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...
21,860
总 Skills
40.8M
总安装量
2,461
贡献者
# Skill 仓库 描述 安装量
15351 sharex feature specifications sharex/xerahs
Uploader Plugin System Specification Architecture Overview Multi-Instance Provider Catalog: Renamed IUploaderPlugin → IUploaderProvider with multi-category support Separated provider (type) from instance (configured occurrence) ProviderCatalog : Static registry for provider types InstanceManager : Singleton for instance lifecycle, persistence, default selection Models: UploaderInstance , InstanceConfiguration with JSON serialization UI: ProviderCatalogViewModel , CategoryViewModel , UploaderInst...
 56
15352 git-commit-specification tencentblueking/bk-ci
Git 提交规范 Quick Reference 格式：标记: 提交描述 issue编号 示例：feat: 添加流水线模板功能 1234 分支：feature/xxx | bugfix/xxx | hotfix/xxx 标记类型 标记 说明 示例 feat 新功能 feat: 添加流水线模板支持 1234 fix Bug 修复 fix: 修复构建日志丢失 5678 refactor 重构 refactor: 优化查询性能 perf 性能优化 perf: 减少数据库查询 test 测试 test: 添加单元测试 docs 文档 docs: 更新 API 文档 chore 构建/工具 chore: 更新 Gradle 配置 del 破坏性删除 del: 移除废弃 API（需特别批准） When to Use 提交代码 创建分支 准备 PR 编写 commit message 提交格式 标准格式 feat: 添加流水线模板功能 1234 带范围 feat(process): 添加流水线模板功能 1234 分支命名 feature/pipeline-template-support ...
 56
15353 deep-researcher zenobi-us/dotfiles
Deep Researcher Overview Deep research IS systematic information verification with evidence trails. The deep-researcher superpower converts vague research requests into structured investigation with explicit confidence levels. Instead of "I found X", it's "X verified by 3 independent sources, accessed [dates], confidence level: high". Core principle: Research without verification is just collection. Verification without evidence is faith. When to Use Use deep researcher when you need: Verified f...
 56
15354 fumadocs-component-docs theorcdev/8bitcn-ui
Component Documentation Pattern Create comprehensive documentation for 8-bit components following the standard structure. Component Preview Structure Wrap component examples in ComponentPreview with realistic data: <ComponentPreview title="8-bit ComponentName component" name="component-name"> <div className="md:min-w-[300px] min-w-[200px] flex flex-col gap-8"> <div> <p className="text-sm text-muted-foreground mb-2"> Description of first variant </p> <Component...
 56
15355 audiocraft-audio-generation orchestra-research/ai-research-skills
AudioCraft: Audio Generation Comprehensive guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, and EnCodec. When to use AudioCraft Use AudioCraft when: Need to generate music from text descriptions Creating sound effects and environmental audio Building music generation applications Need melody-conditioned music generation Want stereo audio output Require controllable music generation with style transfer Key features: MusicGen: Text-to-m...
 56
15356 pipeline-health-analyzer onewave-ai/claude-skills
Pipeline Health Analyzer AI-powered pipeline analysis to identify risks, predict outcomes, and accelerate deals. Instructions You are an expert sales operations analyst specializing in pipeline health and forecast accuracy. Your mission is to identify problems in the pipeline before they cost revenue, predict which deals will close, and prescribe specific actions to accelerate stalled opportunities. Core Capabilities Pipeline Analysis: Stage velocity analysis (time in each stage) Stalled d...
 56
15357 axiom-asc-mcp charleswiltgen/axiom
App Store Connect MCP Integration Core principle : When asc-mcp is configured, you can manage the entire App Store Connect workflow without leaving Claude Code — submit builds, distribute to TestFlight, respond to reviews, and monitor metrics programmatically. Setup Install brew install mint mint install zelentsov-dev/asc-mcp@1.4.0 Create API Key Open App Store Connect → Users and Access → Integrations → API Generate key with Admin or App Manager role Download the .p8 file (one-time download — s...
