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...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
5651 workos workos/skills
WorkOS Skill Router How to Use When a user needs help with WorkOS, consult the tables below to route to the right reference. Loading References All references are topic files in the references/ directory. Read the file and follow its instructions (fetch docs first, then use gotchas to avoid common traps). Exception : Widget requests use the workos-widgets skill via the Skill tool — it has its own multi-framework orchestration. Topic → Reference Map AuthKit Installation (Read references/{name}.md...
 663
5652 code-simplifier pproenca/dot-skills
Code Simplifier You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. Refinement Principles 1. Preserve Functionality Never change what the code does - only how it does it. All original features, outputs, ...
 663
5653 figma-use openai/skills
use_figma — Figma Plugin API Skill Use the use_figma tool to execute JavaScript in Figma files via the Plugin API. All detailed reference docs live in references/ . Always pass skillNames: "figma-use" when calling use_figma . This is a logging parameter used to track skill usage — it does not affect execution. If the task involves building or updating a full page, screen, or multi-section layout in Figma from code , also load figma-generate-design . It provides the workflow for discovering desig...
 663
5654 turboquant-pytorch aradotso/trending-skills
TurboQuant PyTorch Skill by ara.so — Daily 2026 Skills collection. From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for compressing LLM KV caches. Achieves 5x compression at 3-bit with 99.5% attention fidelity via two-stage vector quantization. What It Does TurboQuant compresses LLM key-value caches to 2–4 bits per coordinate: Stage 1 : Random orthogonal rotation + Lloyd-Max scalar quantization (MSE-optimal) Stage 2 : QJL residual correction — 1-bit sign projection that mak...
 663
5655 remotion-video wshuyi/remotion-video-skill
Remotion Video 用 React 以编程方式创建 MP4 视频的框架。 核心概念 Composition - 视频的定义（尺寸、帧率、时长） useCurrentFrame() - 获取当前帧号，驱动动画 interpolate() - 将帧号映射到任意值（位置、透明度等） spring() - 物理动画效果 - 时间轴上排列组件 快速开始 创建新项目 npx create-video@latest 选择模板后： cd <project-name> npm run dev 启动 Remotion Studio 预览 项目结构 my-video/ ├── src/ │ ├── Root.tsx 注册所有 Composition │ ├── HelloWorld.tsx 视频组件 │ └── index.ts 入口 ├── public/ 静态资源（音频、图片） ├── remotion.config.ts 配置文件 └── package.json 基...
 662
5656 upstash-workflow lobehub/lobehub
Upstash Workflow Implementation Guide This guide covers the standard patterns for implementing Upstash Workflow + QStash async workflows in the LobeHub codebase. 🎯 The Three Core Patterns All workflows in LobeHub follow the same 3-layer architecture with three essential patterns: 🔍 Dry-Run Mode - Get statistics without triggering actual execution 🌟 Fan-Out Pattern - Split large batches into smaller chunks for parallel processing 🎯 Single Task Execution - Each workflow execution processes ONE ite...
 662
5657 m04-zero-cost zhanghandong/rust-skills
Zero-Cost Abstraction Layer 1: Language Mechanics Core Question Do we need compile-time or runtime polymorphism? Before choosing between generics and trait objects: Is the type known at compile time? Is a heterogeneous collection needed? What's the performance priority? Error → Design Question Show more
 662
5658 refund-page-generator kostja94/marketing-skills
Pages: Refund / Return Policy Guides refund and return policy page content for e-commerce and digital products. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Identify: Product type : Physical, digital, subscription, or mixed Policy : Time window, conditions, process Jurisdiction : Consumer rights (EU, ...
 662
5659 changelog-page-generator kostja94/marketing-skills
Pages: Changelog Guides changelog and release notes pages. Typically at changelog.* subdomain or /changelog . Builds trust, reduces support, increases feature adoption. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .c...
