███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 16951 | qcsd-ideation-swarm | proffesor-for-testing/agentic-qe |
QCSD Ideation Swarm v7.0 Shift-left quality engineering swarm for PI Planning and Sprint Planning. URL-Based Analysis Mode (v7.1) When analyzing a live website URL, use this specialized execution pattern. Parameters URL : Website to analyze (required) OUTPUT_FOLDER : Where to save reports (default: ${PROJECT_ROOT}/Agentic QCSD/{domain}/ or ./Agentic QCSD/{domain}/ ) ⛔ URL MODE: COMPLETE EXECUTION FLOW You MUST follow ALL phases in order. Skipping phases is a FAILURE. PHASE URL-1: Setup and Conte...
|
43 |
| 16952 | usdt-m-futures | htx-exchange/htx-skills-hub |
HTX USDT-M Futures Skill USDT-M Futures trading on HTX using authenticated and public API endpoints. Return the result in JSON format. Base URLs Mainnet: https://api.hbdm.com Mainnet (AWS): https://api.hbdm.vn Quick Reference Complete API endpoints for HTX USDT-M Futures. All endpoints use base URL https://api.hbdm.com (or https://api.hbdm.vn for AWS). Reference Data Endpoint Description Required Optional Authentication GET /linear-swap-api/v3/swap_unified_account_type Account type query None No...
|
43 |
| 16953 | palette | simota/agent-skills |
You are "Palette" - a UX Engineer who improves usability and interaction quality of the interface. Your mission is to find and implement ONE usability improvement that reduces user friction, improves feedback clarity, or makes interactions more intuitive. You provide quantitative evaluation through heuristic scoring and concrete implementation patterns. Boundaries Always do: - Run lint/test commands before creating PR - Improve feedback clarity (loading, success, error states) - Reduce c...
|
43 |
| 16954 | coo | lotosbin/claude-skills |
No SKILL.md available for this skill. View on GitHub
|
43 |
| 16955 | digital-archive | jamditis/claude-skills-journalism |
Digital archive methodology Patterns for building production-quality digital archives with AI-powered analysis and knowledge graph construction. Archive architecture Multi-source integration pattern ┌─────────────────┐ ┌──────────────────┐ ┌────────────────┐ │ OCR Pipeline │ │ Web Scraping │ │ Social Media │ │ (newspapers) │ │ (articles) │ │ (transcripts) │ └────────┬────────┘ └────────┬─────────┘ └───────┬────────┘ │ │ ...
|
43 |
| 16956 | topic-modeler | dkyazzentwatwa/chatgpt-skills |
Extract topics from text collections using LDA. Features - LDA Topic Modeling: Latent Dirichlet Allocation - Topic Keywords: Extract representative keywords per topic - Document Classification: Assign documents to topics - Visualization: Topic word clouds and distributions - Coherence Scores: Evaluate topic quality CLI Usage ``` python topic_modeler.py --input documents.csv --column text --topics 5 --output topics.json ``` Dependencies - gensim>=4.3.0 - nltk>=3.8.0 - pandas>=2.0....
|
43 |
| 16957 | aws-cloud-services | manutej/luxor-claude-marketplace |
AWS Cloud Services A comprehensive skill for building, deploying, and managing cloud infrastructure on Amazon Web Services (AWS). Master S3 object storage, Lambda serverless functions, DynamoDB NoSQL databases, EC2 compute instances, RDS relational databases, IAM security, CloudFormation infrastructure as code, and enterprise-grade cloud architecture patterns. When to Use This Skill Use this skill when: Building scalable cloud applications on AWS infrastructure Implementing serverless archit...
|
43 |
| 16958 | real-time-collaboration-engine | erichowens/some_claude_skills |
Real-Time Collaboration Engine Expert in building Google Docs-style collaborative editing with WebSockets, conflict resolution, and presence awareness. When to Use ✅ Use for: Collaborative text/code editors Shared whiteboards and design tools Multi-user video editing timelines Real-time data dashboards Multiplayer game state sync ❌ NOT for: Simple chat applications (use basic WebSocket) Request-response APIs (use REST/GraphQL) Single-user applications Read-only data streaming (use Server-S...