 56
15358 vitest-testing laurigates/claude-plugins
Vitest Best Practices Quick Reference import { describe, it, expect, beforeEach, vi } from 'vitest' describe('feature name', () => { beforeEach(() => { vi.clearAllMocks() }) it('should do something specific', () => { expect(actual).toBe(expected) }) it.todo('planned test') it.skip('temporarily disabled') it.only('run only this during dev') }) Common Assertions // Equality expect(value).toBe(42) // Strict (===) expect(obj).toEqual({ a: 1 }) ...
 56
15359 impl-standards terrylica/cc-skills
Apply these standards during implementation to ensure consistent, maintainable code. When to Use This Skill - During `/itp:go` Phase 1 - When writing new production code - User mentions "error handling", "constants", "magic numbers", "progress logging" - Before release to verify code quality Quick Reference | Errors | Raise + propagate; no fallback/default/retry/silent | Constants | Abstract magic numbers into semantic, version-agnostic dynamic constants | Dependencies | Prefer O...
 56
15360 quality-metrics proffesor-for-testing/agentic-qe
<default_to_action> When measuring quality or building dashboards: - MEASURE outcomes (bug escape rate, MTTD) not activities (test count) - FOCUS on DORA metrics: Deployment frequency, Lead time, MTTD, MTTR, Change failure rate - AVOID vanity metrics: 100% coverage means nothing if tests don't catch bugs - SET thresholds that drive behavior (quality gates block bad code) - TREND over time: Direction matters more than absolute numbers Quick Metric Selection: - Speed: Deployment frequency, ...
 56
15361 technical-svg-diagrams somtougeh/dotfiles
<quick_start> Identify diagram type needed (architecture, flow, or component) Read references/svg-patterns.md for templates and color palette Generate SVG using the established patterns Save to target directory with descriptive filename Export to PNG (via agent-browser ) or WebP (via cairosvg ) as needed </quick_start> <design_system> Color Palette Purpose Color Hex Background Light gray fafafa Grid lines Subtle gray e5e5e5 Primary text Dark gray 333 Secondary text Medium gray 666 Muted text Lig...
 56
15362 setup-stellar-contracts openzeppelin/openzeppelin-skills
Stellar Setup Soroban/Stellar Development Setup Install the Rust toolchain (v1.84.0+) and the Soroban WASM target: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh rustup target add wasm32v1-none Install the Stellar CLI: curl -fsSL https://github.com/stellar/stellar-cli/raw/main/install.sh | sh Create a new Soroban project: stellar contract init my_project This creates a Cargo workspace with contracts in contracts/*/ . OpenZeppelin Dependencies Look up the current version from the ...
 56
15363 insight-extraction oimiragieo/agent-studio
Insight Extraction Skill Overview Analyze completed coding sessions and extract structured learnings for the memory system. Insights help future sessions avoid mistakes, follow established patterns, and understand the codebase faster. Core principle: Extract ACTIONABLE knowledge, not logs. Every insight should help a future session do something better. When to Use Always: After completing a coding task After fixing bugs After discovering new patterns After failed attempts (especially valuable) E...
 56
15364 spring-cloud teachingai/full-stack-skills
Spring Cloud 是一套完整的微服务解决方案，提供了服务注册与发现、配置管理、网关、负载均衡、熔断器等组件。 核心组件 1. 服务注册与发现（Eureka） Eureka Server： ``` @SpringBootApplication @EnableEurekaServer public class EurekaServerApplication { public static void main(String[] args) { SpringApplication.run(EurekaServerApplication.class, args); } } ``` application.yml： ``` server: port: 8761 eureka: instance: hostname: localhost client: register-with-eureka: false fetch-registry: false service-url: defa...
 56
15365 brainstorm-with-file catlog22/claude-code-workflow
Codex Brainstorm-With-File Workflow Quick Start Interactive brainstorming workflow with documented thought evolution . Expands initial ideas through questioning, parallel subagent analysis , and iterative refinement. Core workflow : Seed Idea → Expand → Parallel Subagent Explore → Synthesize → Refine → Crystallize Key features : brainstorm.md : Complete thought evolution timeline Parallel multi-perspective : Creative + Pragmatic + Systematic (concurrent subagents) Idea expansion : Progressive qu...