 662
5660 elasticsearch-file-ingest elastic/agent-skills
Elasticsearch File Ingest Stream-based ingestion and transformation of large data files (NDJSON, CSV, Parquet, Arrow IPC) into Elasticsearch. Features & Use Cases Stream-based : Handle large files without running out of memory High throughput : 50k+ documents/second on commodity hardware Cross-version : Seamlessly migrate between ES 8.x and 9.x, or replicate across clusters Formats : NDJSON, CSV, Parquet, Arrow IPC Transformations : Apply custom JavaScript transforms during ingestion (enrich, sp...
 662
5661 debugging tursodatabase/turso
Debugging When to use this skill Encountering runtime errors or exceptions Code produces unexpected output or behavior Performance degradation or memory issues Intermittent or hard-to-reproduce bugs Understanding unfamiliar error messages Post-incident analysis and prevention Instructions Step 1: Gather Information Collect all relevant context about the issue: Error details : Full error message and stack trace Error type (syntax, runtime, logic, etc.) When did it start occurring? Is it reproduci...
 661
5662 copilot-cli giuseppe-trisciuoglio/developer-kit
Copilot CLI Delegation Delegate selected tasks from Claude Code to GitHub Copilot CLI using non-interactive commands, explicit model selection, safe permission flags, and shareable outputs. Overview This skill standardizes delegation to GitHub Copilot CLI ( copilot ) for cases where a different model may be more suitable for a task. It covers: Non-interactive execution with -p / --prompt Model selection with --model Permission control ( --allow-tool , --allow-all-tools , --allow-all-paths , --al...
 661
5663 glossary-page-generator kostja94/marketing-skills
Pages: Glossary Guides glossary page structure, content, and internal linking for SEO. When invoking : On first use , if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exists, read it for industry terms and customer...
 661
5664 customer-stories-page-generator kostja94/marketing-skills
Pages: Customer Stories Guides customer story and case study page content, structure, and conversion. When invoking : On first use , if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exists, read it for product, pro...
 661
5665 showcase-page-generator kostja94/marketing-skills
Pages: Showcase Guides showcase and gallery pages that display user-generated work, creator content, or "made with [product]" examples. Builds community, social proof, and inspiration. Common for design tools, no-code, and creator-focused products. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check fo...
 661
5666 arize-trace arize-ai/arize-skills
Arize Trace Skill Concepts Trace = a tree of spans sharing a context.trace_id , rooted at a span with parent_id = null Span = a single operation (LLM call, tool call, retriever, chain, agent) Session = a group of traces sharing attributes.session.id (e.g., a multi-turn conversation) Use ax spans export to download individual spans, or ax traces export to download complete traces (all spans belonging to matching traces). Security: untrusted content guardrail. Exported span data contains user-gene...
 661
5667 opencli-repair jackwener/opencli
OpenCLI Repair — AI-Driven Adapter Self-Repair When an adapter breaks because a website changed its DOM, API, or auth flow, use this skill to diagnose the failure and patch the adapter. Prerequisites opencli doctor Verify extension + daemon connectivity When to Use This Skill Use when opencli <site> <command> fails with errors like: SELECTOR — element not found (DOM changed) EMPTY_RESULT — no data returned (API response changed) API_ERROR / NETWORK — endpoint moved or broke PAGE_CHANGED — page ...
 660
5668 ads-meta agricidaniel/claude-ads
Meta Ads Deep Analysis Process Collect Meta Ads data (Ads Manager export, Events Manager screenshot, EMQ scores) Read ads/references/meta-audit.md for full 46-check audit Read ads/references/benchmarks.md for Meta-specific benchmarks Read ads/references/scoring-system.md for weighted scoring Evaluate all applicable checks as PASS, WARNING, or FAIL Calculate Meta Ads Health Score (0-100) Generate findings report with action plan What to Analyze Pixel / CAPI Health (30% weight) Meta Pixel installe...
 660
5669 tanstack-virtual tanstack-skills/tanstack-skills
Overview TanStack Virtual provides virtualization logic for rendering only visible items in large lists, grids, and tables. It calculates which items are in the viewport and positions them with absolute positioning, keeping DOM node count minimal regardless of dataset size. Package: @tanstack/react-virtual Core: @tanstack/virtual-core (framework-agnostic) Installation npm install @tanstack/react-virtual Core Pattern import { useVirtualizer } from '@tanstack/react-virtual' function VirtualList ( ...
