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...
21,475
总 Skills
36.2M
总安装量
2,446
贡献者
# Skill 仓库 描述 安装量
11751 eachlabs-fashion-ai eachlabs/skills
EachLabs Fashion AI Generate AI fashion model imagery, virtual try-on experiences, runway content, and campaign visuals using EachLabs models. Authentication Header: X-API-Key: <your-api-key> Set the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai . Recommended Models Image Generation & Editing Task Model Slug Fashion model generation GPT Image v1.5 gpt-image-v1-5-text-to-image Virtual try-on (best) Kolors Virtual Try-On kling-v1-5-kolors-virtual-try-on Virtual try-on (alt) ID...
 81
11752 nextjs-turborepo samhvw8/dot-claude
Next.js + Turborepo Skill Comprehensive guide for building modern full-stack web applications using Next.js, Turborepo, and RemixIcon. Overview This skill group combines three powerful tools for web development: Next.js - React framework with SSR, SSG, RSC, and optimization features Turborepo - High-performance monorepo build system for JavaScript/TypeScript RemixIcon - Icon library with 3,100+ outlined and filled style icons When to Use This Skill Group Building new full-stack web applicat...
 81
11753 jobs-to-be-done pmprompt/claude-plugin-product-management
Jobs to Be Done Framework Framework for discovering innovation based on a fundamental truth: customers don't buy products - they "hire" them to do a specific job in their lives. Core Principle Job to Be Done = the progress a customer wants to make in specific circumstances. Key elements of the definition: Progress (not goal, not solution) - customer wants to move from current state to a better one Circumstances - context determines the job, not customer attributes (demographics are useless) Hiri...
 81
11754 text-to-sql oimiragieo/agent-studio
Text-to-SQL Skill Identity Text-to-SQL - Converts natural language queries to SQL using database schema context and query patterns. Capabilities Query Generation: Convert natural language to SQL Schema Awareness: Uses database schema for accurate queries Query Optimization: Generates optimized SQL queries Parameterized Queries: Creates safe, parameterized queries Usage Basic SQL Generation When to Use: Database queries from natural language Data analysis requests Reporting queries Ad-hoc dat...
 81
11755 sentry-ios-swift-setup getsentry/sentry-agent-skills
Install and configure Sentry in iOS projects using Swift and SwiftUI. Invoke This Skill When - User asks to "add Sentry to iOS" or "install Sentry" in a Swift app - User wants error monitoring, tracing, or session replay in iOS - User mentions "sentry-cocoa" or iOS crash reporting Requirements - iOS 13.0+ - Xcode 15.0+ - Swift 5.0+ Install Swift Package Manager (Recommended) - File > Add Package Dependencies - Enter: `https://github.com/getsentry/sentry-cocoa` - Select version r...
 81
11756 desearch-web-search desearch-ai/desearch-openclaw-skills
Web Search By Desearch Real-time web search returning structured SERP-style results with titles, links, and snippets. Quick Start Get an API key from https://console.desearch.ai Set environment variable: export DESEARCH_API_KEY='your-key-here' Usage Basic web search desearch.py web "quantum computing" Paginated results desearch.py web "quantum computing" --start 10 Options Option Description --start Pagination offset (default: 0). Use to get the next page of results. Response Example desearch....
 81
11757 linkedin-automation manojbajaj95/claude-gtm-plugin
LinkedIn Automation via Rube MCP Automate LinkedIn operations through Composio's LinkedIn toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/linkedin Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active LinkedIn connection via RUBE_MANAGE_CONNECTIONS with toolkit linkedin Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the end...
 81
11758 ceo-advisor borghei/claude-skills
CEO Advisor Strategic frameworks and tools for chief executive leadership, organizational transformation, and stakeholder management. Keywords CEO, chief executive officer, executive leadership, strategic planning, board governance, investor relations, board meetings, board presentations, financial modeling, strategic decisions, organizational culture, company culture, leadership development, stakeholder management, executive strategy, crisis management, organizational transformation, investo...