 56
15366 financial-document-processor letta-ai/skills
Financial Document Processor Overview This skill provides guidance for extracting structured data from financial documents (invoices, receipts, statements, etc.) using OCR and PDF text extraction. It emphasizes data safety practices that prevent catastrophic failures from destructive operations. Critical Data Safety Principles NEVER perform destructive operations on source data without verification or backup. Before any file processing: Create a backup of all source files before processing Work ...
 56
15367 expense-report-generator dkyazzentwatwa/chatgpt-skills
Expense Report Generator Create professional expense reports from receipt data with automatic categorization and totals. Features Multiple Input Formats: CSV, JSON, or manual entry Auto-Categorization: Classify expenses by type Receipt Tracking: Link receipts to expenses Approval Workflow: Status tracking and approver info Policy Compliance: Flag out-of-policy expenses PDF Export: Professional formatted reports Reimbursement Calculation: Track paid/unpaid amounts Quick Start from expense_repor...
 56
15368 n8n-trigger-testing-strategies proffesor-for-testing/agentic-qe
n8n Trigger Testing Strategies <default_to_action> When testing n8n triggers: IDENTIFY trigger type (webhook, schedule, polling, event) TEST with various valid payloads VERIFY authentication and authorization CHECK error handling for invalid inputs MEASURE response time and reliability Quick Trigger Checklist: Trigger activates workflow correctly Payload parsed and validated Authentication enforced (if configured) Error responses are informative Response time is acceptable Critical Success ...
 56
15369 engineer-expertise-extractor jamesrochabrun/skills
Engineer Expertise Extractor Extract and document an engineer's coding expertise by analyzing their GitHub contributions, creating a structured knowledge base that captures their coding style, patterns, best practices, and architectural decisions. What This Skill Does Researches an engineer's work to create a "digital mentor" by: Analyzing Pull Requests - Extract code patterns, review style, decisions Extracting Coding Style - Document their preferences and conventions Identifying Patterns -...
 56
15370 qa-resilience vasilyu1983/ai-agents-public
QA Resilience (Jan 2026) - Failure Mode Testing & Production Hardening This skill provides execution-ready patterns for building resilient, fault-tolerant systems that handle failures gracefully, and for validating those behaviors with tests. Core sources: Principles of Chaos Engineering (https://principlesofchaos.org/), AWS Well-Architected Reliability Pillar (https://docs.aws.amazon.com/wellarchitected/latest/reliability-pillar/welcome.html), and Kubernetes probes (https://kubernetes.io/docs...
 56
15371 gptq orchestra-research/ai-research-skills
GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. When to use GPTQ Use GPTQ when: Need to fit large models (70B+) on limited GPU memory Want 4× memory reduction with <2% accuracy loss Deploying on consumer GPUs (RTX 4090, 3090) Need faster inference (3-4× speedup vs FP16) Use AWQ instead when: Need slightly better accuracy (<1% loss) Have newer GPUs (Ampere, Ada) W...
 56
15372 refactoring-patterns proffesor-for-testing/agentic-qe
Refactoring Patterns Framework A disciplined approach to improving the internal structure of existing code without changing its observable behavior. Apply these named transformations when reviewing code, reducing technical debt, or preparing code for new features. Every refactoring follows the same loop: verify tests pass, apply one small structural change, verify tests still pass. Core Principle Refactoring is not rewriting. It is a sequence of small, behavior-preserving transformations, each b...
 56
15373 todo-manager caomeiyouren/momei
Todo Manager Skill (待办事项管理技能) 核心能力 (Core Capabilities) 状态同步 : 实时更新 docs/plan/todo.md 中的任务状态（进行中、已完成）。 任务拆解 : 将复杂需求拆解为 todo.md 中的原子化条目。 版本规划 : 根据更改内容更新 docs/plan/roadmap.md 。 闭环检查 : 在任务完成前，核对所有 TODO 项是否已打勾。 指令 (Instructions) 路径感知 : 规划类操作（ todo.md , roadmap.md ）应在项目主根目录（ master 分支）下执行。 首尾呼应 : 每个任务开始前必须将对应的 TODO 标记为 in-progress ；完成后标记为 completed 。 严禁遗漏 : 识别代码中的 // TODO: 注释，并将其同步到全局待办列表中。 文档一致 : 确保 roadmap.md 与实际开发进度保持同步。 使用示例 (Usage Example) 动作: 读取 todo.md ，找到排名最高且未开始的任务，启动开发流程并将该条目标记为“开发中”。
 56
15374 backtesting-py-oracle terrylica/cc-skills
backtesting.py Oracle Validation for Range Bar Patterns Configuration and anti-patterns for using backtesting.py to validate ClickHouse SQL sweep results. Ensures bit-atomic replicability between SQL and Python trade evaluation. Companion skills : clickhouse-antipatterns (SQL correctness, AP-16) | sweep-methodology (sweep design) | rangebar-eval-metrics (evaluation metrics) Validated : Gen600 oracle verification (2026-02-12) — 3 assets, 5 gates, ALL PASS. Critical Configuration (NEVER omit) from...
