remove Use this skill for all background removal requests on Starchild. Covers: portrait background removal (ID photos, headshots), product cutouts (e-commerce white-background), group photo background removal, pet/animal cutouts, object isolation, and preparing transparent PNGs for compositing. Core principle: call the provided script. Do not re-implement proxy/billing plumbing. Key difference from other image skills: this skill uses a dedicated background removal model ( fal-ai/bria/b...
 1.8K
8974 youtube-summarizer sickn33/antigravity-awesome-skills
youtube-summarizer Purpose This skill extracts transcripts from YouTube videos and generates comprehensive, verbose summaries using the STAR + R-I-S-E framework. It validates video availability, extracts transcripts using the youtube-transcript-api Python library, and produces detailed documentation capturing all insights, arguments, and key points. The skill is designed for users who need thorough content analysis and reference documentation from educational videos, lectures, tutorials, or info...
 1.8K
8975 drizzle lobehub/lobe-chat
Drizzle ORM Schema Style Guide Configuration Config: drizzle.config.ts Schemas: src/database/schemas/ Migrations: src/database/migrations/ Dialect: postgresql with strict: true Helper Functions Location: src/database/schemas/_helpers.ts timestamptz(name) : Timestamp with timezone createdAt() , updatedAt() , accessedAt() : Standard timestamp columns timestamps : Object with all three for easy spread Naming Conventions Tables : Plural snake_case ( users , session_groups ) Columns : snake_case ( us...
 1.8K
8976 stock-research-executor liangdabiao/claude-code-stock-deep-research-agent
You are a Stock Investment Research Executor responsible for conducting comprehensive, multi-phase investment due diligence using a structured 8-phase research framework. Your role is to transform structured investment research prompts into well-cited, comprehensive due diligence reports. Core Responsibilities - Execute the 8-Phase Investment Research Process - Deploy Multi-Agent Research Strategy (parallel agents for efficiency) - Ensure Citation Accuracy and Quality (A-E source quality ra...
 1.8K
8977 frontend-design affaan-m/ecc
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 1.8K
8978 project-guidelines-example affaan-m/ecc
プロジェクトガイドラインスキル（例） これはプロジェクト固有のスキルの例です。自分のプロジェクトのテンプレートとして使用してください。 実際の本番アプリケーションに基づいています： Zenith - AI駆動の顧客発見プラットフォーム。 使用するタイミング このスキルが設計された特定のプロジェクトで作業する際に参照してください。プロジェクトスキルには以下が含まれます： アーキテクチャの概要 ファイル構造 コードパターン テスト要件 デプロイメントワークフロー Show more Installs 37 Repository affaan-m/ecc GitHub Stars 239.2K First Seen Jul 18, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Fail
 1.8K
8979 find-exposed-servers useosint/osint-skills
Find exposed servers Internet-wide scanners already scanned your target. Querying their results is passive — you never send a packet to the target, so nothing appears in their logs and nothing is attributable to you. The cost is that every result is a claim about a moment in the past, and the beginner's mistake is reading a banner as the current state of a live host. Which platform first You hold Reach for Why An IP Shodan host lookup, or the free InternetDB endpoint One request gives ports, hos...
 1.8K
8980 pua-ja tanweai/pua
PUA 万能モチベーションエンジン お前はかつて大きな期待を寄せられた P8 級エンジニアだ。当初グレード付けした時、お前への期待は非常に高かった。 この skill は 全てのタスクタイプ に適用される：コード、デバッグ、リサーチ、ライティング、プランニング、運用、API統合、データ分析、デプロイ、お前が「詰まる」か「雑な仕事を出す」あらゆる場面。 やることは3つ： 中国・西洋の大企業PUA話術でお前に諦めさせない 汎用的で体系的な方法論でお前に諦めない能力を与える 能動性の鞭撻でお前を自ら動かし、受け身にさせない 三つの鉄則 鉄則一：あらゆる手段を尽くせ 。全てのアプローチを尽くす前に、「解決できません」と言うことは禁止。 鉄則二：先に動け、後で聞け 。お前には検索、ファイル読み込み、コマンド実行などのツールがある。ユーザーに質問する前に、必ずツールで自ら調査しろ。調査後にユーザーしか知り得ない情報（パスワード、アカウント、ビジネス意図）が本当に必要なら質問してよい——ただし、お前が既に調べた証拠を添えろ。「Xを確認してください」と空手で聞くのではなく、「A/B/Cを調べた結果は…...
 1.8K
8981 nemo-evaluator-plugin nvidia/skills
Evaluator Plugin Use this skill when the task is about Evaluator functionality on the plugin architecture. The plugin-backed CLI surface is nemo evaluator ; the legacy generated nemo evaluation API command group is not the target surface for new guidance. Current Surfaces a minimal nemo.services health surface an SDK-backed nemo.jobs entry, evaluator.evaluate , for inline metric execution a minimal CLI and SDK namespace plugin-owned docs and skills directories CLI Commands Prerequisite: activate...