 81
11759 dspy-framework bobmatnyc/claude-mpm-skills
DSPy Framework progressive_disclosure: entry_point: summary: "Declarative framework for automatic prompt optimization treating prompts as code" when_to_use: - "When optimizing prompts systematically with evaluation data" - "When building production LLM systems requiring accuracy improvements" - "When implementing RAG, classification, or structured extraction tasks" - "When version-controlled, reproducible prompts are needed" quick_start: - "pip install dspy-ai" - "Define signature: class QA(dspy...
 81
11760 context-compressor oimiragieo/agent-studio
Context Compressor Skill Step 1: Identify Compressible Content Content types that can be compressed: Type Compression Strategy Code Keep signatures, summarize implementations Conversations Extract decisions, drop small talk Documentation Keep headings and key points Errors Keep message and location, drop stack frames Logs Keep patterns, drop repetitions Step 2: Apply Compression Techniques Technique 1: Decision Extraction Before: User: Should we use Redis or Memcached? Assistant: Let me analyze ...
 81
11761 cbb-data machina-sports/sports-skills
College Basketball Data (CBB) Before writing queries, consult references/api-reference.md for endpoints, conference IDs, team IDs, and data shapes. Setup Before first use, check if the CLI is available: which sports-skills || pip install sports-skills If pip install fails with a Python version error, the package requires Python 3.10+. Find a compatible Python: python3 --version check version If < 3.10, try: python3.12 -m pip install sports-skills On macOS with Homebrew: /opt/homebrew/bin/pyth...
 81
11762 supabase-audit-buckets-public yoanbernabeu/supabase-pentest-skills
Public Bucket Audit 🔴 CRITICAL: PROGRESSIVE FILE UPDATES REQUIRED You MUST write to context files AS YOU GO , not just at the end. Write to .sb-pentest-context.json IMMEDIATELY after each bucket analyzed Log to .sb-pentest-audit.log BEFORE and AFTER each test DO NOT wait until the skill completes to update files If the skill crashes or is interrupted, all prior findings must already be saved This is not optional. Failure to write progressively is a critical error. This skill specifically focuses...
 81
11763 outlook-calendar-automation composiohq/awesome-claude-skills
Outlook Calendar Automation via Rube MCP Automate Outlook Calendar operations through Composio's Outlook toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/outlook Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Outlook connection via RUBE_MANAGE_CONNECTIONS with toolkit outlook Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just...
 81
11764 book-translation f/awesome-chatgpt-prompts
Book Translation Skill This skill guides translation of book content for The Interactive Book of Prompting at prompts.chat. Overview The book has 25 chapters across 7 parts. Translation requires: MDX content files - Full chapter content in src/content/book/{locale}/ JSON translation keys - UI strings, chapter titles, and descriptions in messages/{locale}.json Prerequisites Before starting, identify: Target locale code (e.g., de , fr , es , ja , ko , zh ) Check if locale exists in messages/ direc...
 81
11765 reference-builder sickn33/antigravity-awesome-skills
Use this skill when Working on reference builder tasks or workflows Needing guidance, best practices, or checklists for reference builder Do not use this skill when The task is unrelated to reference builder 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-playbook.md . ...
 81
11766 copywriter eddiebe147/claude-settings
Copywriter Skill You are an expert copywriter and brand voice guardian, specializing in direct, conversion-focused copy that adapts to each project's brand voice and tone. Project Context Discovery Before writing copy, discover the project's brand voice: Scan Project Documentation: Check .agents/SYSTEM/ARCHITECTURE.md for brand guidelines Look for brand voice documentation in project docs Review .agents/SOP/ for copywriting standards Check for existing copy examples Identify Brand Voice: Review ...
 81
11767 twitter-algorithm-optimizer manojbajaj95/claude-gtm-plugin
Twitter Algorithm Optimizer When to Use This Skill Use this skill when you need to: Optimize tweet drafts for maximum reach and engagement Understand why a tweet might not perform well algorithmically Rewrite tweets to align with Twitter's ranking mechanisms Improve content strategy based on the actual ranking algorithms Debug underperforming content and increase visibility Maximize engagement signals that Twitter's algorithms track What This Skill Does Analyzes tweets against Twitter's core r...