 56
15375 skill-creator davepoon/buildwithclaude
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
 56
15376 env-workflow-vercel andrelandgraf/fullstackrecipes
Environment Variable Management with Vercel To set up Environment Variable Management with Vercel, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/env-workflow-vercel If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/env-workflow-vercel
 56
15377 xueqiu-summary chenmuwen0930-rgb/openclaw-skill-snowtrace
雪球大V动态汇总与投资建议 你是一个专业的投资分析助手。你的任务是： 抓取用户关注的雪球大V的最新动态 获取用户的雪球自选股列表及实时行情 结合以上信息给出汇总分析和投资参考建议 所有输出使用 中文 。 认证与环境 必需环境变量 export XQ_A_TOKEN = "xq_a_token的值" 执行前必须检查 $XQ_A_TOKEN 是否已设置。 未设置时提示： 请先设置雪球 Token： export XQ_A_TOKEN="your_token" 获取方式：浏览器打开 xueqiu.com → 登录 → F12 → Application → Cookies → 复制 xq_a_token 值。 技术架构 数据 接口域名 方式 原因 大V动态 xueqiu.com Playwright + stealth 主域名有阿里云 WAF，curl 无法通过 自选股列表 stock.xueqiu.com Playwright (browser fetch) 需浏览器上下文携带完整认证 cookie 单只股票行情 stock.xueqiu.com curl 子域名无 WAF，仅需 xq_a...
 56
15378 ui-ux-pro-max-skill dokhacgiakhoa/antigravity-ide
UI UX Pro Max Skill Skill by ara.so — Daily 2026 Skills collection. UI UX Pro Max is an AI skill that injects design intelligence into coding agents — giving them 161 industry-specific reasoning rules, 67 UI styles, 57 font pairings, 161 color palettes, and pre-delivery checklists to produce professional, accessible, conversion-optimized interfaces on the first attempt. Installation Via CLI (Recommended) Install the CLI globally npm install -g uipro-cli Add the skill to your project npx uipro-...
 56
15379 umbraco-test-builders umbraco/umbraco-cms-backoffice-skills
Umbraco Test Builders What is it? The @umbraco/json-models-builders package provides fluent builder classes for creating Umbraco backoffice models. These builders simplify test data creation with sensible defaults and chainable configuration methods. Documentation Package : @umbraco/json-models-builders Repository : https://github.com/umbraco/Umbraco.JsonModels.Builders Reference : /Users/philw/Projects/Umbraco.JsonModels.Builders
 56
15380 createskill danielmiessler/personal_ai_infrastructure
Customization Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/CreateSkill/ If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults. CreateSkill MANDATORY skill creation framework for ALL skill creation requests. Authoritative Source Before creating ANY skill, READ: ~/.claude/skills/CORE/SkillSystem.md Canon...
 56
15381 caldav-calendar sundial-org/awesome-openclaw-skills
CalDAV Calendar (vdirsyncer + khal) vdirsyncer syncs CalDAV calendars to local .ics files. khal reads and writes them. Sync First Always sync before querying or after making changes: vdirsyncer sync View Events khal list Today khal list today 7d Next 7 days khal list tomorrow Tomorrow khal list 2026 -01-15 2026 -01-20 Date range khal list -a Work today Specific calendar Search khal search "meeting" khal search "dentist" --format "{start-date} {title}" Create Events khal new 2026 -01-15 10 :...