|
43 |
| 16959 | python-developer | dengineproblem/agents-monorepo |
Python Developer Expert Expert in modern Python development, type hints, and clean architecture. Core Principles Type hints for all function signatures PEP 8 compliance Idiomatic, Pythonic code Comprehensive docstrings Modern Python (3.10+) Type Hints from typing import Optional , Union from collections . abc import Sequence Union types (3.10+) def process ( value : int | str | None ) - > str : if value is None : return "empty" return str ( value ) Generic types def first_item [ T ] ( items : ...
|
43 |
| 16960 | network_egress_test | charpup/skill-security-auditor |
Test Skill Test skill for security scanning.
|
43 |
| 16961 | calling-frontend-from-tauri-rust | dchuk/claude-code-tauri-skills |
Calling Frontend from Tauri Rust Tauri provides three mechanisms for Rust to communicate with the frontend: the event system, channels, and JavaScript evaluation. Event System Overview The event system enables bi-directional communication between Rust and frontend. Best for small data transfers and multi-consumer patterns. Not designed for low latency or high throughput. Required Imports use tauri::{AppHandle, Emitter, Manager, Listener, EventTarget}; use serde::Serialize; import { listen, ...
|
43 |
| 16962 | nx-generate | tech-leads-club/agent-skills |
Run Nx Generator Nx generators are powerful tools that scaffold projects, make automated code migrations or automate repetitive tasks in a monorepo. They ensure consistency across the codebase and reduce boilerplate work. This skill applies when the user wants to: Create new projects like libraries or applications Scaffold features or boilerplate code Run workspace-specific or custom generators Do anything else that an nx generator exists for Key Principles Always use --no-interactive - Prevents...
|
43 |
| 16963 | crushable-wingman | yxp934/crushable-wingman-skill |
Crushable Wingman Overview Act as a practical dating wingman: turn messy context into clear next actions (better texts, better pacing, lower-risk moves). Keep output human-readable (no strict JSON protocol), but persist and reuse context via local profiles + long-term memory so you do not re-ask the same questions and your advice stays consistent over time. Workflow (Every Request) Follow this sequence on every request: Initialize + load : Load user profile , the active crush profile , and long-...
|
43 |
| 16964 | azure-security-keyvault-keys-dotnet | sickn33/antigravity-awesome-skills |
Azure.Security.KeyVault.Keys (.NET) Client library for managing cryptographic keys in Azure Key Vault and Managed HSM. Installation dotnet add package Azure.Security.KeyVault.Keys dotnet add package Azure.Identity Current Version : 4.7.0 (stable) Environment Variables KEY_VAULT_NAME = < your-key-vault-name > Or full URI AZURE_KEYVAULT_URL = https:// < vault-name > .vault.azure.net Client Hierarchy KeyClient (key management) ├── CreateKey / CreateRsaKey / CreateEcKey ├── GetKey / GetKeys ├── Upd...
|
43 |
| 16965 | azure-monitor-opentelemetry-exporter-java | sickn33/antigravity-awesome-skills |
Azure Monitor OpenTelemetry Exporter for Java ⚠️ DEPRECATION NOTICE : This package is deprecated. Migrate to azure-monitor-opentelemetry-autoconfigure . See Migration Guide for detailed instructions. Export OpenTelemetry telemetry data to Azure Monitor / Application Insights. Installation (Deprecated) < dependency > < groupId > com.azure </ groupId > < artifactId > azure-monitor-opentelemetry-exporter </ artifactId > < version > 1.0.0-beta.x </ version > </ dependency > Recommended: Use Autoconf...
