# Voltagent Best Practices: Incorporating VoltAgent Architecture Conventions into Agent Skills
`voltagent-best-practices` is an architecture quick-reference Skill officially maintained by VoltAgent, covering trade-offs between Agent and Workflow, src directory conventions, memory default values, Hono/Elysia/serverless servers, and VoltOps observation access. This article cross-verifies the installation and activation methods, code snippets and precautions based on the official SKILL.md, VoltAgent documentation and VoltAgent/skills repository, and explains the division of labor between it and the create-voltagent scaffolding Skill.
Read More# create-voltagent: Initialize AI Agent Project in Accordance with VoltAgent Specification Using Official Skill
`create-voltagent is an Agent Skill officially maintained by VoltAgent, which guides users to create TypeScript AI Agent projects via the `create-voltagent-app` CLI or complete manual steps. This article is cross-verifies based on the official `SKILL.md`, Quick Start and VoltAgent/skills repository: it covers the installation and activation methods, Hono/Elysia and six model providers, directory and environment variable conventions, weather Tool and reimbursement approval Workflow examples, as well as its differences from the general "project scaffolding" Skill.
Read MoreWrite Your First Agent Skill Using the Official template-skill
Template-skill is the starting skeleton of Skill in Anthropic's official repository anthropics/skills, with only one SKILL.md file containing name and description placeholders in the directory. Agent Skills became an open standard in December 2025, and the same file can be enabled by scanning directories in Cursor, Claude Code, and Codex CLI respectively. This article follows the official template and agentskills.io specifications to explain the frontmatter fields, directory structure, installation paths of each tool, and how to fill in the template to create the first triggerable Skill.
Read More`find-bugs: Let AI scan the current branch for bugs and security issues according to the checklist`
find-bugs is an Agent Skill publicly released by the Sentry Engineering Team in the getsentry/skills repository, which is used to review the changes made in a local branch relative to the default branch. It executes in five stages: obtaining the complete diff via Git and GitHub CLI, mapping the attack surface, going through 11 security checklists such as Injection, XSS, authentication, and IDOR item by item, verifying false positives, and finally generating a report with evidence, while explicitly stating that it will not modify any code. It can be installed via the Claude Plugin Marketplace or `npx skills add`, and is compatible with tools that support SKILL.md such as Cursor, Claude Code, and Codex.
Read More# 正确的翻译结果如下： Configure `uv`, `ruff` and `ty` for Python Projects with the `modern-python` Skill
Trail of Bits rebranded its internal cookiecutter-python template as Agent Skill modern-python, replacing pip, flake8, black, mypy and pre-commit with uv, ruff, ty, pytest and prek. This article verifies the installation method, minimal project, PEP 723 scripts and migration steps from requirements.txt / setup.py based on the official SKILL.md and documentation site, and notes limitations such as Python 3.11+ requirement and the beta status of ty.
Read More# shadcn Skill: Let AI Search, Install and Combine shadcn/ui Components According to Project Configuration
shadcn is the official Agent Skill for shadcn/ui. After installation, it will read the project's components.json, inject the framework, aliases, installed components, icon library and underlying primitives via `shadcn info --json`, then search, install, debug and stitch together UIs according to the official combination rules. It was released alongside CLI v4 in March 2026, and can be added to tools like Cursor, Claude Code and Codex via `pnpm dlx skills add shadcn/ui`, preventing assistants from writing components that do not match the project based on memory.
Read More# 翻译结果： firecrawl-cli: Let AI Agents Scrape, Search, Crawl and Map Web Pages via CLI
firecrawl-cli is the official Firecrawl Agent Skill (located in the directory skills/firecrawl-cli, with the frontmatter named firecrawl). It enables assistants such as Cursor, Claude Code, and Codex to search, scrape, map, crawl and interact with web pages via the Firecrawl CLI, with results saved in .firecrawl/ in Markdown/JSON format. Based on the official SKILL.md and CLI documentation, this article explains the installation and authentication procedures, the workflow of search→scrape→map→crawl→interact, as well as key notes including credits and rate limits for users without an API key.
Read MoreImprove Codebase Architecture: Let AI Conduct Architecture Review First Before Deciding Where to Modify
Matt Pocock’s `improve-codebase-architecture` is a user-invoked Agent Skill: it scans for shallow modules and leaky seams based on recent commit hotspots, filters candidates using deletion tests, drafts deepening opportunities into an off-repo HTML report (built with Tailwind + Mermaid), then conducts a grilling on the item you select. It does not modify business code, with the output being testable and navigable architectural decisions, before proceeding to to-spec, to-tickets and implementation stages. It is suitable for regular technical debt governance and structural health checks before major overhauls, rather than automated refactoring.