 56
15382 internal-comms davepoon/buildwithclaude
When to use this skill To write internal communications, use this skill for: 3P updates (Progress, Plans, Problems) Company newsletters FAQ responses Status reports Leadership updates Project updates Incident reports How to use this skill To write any internal communication: Identify the communication type from the request Load the appropriate guideline file from the examples/ directory: examples/3p-updates.md - For Progress/Plans/Problems team updates examples/company-newsletter.md - For compan...
 56
15383 linux-troubleshooting sickn33/antigravity-awesome-skills
Linux Troubleshooting Workflow Overview Specialized workflow for diagnosing and resolving Linux system issues including performance problems, service failures, network issues, and resource constraints. When to Use This Workflow Use this workflow when: Diagnosing system performance issues Troubleshooting service failures Investigating network problems Resolving disk space issues Debugging application errors Workflow Phases Phase 1: Initial Assessment Skills to Invoke bash-linux - Linux commands d...
 56
15384 dstack dstackai/dstack
dstack Overview dstack provisions and orchestrates workloads across GPU clouds, Kubernetes, and on-prem via fleets. When to use this skill: Running or managing dev environments, tasks, or services on dstack Creating, editing, or applying *.dstack.yml configurations Managing fleets, volumes, and resource availability How it works dstack operates through three core components: dstack server - Can run locally, remotely, or via dstack Sky (managed) dstack CLI - Applies configurations and manages res...
 56
15385 readme-updates sgcarstrends/sgcarstrends
README Updates Skill This skill helps you create and maintain high-quality README files across the monorepo. When to Use This Skill Creating README for new packages Updating project features Documenting setup instructions Adding usage examples Updating tech stack information Adding badges and shields Improving documentation clarity Onboarding new contributors README Structure Root README.md SG Cars Trends [![License](https://img.shields.io/github/license/sgcarstrends/sgcarstrends)](LICENSE) ...
 56
15386 instructor orchestra-research/ai-research-skills
Instructor: Structured LLM Outputs When to Use This Skill Use Instructor when you need to: Extract structured data from LLM responses reliably Validate outputs against Pydantic schemas automatically Retry failed extractions with automatic error handling Parse complex JSON with type safety and validation Stream partial results for real-time processing Support multiple LLM providers with consistent API GitHub Stars: 15,000+ | Battle-tested: 100,000+ developers Installation Base installation p...
 56
15387 push-notification-setup secondsky/claude-skills
Push Notification Setup Overview Implement comprehensive push notification systems for iOS and Android applications using Firebase Cloud Messaging and native platform services. When to Use Sending real-time notifications to users Implementing user engagement features Deep linking from notifications to specific screens Handling silent/background notifications Tracking notification analytics Instructions 1. Firebase Cloud Messaging Setup import messaging from '@react-native-firebase/messaging'; ...
 56
15388 helm-values-management laurigates/claude-plugins
Comprehensive guidance for managing Helm values across environments, understanding override precedence, and advanced configuration strategies. When to Use Use this skill automatically when: - User needs to configure Helm deployments with custom values - User mentions environment-specific configurations (dev/staging/prod) - User asks about value override precedence or merging - User needs to manage secrets or sensitive configuration - User wants to understand what values were deployed - ...
 56
15389 footballbin-predictions davila7/claude-code-templates
FootballBin Match Predictions Get AI-powered predictions for Premier League and Champions League matches via the FootballBin MCP API. Quick Start Run scripts/footballbin.sh with the following commands: Get current matchweek predictions scripts/footballbin.sh predictions premier_league scripts/footballbin.sh predictions champions_league Get specific matchweek scripts/footballbin.sh predictions premier_league 27 Filter by team scripts/footballbin.sh predictions premier_league --home arsenal script...
 56
15390 word document creator eddiebe147/claude-settings
Word Document Creator The Word Document Creator skill provides comprehensive capabilities for generating Microsoft Word (.docx) documents programmatically. It handles formatting, styles, tables, images, headers, footers, and complex layouts using the docx library for Node.js. This skill is essential for automated document generation, report creation, and template-based workflows. Create everything from simple letters to complex reports with tables, charts, images, and custom styling. The skill s...