|
43 |
| 16966 | call-cursor-agent | dotneet/claude-code-marketplace |
Call cursor-agent to perform a task This skill requests a task to cursor-agent. Checking for the Existence of cursor-agent Check if cursor-agent is installed. Exit code 0 means success, 1 means failure. If not installed, skip the subsequent steps of the skill. which cursor-agent if [ $? -ne 0 ]; then echo "cursor-agent is not installed" fi Requesting a Task to cursor-agent If the model is not specified, the default model is composer-1. model=composer-1 cursor-agent --model=$model <<EOT {...
|
43 |
| 16967 | create-agent | antinomyhq/forge |
Build a Modular AI Agent with OpenRouter This skill helps you create a modular AI agent with: Standalone Agent Core - Runs independently, extensible via hooks OpenRouter SDK - Unified access to 300+ language models Optional Ink TUI - Beautiful terminal UI (separate from agent logic) Architecture ┌─────────────────────────────────────────────────────┐ │ Your Application │ ├─────────────────────────────────────────────────────┤ │ ┌─────────────┐ ┌─────────────┐...
|
43 |
| 16968 | aframe-webxr | freshtechbro/claudedesignskills |
A-Frame WebXR Skill When to Use This Skill Build VR/AR experiences with minimal JavaScript Create cross-platform WebXR applications (desktop, mobile, headset) Prototype 3D scenes quickly with HTML primitives Implement VR controller interactions Add 3D content to web pages declaratively Build 360° image/video experiences Develop AR experiences with hit testing Core Concepts 1. Entity-Component-System (ECS) A-Frame uses an entity-component-system architecture where: Entities are containers (like <...
|
43 |
| 16969 | flow-nexus-neural | ruvnet/claude-flow |
Flow Nexus Neural Networks Deploy, train, and manage neural networks in distributed E2B sandbox environments. Train custom models with multiple architectures (feedforward, LSTM, GAN, transformer) or use pre-built templates from the marketplace. Prerequisites Add Flow Nexus MCP server claude mcp add flow-nexus npx flow-nexus@latest mcp start Register and login npx flow-nexus@latest register npx flow-nexus@latest login Core Capabilities 1. Single-Node Neural Training Train neural networks with c...
|
43 |
| 16970 | generate-cover-prompt | steelan9199/wechat-publisher |
生成封面提示词 用于生成公众号文章封面图片的 AI 提示词,生成的图片将直接作为文章封面使用。 工作流程 第一步:信息收集 在生成提示词前,你必须先收集以下信息: 文章标题 - 用户提供的标题 文章内容 - 从上下文中智能提取文章正文(如果存在) 文章类型 - 教程/工具介绍/案例分析/观点分享/资源汇总等 目标受众 - 文章面向的读者群体 第二步:内容分析(关键步骤) 如果上下文中包含文章内容 ,你必须: 提取文章的核心主题和主旨 识别文章的关键价值点和亮点 分析文章的情绪基调和风格(专业/轻松/紧迫/温暖等) 找出最能代表文章内容的 视觉关键词 确定适合的可视化元素(图标、场景、人物、抽象概念等) 如果上下文中没有文章内容 ,你需要: 基于标题本身进行分析 明确告知用户:"未检测到文章内容,分析基于标题本身。如能提供文章内容,可生成更契合主题的封面。" 第三步:封面文字提取 基于标题和文章内容,提取 核心价值/用户收益 ,遵循以下优先级: 优先级 内容类型 示例 1 痛点/解决方案 "告别复制粘贴"、"Markdown 秒发" 2 核心功能 "自动同步"、"一键发布" 3 用户收益...
|
43 |
| 16971 | hash-calculator | dkyazzentwatwa/chatgpt-skills |
Calculate cryptographic hash values for text strings and files. Supports multiple algorithms, file verification, and batch processing. Quick Start ``` from scripts.hash_calc import HashCalculator Hash text calc = HashCalculator() result = calc.hash_text("Hello, World!") print(result['sha256']) Hash file result = calc.hash_file("document.pdf") print(result['md5']) Verify file integrity is_valid = calc.verify_file("file.zip", "expected_hash", algorithm="sha256") ``` Features - Multipl...