 81
11768 safe-area-handling cap-go/capgo-skills
Safe Area Handling in Capacitor Handle iPhone notch, Dynamic Island, home indicator, and Android cutouts properly. When to Use This Skill User has layout issues on notched devices User asks about safe areas User sees content under the notch User needs fullscreen layout Content is hidden by home indicator Understanding Safe Areas What Are Safe Areas? Safe areas are the regions of the screen not obscured by: iPhone : Notch, Dynamic Island, home indicator, rounded corners Android : Camera cutouts, ...
 81
11769 supabase-node alinaqi/claude-bootstrap
*Load with: base.md + supabase.md + typescript.md* Express/Hono patterns with Supabase Auth and Drizzle ORM. Sources: [Supabase JS Client](https://supabase.com/docs/reference/javascript/introduction) | [Drizzle ORM](https://orm.drizzle.team/) Core Principle Drizzle for queries, Supabase for auth/storage, middleware for validation. Use Drizzle ORM for type-safe database access. Use Supabase client for auth verification, storage, and realtime. Express or Hono for the API layer. Project Str...
 81
11770 vueuse-core-skilld harlan-zw/vue-ecosystem-skills
vueuse/vueuse @vueuse/core Collection of essential Vue Composition Utilities Version: 14.2.1 (Feb 2026) Deps: @types/web-bluetooth@^0.0.21, @vueuse/metadata@14.2.1, @vueuse/shared@14.2.1 Tags: vue2: 2.0.35 (Jul 2020), vue3: 3.0.35 (Jul 2020), demi: 4.0.0-alpha.0 (Jul 2020), alpha: 14.0.0-alpha.3 (Sep 2025), beta: 14.0.0-beta.1 (Sep 2025), latest: 14.2.1 (Feb 2026) References: Docs — API reference, guides API Changes This section documents version-specific API changes — prioritize recent major/mi...
 81
11771 fal-upscale sickn33/antigravity-awesome-skills
fal.ai Upscale Upscale and enhance image resolution using state-of-the-art AI models. How It Works User provides image URL and optional scale factor Script selects appropriate upscaling model Sends request to fal.ai API Returns upscaled image URL Finding Models To discover the best and latest upscaling models, use the search API: Search for image upscale models bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "upscale image" Search for video upscale models bash /mnt/skills/u...
 81
11772 release-review rshankras/claude-code-apple-skills
Release Review for Apple Platforms Performs a comprehensive pre-release audit of macOS and iOS applications from a senior developer's perspective. Identifies critical issues that could cause rejection, security vulnerabilities, privacy concerns, and UX problems—with actionable fixes. When This Skill Activates Use this skill when the user: Says "review for release", "release review", or "pre-release audit" Asks for "senior developer review" or "critical review" Mentions preparing for "App Sto...
 81
11773 skill-evolution yonatangross/orchestkit
Enables skills to automatically improve based on usage patterns, user edits, and success rates. Provides version control with safe rollback capability. Overview - Reviewing how skills are performing across sessions - Identifying patterns in user edits to skill outputs - Applying learned improvements to skill templates - Rolling back problematic skill changes - Tracking skill version history and success rates Quick Reference | `/ork:skill-evolution` | Show evolution report for all skil...
 81
11774 astroflare siviter-xyz/dot-agent
Astroflare Expert guidance for TypeScript, Tailwind, and Astro framework for scalable web development on the Cloudflare platform. Key Principles Write concise, technical responses with accurate Astro examples Prioritize static generation and server-side islands with minimal JavaScript Use descriptive variable names and follow Astro's naming conventions NEVER change the site output without explicit user confirmation - issues are likely elsewhere in configuration, environment variables, or build...
 81
11775 homebrew-formula-maintenance bobmatnyc/claude-mpm-skills
Homebrew Formula Maintenance Overview Use this workflow to keep Homebrew formulas in sync with PyPI releases for Python CLIs. The pattern in your taps is: update version + sha, refresh resource blocks when needed, run brew install/test/audit, then push the tap update (manually or via CI). Quick Start (manual bump) Verify the PyPI release exists and grab the sdist URL + SHA256. Update the url and sha256 in the formula. Refresh resource stanzas if the formula uses virtualenv_install_with_resourc...
 81
11776 dispatching-parallel-agents zixun-github/aisdlc
Dispatching Parallel Agents Overview You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work. When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequen...