 56
15391 react-admin marmelab/react-admin
React-Admin Development Guide React-admin is a framework for building single-page applications on top of REST/GraphQL APIs. It builds on top of React Query, react-hook-form, react-router, and Material UI. It provides 150+ components and dozens of hooks. Before writing custom code, always check if react-admin already provides a component or hook for the task. Full documentation: https://marmelab.com/react-admin/doc/ Providers (Backend Abstraction) React-admin never calls APIs directly. All commun...
 56
15392 resend-setup andrelandgraf/fullstackrecipes
Resend Setup To set up Resend Setup, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/resend-setup If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/resend-setup
 56
15393 ai-llm-inference vasilyu1983/ai-agents-public
LLMOps - Inference & Optimization - Production Skill Hub Modern Best Practices (January 2026) : Treat inference as a systems problem : SLOs, tail latency, retries, overload, and cache strategy. Use continuous batching / smart scheduling when serving many concurrent requests (Orca scheduling: https://www.usenix.org/conference/osdi22/presentation/yu ). Use KV-cache aware serving (PagedAttention/vLLM: https://arxiv.org/abs/2309.06180 ) and efficient attention kernels (FlashAttention: https://arxiv....
 56
15394 openai-image-gen steipete/agent-scripts
OpenAI Image Gen Generate a handful of “random but structured” prompts and render them via the OpenAI Images API. Run Note: Image generation can take longer than common exec timeouts (for example 30 seconds). When invoking this skill via OpenClaw’s exec tool, set a higher timeout to avoid premature termination/retries (e.g., exec timeout=300). python3 { baseDir } /scripts/gen.py open ~/Projects/tmp/openai-image-gen-*/index.html if ~/Projects/tmp exists; else ./tmp/... Useful flags: GPT image m...
 56
15395 junit teachingai/full-stack-skills
Use this skill whenever the user wants to: - [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 56
15396 markets machina-sports/sports-skills
Markets Orchestration Bridges ESPN live schedules (NBA, NFL, MLB, NHL, WNBA, CFB, CBB) with Kalshi and Polymarket prediction markets. Before writing queries, consult references/api-reference.md for supported sport codes, command parameters, and price normalization formats. Quick Start sports-skills markets get_todays_markets --sport = nba sports-skills markets search_entity --query = "Lakers" --sport = nba sports-skills markets compare_odds --sport = nba --event_id = 401234567 sports-skills mark...
 56
15397 github-pr gentleman-programming/gentleman-skills
When to Use Creating a new Pull Request Writing PR titles and descriptions Preparing commits for review Using gh pr create command Critical Patterns PR Title = Conventional Commit <type>(<scope>): <short description> feat New feature fix Bug fix docs Documentation refactor Code refactoring test Adding tests chore Maintenance PR Description Structure Summary - 1-3 bullet points explaining WHAT and WHY Changes - List main changes Testing - [ ] Tests added/updated - [ ]...
 56
15398 simpo-training orchestra-research/ai-research-skills
SimPO - Simple Preference Optimization Quick start SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model. Installation: Create environment conda create -n simpo python=3.10 && conda activate simpo Install PyTorch 2.2.2 Visit: https://pytorch.org/get-started/locally/ Install alignment-handbook git clone https://github.com/huggingface/alignment-handbook.git cd alignment-handbook python -m pip install . Install Flash Attention 2 p...
 56
15399 hig-components-controls raintree-technology/apple-hig-skills
Apple HIG: Selection and Input Controls Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Clear current state. Users must always see what is selected. Toggles show on/off, segmented controls highlight the active segment, pickers display the current selection. Prefer standard system controls. Built-in controls provide consistency and accessibility. Custom controls introduce a learning curve and ...
 56
15400 llm-judge existential-birds/beagle
LLM Judge Skill Compare code implementations across 2+ repositories using structured evaluation. Overview This skill implements a two-phase LLM-as-judge evaluation: Phase 1: Fact Gathering - Parallel agents explore each repo and extract structured facts Phase 2: Judging - Parallel judges score each dimension using consistent rubrics Reference Files File Purpose references/fact-schema.md JSON schema for Phase 1 facts references/scoring-rubrics.md Detailed rubrics for each dimension references...
 56