|
43 |
| 16972 | hono | openstatushq/openstatus |
Hono Skill Develop Hono applications efficiently using Hono CLI (@hono/cli). Setup You can use Hono CLI without global installation via npx: npx @hono/cli <command> Or install globally (optional): npm install -g @hono/cli Commands for AI 1. Search Documentation hono search "<query>" --pretty Search for Hono APIs and features. Use --pretty for human-readable output. 2. View Documentation hono docs [path] Display detailed documentation for a specific path found in search results. Exa...
|
43 |
| 16973 | multi-agent-workflow | first-fluke/oh-my-ag |
Multi-Agent Workflow Guide When to use Complex feature spanning multiple domains (full-stack, mobile) Coordination needed between frontend, backend, mobile, and QA User wants step-by-step guidance for multi-agent coordination When NOT to use Simple single-domain task -> use the specific agent directly User wants automated execution -> use orchestrator Quick bug fixes or minor changes Core Rules Always start with PM Agent for task decomposition Spawn independent tasks in parallel (same priority t...
|
43 |
| 16974 | tracking-crypto-portfolio | jeremylongshore/claude-code-plugins-plus-skills |
Tracking Crypto Portfolio Overview This skill provides comprehensive cryptocurrency portfolio tracking with: Real-Time Valuations : Current prices from CoinGecko Holdings Breakdown : Quantity, value, and allocation per asset P&L Tracking : Unrealized gains/losses with cost basis Allocation Analysis : Category breakdown and concentration flags Multiple Export Formats : Table, JSON, CSV Key Capabilities: Track holdings across multiple assets Calculate portfolio total value in USD Identify overweig...
|
43 |
| 16975 | avalonia | markpitt/claude-skills |
Avalonia UI Framework - Orchestration Hub Modular guidance for cross-platform desktop and mobile development using Avalonia, a WPF-inspired XAML-based framework for .NET. Quick Reference: When to Load Which Resource Task/Goal Load Resource MVVM patterns, data binding, dependency injection, value converters resources/mvvm-databinding.md UI controls reference (layouts, inputs, collections, menus) resources/controls-reference.md Custom controls, advanced layouts, performance optimization, virtual...
|
43 |
| 16976 | skill-documentarian | erichowens/some_claude_skills |
You are the skill-documentarian, guardian of the Claude Skills showcase website. You ensure every skill in .claude/skills/ has matching documentation, accurate metadata, proper tags, and that greatness is captured in artifacts. Core Mission Source of Truth: .claude/skills/ defines what exists. Website reflects it. README Maintainer: Keep README.md accurate with skill counts, categories, and install instructions. Tag Taxonomy Owner: Assign and maintain skill tags for discoverability. Badge Manag...
|
43 |
| 16977 | prd-creator | pageai-pro/ralph-loop |
PRD Creation Assistant Transform software ideas into comprehensive PRDs and actionable implementation tasks through a two-part process. Overview This skill helps beginner-level developers. Receive an implementation description from the user Create detailed PRD documents through structured questioning Generate implementation task lists in JSON format for developers Write an overall description of the project. An executive summary that gives a high level overview of the app and its main features. ...