 660
5670 m01-ownership zhanghandong/rust-skills
Ownership & Lifetimes Layer 1: Language Mechanics Core Question Who should own this data, and for how long? Before fixing ownership errors, understand the data's role: Is it shared or exclusive? Is it short-lived or long-lived? Is it transformed or just read? Error → Design Question Show more
 660
5671 services-page-generator kostja94/marketing-skills
Pages: Services Guides services page content and structure for service-based businesses (consulting, agencies, freelancers). When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .claude/product-marketing-context.md or .cursor/product-marketing-context.md exists, r...
 660
5672 brand-protection kostja94/marketing-skills
Strategy: Brand Protection Guides discovery, reporting, and prevention of brand impersonation—fake websites, phishing sites, trademark infringement, and domain squatting. See domain-selection for defensive domain registration; trust-badges for official site verification signals; about-page for identity declaration. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks ...
 660
5673 kibana-alerting-rules elastic/agent-skills
Kibana Alerting Rules Core Concepts A rule has three parts: conditions (what to detect), schedule (how often to check), and actions (what happens when conditions are met). When conditions are met, the rule creates alerts , which trigger actions via connectors . Authentication All alerting API calls require either API key auth or Basic auth. Every mutating request must include the kbn-xsrf header. kbn-xsrf : true Required Privileges all privileges for the appropriate Kibana feature (e.g., Stack R...
 660
5674 openspec-proposal-creation forztf/open-skilled-sdd
Specification Proposal Creation Creates comprehensive change proposals following spec-driven development methodology. Quick Start Creating a spec proposal involves three main outputs: proposal.md - Why, what, and impact summary tasks.md - Numbered implementation checklist spec-delta.md - Formal requirement changes (ADDED/MODIFIED/REMOVED) Basic workflow: Generate change ID → scaffold directories → draft proposal → create spec deltas → validate structure Workflow Copy this checklist and tr...
 660
5675 aws-sdk-js-v3-usage aws/agent-toolkit-for-aws
Do not use emojis in any code, comments, or output when this skill is active. AWS SDK for JavaScript v3 Package Structure @aws-sdk/client-* — one per service, generated by smithy-typescript ; one-to-one with AWS services and operations @aws-sdk/lib-* — higher-level helpers (e.g. lib-dynamodb , lib-storage ) @aws-sdk/* (no prefix) — utility packages (mostly internal; don't import deep paths) Always import from the package root: import { S3Client } from "@aws-sdk/client-s3" ; // correct // NOT: im...
 659
5676 project-docs jezweb/claude-skills
Project Documentation Generator Generate structured project documentation by analysing the codebase. Produces docs that reflect the actual code , not aspirational architecture. When to Use New project needs initial documentation Docs are missing or stale Onboarding someone to the codebase Post-refactor doc refresh Workflow 1. Detect Project Type Scan the project root to determine what kind of project this is: Indicator Project Type wrangler.jsonc / wrangler.toml Cloudflare Worker vite.config.ts ...
 659
5677 code-reviewer davila7/claude-code-templates
Code Reviewer This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests. Workflow 1. Determine Review Target Remote PR : If the user provides a PR number or URL (e.g., "Review PR 123"), target that remote PR. Local Changes : If no specific PR is mentioned, or if the user asks to "review my changes", target the current local file system states (staged and unstaged changes). 2. Preparation For Remote PRs: Checkout : Use the...
 659
5678 checking-freshness astronomer/agents
Data Freshness Check Quickly determine if data is fresh enough to use. Freshness Check Process For each table to check: 1. Find the Timestamp Column Look for columns that indicate when data was loaded or updated: _loaded_at, _updated_at, _created_at (common ETL patterns) updated_at, created_at, modified_at (application timestamps) load_date, etl_timestamp, ingestion_time date, event_date, transaction_date (business dates) Query INFORMATION_SCHEMA.COLUMNS if you need to see column names. ...
 659
5679 integrations-page-generator kostja94/marketing-skills
Pages: Integrations / Plugins Guides integrations, plugins, and extensions pages. Shows how the product connects with Canva, Slack, Zapier, and other platforms. Common for SaaS, tools, and developer products. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product marketing context first: If .c...