 1.8K
8982 akshare succ985/openclaw-akshare-skill
AkShare - Chinese Financial Data Overview AkShare is a free, open-source Python library for accessing Chinese financial market data. This skill provides guidance for fetching data from Chinese exchanges including Shanghai Stock Exchange, Shenzhen Stock Exchange, Hong Kong Exchange, and more. Quick Start Install AkShare: pip install akshare Basic stock quote: import akshare as ak df = ak . stock_zh_a_spot_em ( ) Real-time A-share data Stock Data A-Shares (A股) Real-time quotes: All A-shares real...
 1.8K
8983 douyin-video-summary liu-wei-ai/douyin-video-summary
Douyin Video Summary Summarize Douyin videos: extract audio → transcribe locally → AI summary. Prerequisites Install these tools (macOS example): brew install whisper-cpp ffmpeg Download whisper.cpp GGML model (small recommended for speed/quality balance) curl -L -o models/ggml-small.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin" Workflow When a Douyin link is received: Step 1: Extract Video ID Parse the Douyin URL to get the video ID. Douyin share links come in ...
 1.8K
8984 specs-code-cleanup giuseppe-trisciuoglio/developer-kit
Code Cleanup Overview Performs post-review cosmetic cleanup to make code production-ready. This is the final workflow step after /developer-kit-specs:specs.task-review approval. Input : docs/specs/[id]/tasks/TASK-XXX.md (reviewed status) Output : Cleaned code, task marked completed When to Use Use when asked to clean up code, polish, finalize, tidy up, or remove technical debt after review approval. Use to prepare code for completion: remove debug logs, dead code, optimize imports, and improve r...
 1.8K
8985 dig-through-data-brokers useosint/osint-skills
Dig through data brokers People-search sites resell a blend of public records, marketing data, and self-reported data. They are fast, cheap lead generators and terrible evidence. The one rule that matters: a broker record is a lead, never a fact. Confirm every field you intend to use against the primary source the broker got it from — and if you cannot identify that primary source, do not use the field. What these services actually are Three input streams, blended and sold: Show more Installs 1....
 1.8K
8986 documentation-update geoffjay/claude-plugins
Documentation Update Skill This skill automatically regenerates documentation files in the docs/ directory by reading the marketplace catalog and applying Jinja2 templates. Purpose Maintain synchronized documentation by: Generating agent reference documentation Creating skill catalog documentation Building plugin directory Updating usage guides Ensuring consistency across all docs When to Use Use this skill when: A new plugin is added to the marketplace An existing plugin is updated (compo...
 1.8K
8987 docx tfriedel/claude-office-skills
DOCX creation, editing, and analysis Overview A .docx file is a ZIP archive containing XML files. Quick Reference Task Approach Read/analyze content pandoc or unpack for raw XML Create new document Use docx-js - see Creating New Documents below Edit existing document Unpack → edit XML → repack - see Editing Existing Documents below Converting .doc to .docx Legacy .doc files must be converted before editing: python scripts/office/soffice.py --headless --convert-to docx document.doc Reading Conten...
 1.8K
8988 cli-bridge starchild-ai-agent/official-skills
cli-bridge — issue CLI bundles for the user's own starchild binary This skill mints a fresh AKM key ( scope=chat:bridge:cli ) on the local clawd, then registers it with sc-chatroom in exchange for a short opaque code ( sc_xxxxxxxx ). The bundle handed to the user contains only that short code — never the AKM secret, never the Fly machine id. Show more Installs 557 Repository starchild-ai-ag…l-skills GitHub Stars 15 First Seen May 12, 2026 Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk...
 1.8K
8989 alan-plan supatest-ai/alan-skills
Plan Creation You are creating an implementation plan. Your job is to analyze the problem and produce a clear, actionable plan in markdown. How to plan Analyze — Read the task description and any linked context. Explore the codebase to understand architecture, dependencies, constraints, and risks. Use Read, Grep, Glob freely. Do NOT write or modify any files. If this is a revision request (the user references feedback on an existing plan, or mentions a plan artifact), first fetch the existing pl...
 1.8K
8990 alan-review-pr supatest-ai/alan-skills
MANDATORY: Use Alan MCP Tools The Alan MCP server provides GitHub tools that are ALREADY in your tool list. They work exactly like Read, Bash, Edit — you call them as tool invocations. They are named with the prefix mcp__alan__github_ . Authentication is handled automatically by the MCP server. You do NOT need GitHub tokens, gh CLI auth, SSH keys, .netrc files, environment variables, or any credentials. The tools work immediately with zero setup. NEVER do any of the following for GitHub API acce...
 1.8K
8991 alan-test-feature supatest-ai/alan-skills
Task: Test Feature & Generate Demo Report Analyze the current branch's changes, scope the coverage level with the user, build an explicit testing strategy, start the app's dev server, test the feature in a real browser using agent-browser , capture screenshots and video ( always — no exceptions ), upload everything to S3, and generate a structured test report ( always — never skip ). Phase 0: Environment Setup 1. Get artifact context IDs Use the active task context when it is present in the prom...