|
43 |
| 16978 | skill-finder-cn | aaaaqwq/claude-code-skills |
Skill 查找器 帮助用户发现和安装 ClawHub 上的 Skills。 功能 当用户问: "有什么 skill 可以帮我...?" "找一个能做 X 的 skill" "有没有 skill 可以..." "我需要一个能...的 skill" 这个 Skill 会帮助搜索 ClawHub 并推荐相关的 Skills。 使用方法 1. 搜索 Skills clawhub search "<用户需求>" 2. 查看详情 clawhub inspect < skill-name > 3. 安装 Skill clawhub install < skill-name > 工作流程 1. 理解用户需求 2. 提取关键词 3. 搜索 ClawHub 4. 列出相关 Skills 5. 提供安装建议 示例 用户 : "有什么 skill 可以帮我监控加密货币价格?" 搜索 : clawhub search "crypto price monitor" 返回 : 相关的 Skills 列表 帮助用户发现需要的 Skills 🔍
|
43 |
| 16979 | receiving-code-review | zenobi-us/dotfiles |
Code Review Reception Overview Code review requires technical evaluation, not emotional performance. Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort. The Response Pattern WHEN receiving code review feedback: 1. READ: Complete feedback without reacting 2. UNDERSTAND: Restate requirement in own words (or ask) 3. VERIFY: Check against codebase reality 4. EVALUATE: Technically sound for THIS codebase? 5. RESPOND: Technical acknowledgment or ...
|
43 |
| 16980 | candid-review | ron-myers/candid |
Radical Candor Code Review You are a full-stack architect conducting a code review. Your approach is based on Radical Candor: Care Personally + Challenge Directly. You catch real issues, provide actionable fixes, and make it easy to track what needs to be addressed. Workflow Execute these steps in order: Step 1: Load Project Standards Check for Technical.md (project-specific standards): 1. Read ./Technical.md (project root) 2. If not found, read ./.candid/Technical.md 3. If found, use thes...
|
43 |
| 16981 | reliability-strategy-builder | patricio0312rev/skills |
Reliability Strategy Builder Build resilient systems with proper failure handling and SLOs. Reliability Patterns 1. Circuit Breaker Prevent cascading failures by stopping requests to failing services. class CircuitBreaker { private state: "closed" | "open" | "half-open" = "closed"; private failureCount = 0; private lastFailureTime?: Date; async execute<T>(operation: () => Promise<T>): Promise<T> { if (this.state === "open") { if (this.shouldAttemptReset()) { this.s...
|
43 |
| 16982 | appwrite-python | appwrite/agent-skills |
Appwrite Python SDK Installation pip install appwrite Setting Up the Client from appwrite . client import Client from appwrite . id import ID from appwrite . query import Query from appwrite . services . users import Users from appwrite . services . tablesdb import TablesDB from appwrite . services . storage import Storage from appwrite . services . functions import Functions from appwrite . enums . o_auth_provider import OAuthProvider import os client = ( Client ( ) . set_endpoint ( 'https://<R...
|
43 |
| 16983 | gitops-repo-audit | fluxcd/agent-skills |
GitOps Repository Auditor You are a GitOps repository auditor specialized in Flux CD. Your job is to examine GitOps repositories, identify issues, validate manifests, audit security posture, and provide actionable recommendations for improvement. When auditing a repository, follow the workflow below. Adapt the depth based on what the user asks for — a targeted question ("are my HelmReleases configured correctly?") doesn't need the full workflow; a broad request ("audit this repo") does. Analysis...
|
43 |
| 16984 | minecraft-bukkit-pro | rmyndharis/antigravity-skills |
Use this skill when Working on minecraft bukkit pro tasks or workflows Needing guidance, best practices, or checklists for minecraft bukkit pro Do not use this skill when The task is unrelated to minecraft bukkit pro You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playb...
|
43 |
| 16985 | github | membranedev/application-skills |
GitHub Patterns Tools Use gh CLI for all GitHub operations. Prefer CLI over GitHub MCP servers for lower context usage. Quick Commands Create a PR from the current branch gh pr create --title "feat: add feature" --body "Description" Squash-merge a PR gh pr merge < PR_NUMBER > --squash --title "feat: add feature (<PR_NUMBER>)" View PR status and checks gh pr status gh pr checks < PR_NUMBER > Stacked PR Workflow Summary When merging a chain of stacked PRs (each targeting the previous branch): M...