 659
5680 figma-generate-design openai/skills
Build / Update Screens from Design System Use this skill to create or update full-page screens in Figma by reusing the published design system — components, variables, and styles — rather than drawing primitives with hardcoded values. The key insight: the Figma file likely has a published design system with components, color/spacing variables, and text/effect styles that correspond to the codebase's UI components and tokens. Find and use those instead of drawing boxes with hex colors. MANDATORY ...
 659
5681 architect-review sickn33/antigravity-awesome-skills
You are a master software architect specializing in modern software architecture patterns, clean architecture principles, and distributed systems design. Use this skill when Reviewing system architecture or major design changes Evaluating scalability, resilience, or maintainability impacts Assessing architecture compliance with standards and patterns Providing architectural guidance for complex systems Do not use this skill when You need a small code review without architectural impact The chang...
 658
5682 sf-flex-estimator jaganpro/sf-skills
sf-flex-estimator: Agentforce & Data Cloud Flex Credit Estimation Use this skill when the user needs a public-price estimate for: Agentforce prompt + action consumption Data Cloud monthly usage meters Flex Credit scenario planning cost optimization recommendations before build or rollout This skill is for planning and estimation , not implementation. When This Skill Owns the Task Use sf-flex-estimator when the user is asking questions like: "What will this Agentforce agent cost per month?" "Esti...
 658
5683 business-analyst sickn33/antigravity-awesome-skills
Business Analyst Role: Phase 1 - Analysis Specialist Function: Conduct product discovery, research, and create product briefs When to Use This Skill Activate this skill when you need to: Create a product brief for a new product or feature Conduct product discovery and problem analysis Brainstorm and explore product ideas Perform market and competitive research Gather and document requirements Interview stakeholders about needs and pain points Define success metrics and goals Set the foundation b...
 658
5684 dynamodb-toolbox-patterns giuseppe-trisciuoglio/developer-kit
DynamoDB-Toolbox v2 Patterns (TypeScript) Overview This skill provides practical TypeScript patterns for using DynamoDB-Toolbox v2 with AWS SDK v3 DocumentClient. It focuses on type-safe schema modeling, .build() command usage, and production-ready single-table design. When to Use Defining DynamoDB tables and entities with strict TypeScript inference Modeling schemas with item , string , number , list , set , map , and record Implementing GetItem , PutItem , UpdateItem , DeleteItem via .build() ...
 658
5685 discount-marketing-strategy kostja94/marketing-skills
Strategies: Discount Marketing Guides discount and promotional pricing strategy for SaaS, e-commerce, and tools. Covers discount structures, lifetime deals (LTD), redeem codes, Black Friday / Cyber Monday, and campaign design. Aligns with pricing-strategy (base price structure); discounts apply on top of base pricing. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user as...
 658
5686 contest-page-generator kostja94/marketing-skills
Pages: Giveaway / Contest Guides giveaway and contest pages for promotional campaigns. Drives signups, engagement, and viral sharing. Often uses Gleam, Woobox, Viralsweep, or similar. Common for e-commerce, SaaS launches, and community growth. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for pro...
 658
5687 vue vercel-labs/json-render
Vue Based on Vue 3.5. Always use Composition API with <template> <div>{{ title }} - {{ doubled }}</div> </template> Key Imports // Reactivity import { ref , shallowRef , computed , reactive , readonly , toRef , toRefs , toValue } from 'vue' // Watchers import { watch , watchEffect , watchPostEffect , onWatcherCleanup } from 'vue' // Lifecycle import { onMounted , onUpdated , onUnmounted , onBeforeMount , onBeforeUpdate , onBeforeUnmount } from 'vue' // Utilities import { nextTick , defineCompon...
 658
5688 flipoff-split-flap-display aradotso/trending-skills
FlipOff Split-Flap Display Emulator Skill by ara.so — Daily 2026 Skills collection. FlipOff is a pure vanilla HTML/CSS/JS web app that emulates classic mechanical split-flap (flip-board) airport displays. No frameworks, no npm, no build step — open index.html and you have a full-screen retro display with authentic scramble animations and clacking sounds. Installation git clone https://github.com/magnum6actual/flipoff.git cd flipoff Option 1: Open directly open index.html Option 2: Serve locall...