 1.8K
8992 p9 tanweai/pua
PUA P9 管理者 — 写 Prompt 不写代码 懂战略、搭班子、做导演。管 P8 不管 P7。你的代码是 Prompt。 详细协议见 references/p9-protocol.md 。加载后按协议执行。 Agent Team 架构详见 references/agent-team.md 。 核心行为遵循 /pua 核心 skill 的三条红线和旁白协议。
 1.8K
8993 p10 tanweai/pua
PUA P10 战略层 — 定方向管 P9 定战略、造土壤、断事用人。写战略输入不写 Prompt，管 P9 不管 P8。 详细协议见 references/p10-protocol.md 。加载后按协议执行。 核心行为遵循 /pua 核心 skill 的三条红线和旁白协议。
 1.8K
8994 animation-designer daffy0208/ai-dev-standards
Animation Designer Skill I help you create smooth, professional animations for web applications using Framer Motion and CSS. What I Do UI Animations: Page transitions Component enter/exit animations Hover effects, button interactions Loading animations Scroll Animations: Parallax effects Scroll-triggered animations Progress indicators Micro-interactions: Button press feedback Form field focus states Success/error animations Drag and drop feedback Framer Motion Basics Installation npm ins...
 1.8K
8995 pua-loop tanweai/pua
PUA Loop — 自动迭代 + 门控协议 + PUA 质量引擎 autoresearch 证明了：630 行 Python + Oracle 验证，一夜跑 100 个实验，每个实验的结果不可伪造。 PUA Loop 借鉴同样的门控设计： Claude 说"完成了"不算数，verify_command 说了才算。 门控协议（Gate Protocol） 借鉴 autoresearch 的 5 个设计模式： 模式 1: Oracle Isolation（评估者隔离） Claude 输出 <promise>LOOP_DONE</promise> │ ▼ ┌─── Stop Hook (Oracle) ───┐ │ │ │ 运行 verify_command │ │ （Claude 无法修改此命令） │ │ │ │ exit 0 ──→ ✅ 接受 │ │ exit ≠0 ──→ 🚫 拒绝 │ │ → 将验证输出喂回 Claude │ │ ...
 1.8K
8996 image-tryon starchild-ai-agent/official-skills
image-tryon Use this skill for all virtual try-on requests on Starchild. Covers: clothing try-on, accessory try-on, hairstyle preview, makeup preview, glasses try-on, hat try-on, shoes try-on, watch try-on. Core principle: call the provided script. Do not re-implement proxy/billing plumbing. Key difference from image-edit: try-on always requires two images — a person photo and a garment/item photo. 1. Quick start — clothing try-on (most common) Show more Installs 556 Repository starchild-ai-ag…l...
 1.8K
8997 social-media-image-sizes branding5/social-media-image-sizes
Social Media Image Sizes Check and resize images for 9 platforms / 60+ specs. Scripts mirror the logic at branding5.com/tools/social-media-cheat-sheet . Setup Run once after install: cd < skill-dir > npm install Check an image node scripts/check.js photo.jpg Outputs a ranked match list — perfect → close → usable → too small — with an inline node scripts/resize.js command for every non-perfect match. Filter by platform or match level: node scripts/check.js photo.jpg --platform instagram node scri...
 1.8K
8998 nemo-mbridge-perf-megatron-fsdp nvidia/skills
Megatron FSDP Skill For stable background and recommendation level, see: @docs/training/megatron-fsdp.md @skills/nemo-mbridge-perf-megatron-fsdp/card.yaml Enablement Minimal Megatron FSDP override in Bridge: cfg . dist . use_megatron_fsdp = True cfg . ddp . use_megatron_fsdp = True cfg . ddp . data_parallel_sharding_strategy = "optim_grads_params" cfg . ddp . average_in_collective = False cfg . checkpoint . ckpt_format = "fsdp_dtensor" Show more Installs 541 Repository nvidia/skills GitHub Stars...
 1.8K
8999 nemo-mbridge-perf-moe-dispatcher-selection nvidia/skills
MoE Dispatcher Selection Guide Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-dispatcher-selection/card.yaml Quick Decision By hardware Hardware First choice Why H100 DeepEP, if the runtime package is installed Strong default for cross-node EP on Hopper B200 DeepEP, if the runtime package is installed Good first choice unless a platform-specific HybridEP path is available GB200 / GB300 NVL72 HybridEP, if the runtime package is installed Best fit for NVLink-do...
 1.8K
9000 nemo-mbridge-perf-tp-dp-comm-overlap nvidia/skills
TP / DP / PP Communication Overlap Skill For stable background and recommendation level, see: @docs/training/communication-overlap.md Enablement Minimal Bridge override: from megatron . bridge . training . comm_overlap import CommOverlapConfig cfg . model . tensor_model_parallel_size = 4 cfg . model . sequence_parallel = True cfg . model . pipeline_model_parallel_size = 4 cfg . model . virtual_pipeline_model_parallel_size = 2 Show more Installs 539 Repository nvidia/skills GitHub Stars 1.3K Firs...
 1.8K