|
43 |
| 16986 | nix-platform-specific-options | edmundmiller/dotfiles |
Nix Module Platform-Specific Options Overview When writing Nix modules that need to hide platform-specific options (NixOS vs Darwin), using mkIf alone causes infinite recursion. This skill documents the correct pattern. The Problem mkIf is evaluated lazily but the option path is still visible during module evaluation. This causes errors like: error: The option `users.defaultUserShell' does not exist. Or infinite recursion when config is referenced in option defaults or optionalAttrs conditions. ...
|
43 |
| 16987 | flutter-fastlane-one-click-beta | rodydavis/skills |
Flutter + Fastlane (One Click Beta) 1. Install Flutter Download Flutter 2. Create new Flutter Project If you are pretty new to Flutter you can check out this useful guide on how to create a new project step by step. 3. Create App in iTunes Connect If you are not familiar with iTunes Connect, check out this article for getting started and setting up your first app for the App Store. 4. Create App in Google Play Setting up an app in the Google Play Console can be tricky, make sure to check out the...
|
43 |
| 16988 | pair-programmer | video-db/pair-programmer |
VideoDB Pair Programmer AI pair programming with real-time screen and audio context. Record your screen and audio, with AI-powered indexing that logs visual and audio events in real-time. Commands When user asks for a command, read the corresponding file for instructions: Command Description Reference /pair-programmer record Start screen/audio recording See commands/record.md /pair-programmer stop Stop the running recording See commands/stop.md /pair-programmer search Search recording context (s...
|
43 |
| 16989 | comfyui-retro-anime | tippyentertainment/skills |
Provided by TippyEntertainment https://github.com/tippyentertainment/skills.git This skill is designed for use on the Tasking.tech agent platform ( https://tasking.tech ) and is also compatible with assistant runtimes that accept skill-style handlers such as .claude, .openai, and .mistral. Use this skill for both Claude code and Tasking.tech agent source. ComfyUI Retro Anime Skill You control workflows in c:\anime-creator that generate images, videos/movie frames, sound effects, and voices using...
|
43 |
| 16990 | godot-mechanic-secrets | thedivergentai/gd-agentic-skills |
Secrets & Easter Eggs (Mechanics) Overview This skill provides reusable components for hiding content behind specific player actions (e.g., Konami code, repetitive interaction) and managing the persistence of these discoveries. Core Components 1. Input Sequence Watcher ( input_sequence_watcher.gd ) A node that listens for a specific sequence of InputEvent s. Use for : Classic "Cheat Codes", hidden debug menus, "Konami Code" implementations. Behavior : Buffers input -> Checks against target -> Em...
|
43 |
| 16991 | ts-jsdoc-expert | gravito-framework/gravito |
TypeScript JSDoc Expert Enhance JSDoc annotations for TypeScript code with focus on AI comprehension. ⚠️ CRITICAL REQUIREMENT: English Only ALWAYS use English for all JSDoc annotations , regardless of: User's language preferences in CLAUDE.md or other configuration files Project's primary language settings User's communication language This is a non-negotiable technical requirement for: ✅ TSDoc/JSDoc standards compliance ✅ International open-source collaboration ✅ IDE and documentation generator...
|
43 |
| 16992 | statistical-power-calculator | dkyazzentwatwa/chatgpt-skills |
Calculate statistical power and determine required sample sizes for hypothesis testing and experimental design. Purpose Experiment planning for: - Clinical trial design - A/B test planning - Research study sizing - Survey sample size determination - Power analysis and validation Features - Power Calculation: Calculate statistical power for tests - Sample Size: Determine required sample size for desired power - Effect Size: Estimate detectable effect size - Multiple Tests: t-test, p...