Read MoreUse Matt Pocock's TDD Skills for Vertical Slice Test-Driven Development
This article introduces Matt Pocock's tdd Skill constrained programming Agent that follows vertical slice TDD: first agree on the public seams, then write exactly one failing test and just enough implementation code to pass it each time. Based on GitHub's SKILL.md, tests.md, mocking.md and aihero.dev, the article sorts out the testing standards, three anti-patterns, mocking boundaries, installation methods for Cursor / Claude Code / Codex, as well as restrictions such as refactoring being moved to code review and not suitable for glue code.
Read Moregrill-me: Before you start coding, let the Agent ask you thoroughly first
grill-me is the user-triggered entry point in Matt Pocock’s skill set: before the Agent takes action, it conducts round-by-round questioning via a decision tree to refine unformed ideas into actionable commitments. It is stateless, does not write files, and the topics do not have to be related to code. The actual interview loop is located in the grilling directory within the same repository, and simply deploying grill-me often fails to run properly. Based on the official SKILL.md and aihero.dev documentation, this article organizes the installation method, question format, the division of labor between grill-with-docs and wayfinder, as well as common pitfalls such as passive nodding, overly broad scope, and unloaded Skill.
Read MoreAdding Analytics: Let AI Agent Integrate PostHog into Web Applications According to Standard Procedures
# 官方正式翻译结果： adding-analytics is a SKILL.md in the awesome-cursor-skills repository, which formalizes the process of integrating PostHog into web applications: identify the framework, install posthog-js/posthog-node, initialize the Provider, supplement pageview tracking for SPAs, manage keys using environment variables, and add custom events, Feature Flags and session replays as needed. This article cross-verifies based on the original Skill content and official documents of PostHog, Cursor, Claude Code and Codex, explains the installation directory, reproducible examples, as well as the differences between variable names, React package paths, pageview default behavior, input desensitization and other aspects compared with current official documents.
Read MoreDatabase Design: Let AI Agents Design Table Relationships, Indexes, Constraints and ORM According to Specifications
# SKILL.md for Database Design (Included in awesome-cursor-skills) ## Overview This is a database modeling skill collected in awesome-cursor-skills, which covers entity identification, table relationships, constraints, indexes, and Prisma/Drizzle configuration. ## Six-step Workflow Verified against the official original text, the workflow is as follows: 1. **Entity Identification**: Extract core business entities from requirements 2. **Define Entity Attributes**: Clarify each entity's fields and data types 3. **Establish Table Relationships**: Map one-to-one, one-to-many, and many-to-many associations between entities 4. **Set Up Constraints**: Add NOT NULL, unique, primary key, foreign key and other constraints to ensure data integrity 5. **Design Indexes**: Create appropriate indexes to optimize query performance 6. **Generate ORM Configuration**: Write standardized Prisma or Drizzle schema files based on the designed database structure ## PostgreSQL Example & Installation Method ### Example Code ```sql -- Sample PostgreSQL table creation script CREATE TABLE users ( id SERIAL PRIMARY KEY, username VARCHAR(50) UNIQUE NOT NULL, email VARCHAR(255) UNIQUE NOT NULL, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ); CREATE TABLE posts ( id SERIAL PRIMARY KEY, title VARCHAR(255) NOT NULL, content TEXT, author_id INTEGER NOT NULL, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP, FOREIGN KEY (author_id) REFERENCES users(id) ON DELETE CASCADE ); -- Sample index CREATE INDEX idx_posts_author_id ON posts(author_id); ``` ### Prisma Configuration Example ```prisma generator client { provider = "prisma-client-js" } datasource db { provider = "postgresql" url = env("DATABASE_URL") } model User { id Int @id @default(autoincrement()) username String @unique @db.VarChar(50) email String @unique @db.VarChar(255) createdAt DateTime @default(now()) @db.Timestamptz() posts Post[] } model Post { id Int @id @default(autoincrement()) title String @db.VarChar(255) content String? authorId Int author User @relation(fields: [authorId], references: [id], onDelete: Cascade) createdAt DateTime @default(now()) @db.Timestamptz() } ``` ### Drizzle Configuration Example ```typescript import { pgTable, serial, varchar, text, integer, timestamp, unique } from 'drizzle-orm/pg-core'; export const users = pgTable('users', { id: serial('id').primaryKey(), username: varchar('username', { length: 50 }).notNull(), email: varchar('email', { length: 255 }).notNull(), createdAt: timestamp('created_at').defaultNow().notNull() }, (table) => { return { usernameUnique: unique().on(table.username), emailUnique: unique().on(table.email), } }); export const posts = pgTable('posts', { id: serial('id').primaryKey(), title: varchar('title', { length: 255 }).notNull(), content: text('content'), authorId: integer('author_id').notNull(), createdAt: timestamp('created_at').defaultNow().notNull() }, (table) => { return { authorRef: foreignKey({ columns: [table.authorId], foreignColumns: [users.id] }).onDelete('cascade'), authorIndex: index('idx_posts_author_id').on(table.authorId) } }); ``` ## Supplementary Role of AI Programming This skill makes up for the shortcomings of AI programming in schema design: 1. Provides standardized, step-bysted operating specifications to avoid AI from generating incomplete or non-compliant database schemas 2. Combines business requirements with technical implementation, helping AI transform abstract business logic into a practical, production-ready database structure 3. Standardizes the connection between logical design and physical implementation, ensuring the consistency of schema design from demand analysis to ORM code generation ## Usage Restrictions 1. **PostgreSQL Dialect Limitation**: The current skill takes PostgreSQL as the only demonstration database, and may need to be adjusted when adapting to MySQL, SQL Server and other relational databases 2. **ORM Scope Limitation**: Only covers Prisma and Drizzle two mainstream Node.js ORM frameworks, and is not applicable to ORM tools in other programming languages or non-mainstream Node.js ORMs 3. **Basic Database Design Only**: Focuses on conventional relational database modeling, and does not cover special scenarios such as distributed databases, columnar storage databases, and non-relational databases 4. Requires manual verification: AI generated content still needs developers to check for business matching, performance bottlenecks and compliance issues in actual production environments
Read More# Adding Stripe: Enabling AI Agents to Integrate Stripe Payments via Standard Procedures
# Adding Stripe is a community Agent Skill in awesome-cursor-skills, compiling Stripe Checkout, subscription Webhooks and Customer Portal into a 7-step checklist. Based on the original SKILL.md text and cross-referenced with the documentation for Stripe Checkout, Webhooks, Billing Portal and Cursor Skills, this article explains what problem it solves, how to install it in Cursor / Claude Code / Codex, as well as usage notes such as signature verification, Customer ID and API version.
Read MoreUse recording-browser-flow-as-test: Walk through the process in the browser and automatically generate Playwright tests
# Introduction to `recording-browser-flow-as-test` in spencerpauly/awesome-cursor-skills: This tool allows users to walk through user workflows step-by-step using Cursor's built-in browser, record accessibility tree information via `browser_snapshot`, and then generate Playwright tests that use stable locators such as `getByRole` and `getByLabel`. This article verifies the installation commands, prerequisites, recording steps, assertion and hardening suggestions, as well as inapplicable scenarios such as 2FA and verification codes.
Read More# Accessibility Auditing: Performing Accessibility Audits Using Cursor Browser's ARIA Tree
### Translated Abstract: Introducing accessibility-auditing in spencerpauly/awesome-cursor-skills: Leveraging Cursor's built-in browser tools including `browser_navigate`, `browser_snapshot` and `browser_press`, it conducts audits on the page ARIA tree covering missing labels, semantic HTML, keyboard navigation order, ARIA misuses and color contrast issues. It generates a categorized report with Critical/Warnings/Passed statuses and can directly modify the source code. The document also explains the installation methods via `.cursor/skills` directory or `npx skills add` command, as well as applicable scenarios and compliance review considerations.
Read MoreVisual QA Testing in Cursor: Capture Screenshots, Console Logs and Network Requests in One Go
visual-qa-testing is an Agent Skill in the community repository awesome-cursor-skills, which guides Cursor Agent to use the built-in browser (cursor-ide-browser) to perform visual QA after modifying the UI: confirm the development service, take page screenshots, check console errors and network requests, and conduct verification after interacting with button forms. Based on SKILL.md and Cursor's official Skills/Browser documentation, this article explains its positioning, installation directory and npx skills installation method, typical calling steps, as well as precautions such as relying on the built-in browser and being an alternative to non-test frameworks.
Read MoreLet Agent fix itself until all tests pass with grinding-until-pass
### 介绍 This article introduces `grinding-until-pass` from spencerpauly/awesome-cursor-skills: It enables the Agent to independently fix issues until tests, builds, or lint checks pass via the `fix→run→check` loop. We verify that the steps follow the official SKILL.md rules, including iterating within 10 times, fixing one thing at a time, and prohibiting deleting tests or suppressing errors. We also explain the installation methods using `npx skills` or copying the skill to `.cursor/skills`, along with target command examples and advanced usage of Cursor Hooks. This skill is suitable for scenarios such as large-scale refactoring, dependency upgrades, and clearing failed builds after merging branches; manual intervention is required for slow tests or when design changes are needed.