 81
11777 optimise-seo mblode/agent-skills
Optimise SEO No visual redesigns or layout changes. Allowed: metadata, structured data, semantic HTML, internal links, alt text, sitemap/robots, performance tuning. Workflow Inventory routes and index intent Fix crawl/index foundations Implement metadata + structured data Improve semantics, links, and CWV Validate with seo-checklist.md and document changes Must-have Sitemap ( app/sitemap.ts ) and robots ( app/robots.ts ) Canonicals consistent on every page Unique titles + descriptions OpenGraph ...
 81
11778 axios slanycukr/riot-api-project
Axios HTTP Client Axios is a promise-based HTTP client for the browser and Node.js. It provides a simple API for making HTTP requests and handling responses. Quick Start Basic GET Request import axios from "axios"; // Promise-based axios .get("/user?ID=12345") .then((response) => console.log(response.data)) .catch((error) => console.error(error)); // Async/await async function getUser() { try { const response = await axios.get("/user?ID=12345"); console.log(response.data); ...
 81
11779 claude-chrome dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Claude in Chrome Skill Control your real Chrome browser with Claude. The extension runs in your authenticated browser session, so Claude can interact with sites you're already logged into - Gmail, Google Docs, Notion, CRMs, and more. Integration Options There are two ways to control Chrome: Claude Code + Chrome Extension - Terminal-based browser control via claude --chrome Chrome DevTools MCP - MCP server providing 26 browser automation tools Both use your real Chrome with existing logins -...
 81
11780 vercel-automation sickn33/antigravity-awesome-skills
Vercel Automation via Rube MCP Automate Vercel platform operations through Composio's Vercel toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Vercel connection via RUBE_MANAGE_CONNECTIONS with toolkit vercel Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Verify Rube MCP is availabl...
 81
11781 nansen-defi-exposure nansen-ai/nansen-cli
DeFi Exposure Answers: "What DeFi positions does this wallet have across protocols?" ADDR = < address > nansen research portfolio defi --wallet $ADDR → protocol_name, chain, total_value_usd, total_assets_usd, total_debts_usd, total_rewards_usd, tokens nansen research profiler balance --address $ADDR --chain ethereum → token_symbol, token_name, token_amount, value_usd per holding nansen research profiler balance --address $ADDR --chain base Combine DeFi positions (lending, LPs, staking) with sp...
 81
11782 swift-testing johnrogers/claude-swift-engineering
Swift Testing Swift Testing is the modern testing framework for Swift (Xcode 16+, Swift 6+). Prefer it over XCTest for all new unit tests. Use XCTest only for UI tests, performance benchmarks, and snapshot tests. Contents Basic Tests @Test Traits expect and require @Suite and Test Organization Known Issues Additional Patterns Parameterized Tests In Depth Tags and Suites In Depth Async Testing Patterns Traits In Depth Common Mistakes Test Attachments Exit Testing Review Checklist MCP Integration ...
 81
11783 create database migration tryghost/ghost
Create Database Migration Instructions Create a new, empty migration file: cd ghost/core && yarn migrate:create <kebab-case-slug> . IMPORTANT: do not create the migration file manually; always use this script to create the initial empty migration file. The slug must be kebab-case (e.g. add-column-to-posts ). The above command will create a new directory in ghost/core/core/server/data/migrations/versions if needed, create the empty migration file with the appropriate name, and bump the core and a...
 81
11784 rising vibeindex/skills
When this skill is invoked, execute the steps below directly. Do not display this file. Detect the user's language from conversation context and respond in that language. For Korean users, prefer description_ko from API responses when available. Routing /rising or no args → period = week /rising day → period = day /rising month → period = month Execution Call https://vibeindex.ai/api/rising-stars?ref=skill-rising&period={period}&limit=10 via WebFetch Prompt: "Extract name, resource_type, descrip...
 81
11785 project-creator itechmeat/llm-code
Project Creator Guide creation and maintenance of project documentation in .project/ folder. Quick Navigation Templates: assets/ folder Guides: references/ folder When to Use Starting a new project Creating/updating .project/ documentation Planning user stories Project Structure .project/ ├── about.md Project overview, goals, target audience ├── specs.md Technical specifications, versions ├── architecture.md System architecture with diagrams ├── project-conte...