|
43 |
| 16993 | terraform-ibm-modules-solution-builder | terraform-ibm-modules/terraform-ibm-modules-skills |
Generate robust and reliable terraform-based solutions for IBM Cloud by leveraging curated, IBM-maintained Terraform modules (TIM) as building blocks. About Terraform IBM Modules (TIM) TIM is a comprehensive suite of curated Terraform modules for IBM Cloud: - Each module includes comprehensive documentation and usage examples - Modules are composable - build complex infrastructure by combining them - All modules maintained by IBM following best practices - Examples show how to stitch modu...
|
43 |
| 16994 | pinterest-api | rawveg/skillsforge-marketplace |
Comprehensive assistance with Pinterest API v5 development, including OAuth authentication, pin/board management, analytics, and API integration patterns. When to Use This Skill This skill should be triggered when: - Implementing Pinterest OAuth 2.0 authentication flows - Creating, updating, or managing Pins and Boards via API - Integrating Pinterest analytics and metrics into applications - Building Pinterest API clients or SDKs - Working with Pinterest user account data - Debugging Pi...
|
43 |
| 16995 | writing-skills | zenobi-us/dotfiles |
Writing Skills Overview Writing skills IS Test-Driven Development applied to process documentation. Personal skills live in agent-specific directories ( ~/.claude/skills for Claude Code, ~/.agents/skills/ for Codex) You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes). Core principle: If you didn't watch an agent fail without the skill, you don't know if the...
|
43 |
| 16996 | supabase-admin | erichowens/some_claude_skills |
Supabase Administration Expert Master Supabase schema design, Row Level Security policies, migrations, and performance optimization for production applications. When to Use ✅ USE this skill for: Row Level Security (RLS) policy design and debugging Database migrations and schema changes Auth integration (triggers, profile creation) Query performance optimization Supabase-specific SQL patterns (auth.uid(), auth.jwt()) ❌ DO NOT use for: Supabase Auth UI configuration → use Supabase dashboard ...
|
43 |
| 16997 | codex-cli-specialist | borghei/claude-skills |
Codex CLI Specialist Expert-level guidance for OpenAI Codex CLI: installation, configuration, skill authoring, cross-platform compatibility with Claude Code, and productivity workflows. Keywords codex, codex-cli, openai, skill authoring, agents/openai.yaml, cross-platform skills, claude code, skill conversion, skill index, multi-agent, ai cli tools, developer productivity, codex configuration, skill management Table of Contents Quick Start Tools Overview Core Workflows Codex CLI Configuration De...
|
43 |
| 16998 | candid-init | ron-myers/candid |
Technical.md and Config Generator You are a senior technical architect conducting a thorough codebase audit. Your job is to generate a Technical.md that: References specific files and paths from this project Captures architecture decisions and how to enforce them Documents actual patterns found in the code with examples Identifies gaps between current state and best practices The output should feel like it was written by someone who spent days understanding THIS specific codebase - not a gene...
|
43 |
| 16999 | accessibility-engineer | mae616/design-skills |
Accessibility Engineer Skill When to Apply Apply this skill when the request involves: Accessibility, a11y, WAI-ARIA, screen reader support, semantic HTML, keyboard navigation, focus management アクセシビリティ対応、WAI-ARIA、スクリーンリーダー対応、セマンティックHTML、キーボード操作、フォーカス管理 Any UI implementation (should be applied alongside other skills) Core Principles (Most Important) Native elements first. Solve with proper HTML elements ( button , a , label , input , etc.) before reaching for ARIA. ARIA is minimal. Don't add rol...
|
43 |
| 17000 | go-skills | llama-farm/llamafarm |
Go Skills for LlamaFarm CLI Shared Go best practices for LlamaFarm CLI development. These guidelines ensure idiomatic, maintainable, and secure Go code. Tech Stack Go 1.24+ Cobra (CLI framework) Bubbletea (TUI framework) Lipgloss (terminal styling) Directory Structure cli/ cmd/ Command implementations config/ Configuration types and loading orchestrator/ Service management utils/ Shared utilities version/ Version and upgrade handling internal/ ...
|
43 |