Read MoreBest-of-n-solving: Isolate Worktree to Parallelly Test Multiple Solutions and Then Merge the Optimal One
This article introduces best-of-n-solving from spencerpauly/awesome-cursor-skills: When facing complex refactoring, tricky bugs or architecture selection, first define 2 to 3 strategies, then use Cursor's best-of-n-runner to attempt them in parallel in isolated git worktrees, and select the optimal solution for merging based on testing, implementation quality, performance and maintainability. The article verifies the four-step process in the official SKILL.md, the installation methods of npx skills or manual installation to .cursor/skills, as well as applicable scenarios and precautions such as "do not use Best-of-N for simple problems".
Read MoreUse expo-native-ui to let AI write Expo interfaces that look more like native apps
### Official Translation: This introduces Expo's official Agent Skill expo-native-ui (v1.1.1): it teaches AI to build Expo screens that closely match the system's visual style following conventions such as Apple HIG, semantic colors, native controls, and prioritizing Reanimated and Expo Go. The article verifies the installation methods of Cursor / Claude Code / Codex, the Color API and animation examples, and explains that navigation should be paired with expo-router, as well as the differences in division of labor with expo-ui.
Read More# remotion-best-practices: Let AI Write Remotion Programmatic Videos According to Specifications
This article introduces Remotion's official Agent Skill `remotion-best-practices`: as the main entry point, it routes sub-skills such as project creation, Markup, maps, subtitles, Studio, rendering, and upgrades to agents including Cursor, Claude Code, and Codex. Based on the official `SKILL.md` and documentation, this guide explains installation commands, frame-driven animation specifications (`useCurrentFrame` + `interpolate`), media and resource conventions, as well as preview/frame extraction usage, helping users avoid rendering pitfalls when using AI to program videos.
Read MoreUse supabase-postgres-best-practices to help AI programming assistants master Postgres skills
### 翻译结果： Introduce the Agent Skill `supabase-postgres-best-practices` maintained by Supabase: A tool designed for platforms such as Cursor and Claude Code, it restricts AI when writing SQL, modifying tables and troubleshooting performance based on eight priority rules covering query performance, connection management, RLS, schema and other aspects. The article verifies the official installation commands, rule structure and typical correct and incorrect examples, and explains how it cooperates with Supabase MCP.
Read More# agents-sdk Skill: Build Stateful AI Agents on Cloudflare
### Official Translation: This article introduces Cloudflare's official agents-sdk Skill: it guides AI assistants to prioritize retrieving Agents documentation, and correctly build stateful Agents on Workers / Durable Objects, covering features such as `setState`, `@callable RPC`, scheduling, Workflows, MCP and React hooks. The article provides installation steps, agents dependency verification, wrangler configuration and a Counter example, and marks precautions such as decorators, migrations and experimental features.
Read MoreFrontend Performance Audit with web-perf Skill: Integrate Core Web Vitals into Agent Workflow
### Official Cloudflare Agent Skill `web-perf` Introduction This tool leverages Chrome DevTools MCP to audit Core Web Vitals (LCP, INP, CLS) alongside FCP, TBT, and Speed Index, and troubleshoots issues including render-blocking resources, network dependency chains, layout shifts, and caching problems. The article explains its positioning, five-stage workflow, installation methods in tools such as Cursor, Claude Code, and Codex, mandatory configurations for MCP, typical prompt words and output formats, and reminds users to verify thresholds against current official documentation and avoid hardcoding conclusions without an MCP.
Read MoreWrangler Skill: Enable AI Assistants to Deploy Cloudflare Workers Correctly
This article introduces Cloudflare's official Agent Skill "wrangler": it guides AI programming assistants to prioritize retrieving official documentation and configuration schemas before deploying and managing resources such as Workers, KV, R2, D1, etc., to avoid outdated commands and incorrect bindings. The article covers the positioning of the Skill, its core capabilities, installation and activation in tools including Cursor, Claude Code, Codex and other platforms, typical examples of wrangler.jsonc and commonly used commands, as well as precautions such as key security and local remote binding.
Read MoreOne-click Preview and Deployment of AI-written Projects with deploy-to-vercel
# Official Vercel Labs Agent Skill `deploy-to-vercel` Introduction This article introduces Vercel Labs' official Agent Skill `deploy-to-vercel`: how to install it in tools such as Cursor, Claude Code, and Codex; how to automatically select between `git push`, `vercel deploy`, or an unauthenticated sandbox script based on git remote, `.vercel` association, and CLI login status; how to generate a Preview URL by default; and how to try to advance the project to a long-term automatically deployable link state. All commands and branch logic in this article are verified against the official `SKILL.md (v3.0.0)` and the `skills.sh` installation instructions.
Read More