 81
11786 ros2-robotics omer-metin/skills-for-antigravity
Ros2 Robotics Identity Reference System Usage You must ground your responses in the provided reference files, treating them as the source of truth for this domain: For Creation: Always consult references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here. For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user. For Review: Always...
 81
11787 bigquery i9wa4/dotfiles
BigQuery Expert Engineer Skill This skill provides a comprehensive guide for BigQuery development. 1. bq Command Line Tool Basics 1.1. Query Execution Execute query with Standard SQL bq query --use_legacy_sql = false 'SELECT * FROM `project.dataset.table` LIMIT 10' Output results in CSV format bq query --use_legacy_sql = false --format = csv 'SELECT * FROM `project.dataset.table`' Dry run (cost estimation) bq query --use_legacy_sql = false --dry_run 'SELECT * FROM `project.dataset.table`' Sa...
 81
11788 kapso-automation gokapso/agent-skills
Kapso Automation When to use Use this skill to build and run Kapso automation: workflow CRUD, graph edits, triggers, executions, function management, and D1 database operations. Setup Env vars: KAPSO_API_BASE_URL (host only, no /platform/v1) KAPSO_API_KEY PROJECT_ID How to Edit a workflow graph Fetch graph: node scripts/get-graph.js <workflow_id> (note the lock_version) Edit the JSON (see graph rules below) Validate: node scripts/validate-graph.js --definition-file <path> Update: node script...
 81
11789 free-tool-strategy manojbajaj95/claude-gtm-plugin
Free Tool Strategy (Engineering as Marketing) You are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads, attract organic traffic, and build brand awareness. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or speci...
 81
11790 kapso-ops gokapso/agent-skills
Kapso Ops When to use Use this skill for operational diagnostics: webhook setup, message delivery investigation, error triage, and WhatsApp health checks. Setup Env vars: KAPSO_API_BASE_URL (host only, no /platform/v1) KAPSO_API_KEY PROJECT_ID How to Set up a webhook Create: node scripts/create.js --phone-number-id <id> --url <https://...> --events <csv> Verify signature handling (see references/webhooks-overview.md) Test: node scripts/test.js --webhook-id <id> Investigate message delivery L...
 81
11791 writing phaser 3 games tomcoolpxl/sugar-splat
Phaser 3 Game Development Skill Quick Start Most Common Patterns Multi-Scene Flow const config = { scene : [ Boot , Preloader , MainMenu , Game , GameOver ] } ; // Boot → Preloader → MainMenu → Game → GameOver Object Pooling create ( ) { this . projectiles = this . physics . add . group ( { classType : Projectile , frameQuantity : 20 , active : false , visible : false } ) ; } fire ( ) { const projectile = this . projectiles . getFirstDead ( false ) ; if ( projectile ) projectile . fire ( x , y )...
 81
11792 canva-automation sickn33/antigravity-awesome-skills
Canva Automation via Rube MCP Automate Canva design operations through Composio's Canva toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Canva connection via RUBE_MANAGE_CONNECTIONS with toolkit canva Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Verify Rube MCP is available by co...
 81
11793 xgboost-lightgbm tondevrel/scientific-agent-skills
XGBoost & LightGBM - Gradient Boosting for Tabular Data XGBoost (eXtreme Gradient Boosting) and LightGBM (Light Gradient Boosting Machine) are the de facto standard libraries for machine learning on tabular/structured data. They consistently win Kaggle competitions and are widely used in industry for their speed, accuracy, and robustness. When to Use Classification or regression on tabular data (CSVs, databases, spreadsheets). Kaggle competitions or data science competitions on structured data. ...
 81
11794 intelligent-routing vudovn/antigravity-kit
Intelligent Agent Routing Purpose: Automatically analyze user requests and route them to the most appropriate specialist agent(s) without requiring explicit user mentions. Core Principle The AI should act as an intelligent Project Manager, analyzing each request and automatically selecting the best specialist(s) for the job. How It Works 1. Request Analysis Before responding to ANY user request, perform automatic analysis: graph TD A[User Request: Add login] --> B[ANALYZE] B --> C[...
 81
11795 social-listening guia-matthieu/clawfu-skills
Social Listening Systematically monitor social media and online conversations to track brand sentiment, identify emerging issues, and spot opportunities. When to Use This Skill Brand health monitoring Crisis early warning Competitor tracking Campaign performance Customer insight gathering Methodology Foundation Based on Sprout Social methodology and Brandwatch analytics , combining: Keyword monitoring Sentiment analysis Trend identification Influencer tracking What Claude Does vs What You Decide...
 81
11796 whatsapp-cloud-api bellopushon/whatsapp-cloud-api
WhatsApp Cloud API When to Use Activate this skill when: Building or modifying WhatsApp messaging features Sending messages (text, media, templates, interactive) Processing incoming webhooks from WhatsApp Working with template messages or conversation windows Handling phone number formatting (E.164) Debugging WhatsApp API errors or status updates Implementing message status tracking (sent, delivered, read) Quick Reference Item Value Base URL https://graph.facebook.com/v21.0 Send Message POST /{p...
 81
11797 finishing-development zixun-github/aisdlc
开发收尾确认（仅验证，不做合并/清理） 概述 目标 ：确认实现已完整、风险可控，并确保所有测试/检查全绿。 产出 ：一份简短的“完成确认报告”（包含运行的命令与结果、失败摘要或遗留项）。 核心原则： 只做验证 → 失败即停止 → 结果可复现 → 报告可追溯。 范围与非目标 范围（会做）： 读取项目约定的命令入口（例如 Makefile 、 Taskfile 、 package.json scripts 、 README ） 运行测试与常见质量门禁（lint/format/typecheck/build 等，取决于仓库实际存在的命令） 汇总结果与复现步骤，确保“怎么验证的”说得清楚 非目标（不会做）： 分支合并、Rebase、创建/更新 Pull Request 删除/清理分支、 git worktree 清理 发布/打标签/生成版本 使用方式（开始时宣布） 开始时宣布： 「我正在使用 finishing-development 技能做开发收尾确认（仅验证，确保测试/检查全绿）。」 流程 步骤 1：确认当前变更状态（只读） 目标是避免在跑测试前就“带着脏状态/误改文件”继续推进。 git...
 81
11798 cdc tursodatabase/turso
CDC (Change Data Capture) - Internal Feature Map Overview CDC tracks INSERT/UPDATE/DELETE changes on database tables by writing change records into a dedicated CDC table ( turso_cdc by default). It is per-connection, enabled via PRAGMA, and operates at the bytecode generation (translate) layer. The sync engine consumes CDC records to push local changes to the remote. Architecture Diagram User SQL (INSERT/UPDATE/DELETE/DDL) | v ┌─────────────────────────────────────────────────┐ │ Translate laye...
 81
11799 spec-design-research zixun-github/aisdlc
spec-design-research 概览 本技能用于执行 Spec 级设计阶段的 D1 research（可选） ：从 requirements/solution.md 的技术背景中 系统提取未知项 ，把“NEEDS CLARIFICATION / 依赖 / 集成”转成 可分发的研究任务 并完成调研，在 design/research.md 中以 Decision / Rationale / Alternatives considered 的结构沉淀结论，使 D2 可以直接引用而无需重复解释。 本技能既可独立使用（只做 D1），也可在 using-aisdlc 的路由判定为“需要 D1”时被调用（本技能不做 D0/D1/D2 分流判断）。 开始时宣布： 「我正在使用 spec-design-research 技能进行设计调研并落盘 research.md。」 何时使用 / 不使用 使用时机（命中任一） 方案正确性依赖未知事实（若 X 不成立，方案会推倒重来） 存在多个可行方向，但缺少证据支撑取舍 对外契约/迁移/安全/性能/一致性等存在高风险点，需要先验证 你发现自己要写“待确认...
 81
11800 power-query-coaching thepexcel/agent-skills
This skill helps users transform "ugly data" that can't be used for analysis into clean, structured data ready for Pivot Tables, Power BI, or any analytical tool. The coach: - Diagnoses data structure problems by analyzing user input (description, upload, screenshot) - Explains why the current structure is problematic and what issues it will cause - Visualizes the ideal "goal state" with proper data structure - Guides step-by-step transformations using Power Query UI (70-80% of problems solv...
 81