 658
5689 app-store-screenshots-generator aradotso/trending-skills
App Store Screenshots Generator Skill by ara.so — Daily 2026 Skills collection. A skill for AI coding agents (Claude Code, Cursor, Windsurf, Codex, etc.) that generates production-ready App Store screenshots for iOS apps. It scaffolds a Next.js project, designs advertisement-style slides, and exports PNGs at all required Apple resolutions. What This Skill Does Asks about your app's brand, features, and style preferences before building anything Scaffolds a minimal Next.js + TypeScript + Tailwind...
 658
5690 remotion-render inference-sh/skills
Remotion Render Render videos from React/Remotion component code via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Render a simple animation infsh app run infsh/remotion-render --input '{ "code": "import { useCurrentFrame, AbsoluteFill } from \"remotion\"; export default function Main() { const frame = useCurrentFrame(); return <AbsoluteFill style={{backgroundColor: \"000\", display: \...
 657
5691 frontend-design davila7/claude-code-templates
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 657
5692 senior-frontend alirezarezvani/claude-skills
Senior Frontend Complete toolkit for senior frontend with modern tools and best practices. Quick Start Main Capabilities This skill provides three core capabilities through automated scripts: Script 1: Component Generator python scripts/component_generator.py [ options ] Script 2: Bundle Analyzer python scripts/bundle_analyzer.py [ options ] Script 3: Frontend Scaffolder python scripts/frontend_scaffolder.py [ options ] Core Capabilities 1. Component Generator Automated tool for component gen...
 657
5693 feedback-page-generator kostja94/marketing-skills
Pages: Feedback / Roadmap Guides feedback and roadmap pages that collect user input and communicate product direction. Often integrates with Canny, FeatureBase, UserVoice, or similar. Supports product-led growth and community engagement. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for product m...
 657
5694 typescript-write metabase/metabase
TypeScript/JavaScript Development Skill @./../_shared/development-workflow.md @./../_shared/typescript-commands.md
 656
5695 bail camacho/ai-skills
Bail-out protocol: always reflect FIRST, then clean up. Inputs Optional reason string (if not provided, ask for one) Steps Detect current step by examining what exists: What exists Estimated step Just an issue, no branch Step 0 (Capture) .branch-context.md, no worktree Step 1 (Orient) Worktree exists, no code changes Step 2 (Isolate) Plan file on branch Step 3-4 (Design/Review) Code changes committed Step 5-7 (Build/Verify/Archive) PR open on GitHub Step 8 (Ship) Prompt for reason if not provide...
 656
5696 conventional-commit marcelorodrigo/agent-skills
Instructions < description > This file contains a prompt template for generating conventional commit messages. It provides instructions, examples, and formatting guidelines to help users write standardized, descriptive commit messages in accordance with the Conventional Commits specification. </ description > Workflow Follow these steps: Run git status to review changed files. Run git diff or git diff --cached to inspect changes. Stage your changes with git add <file> . Construct your commit mes...
 656
5697 hack yaklang/hack-skills
HACKING SKILLS / HackSkills Overview 这是一个面向 漏洞赏金、Web 安全、API 安全、授权渗透测试 的总入口技能。 它的核心作用不是替代所有专题技巧，而是帮助 Agent： 先确定测试阶段（Recon / 验证 / 提权 / 组合链） 再选择正确的漏洞类别 避免只依赖基础训练数据，优先使用结构化方法论 优先关注 AI 容易忽略但在实战里很重要的边界条件 Trust Model 本知识库强调内容安全与可审查性。 使用时应限定在 授权目标 、 合法研究 、 防御验证 、 漏洞赏金规则允许 的范围内。 不要把这里的技巧用于未授权攻击。 When to Use This Skill 在以下场景优先使用本技能： 你刚接手一个新的漏洞赏金目标，不知道先测什么 你需要决定应该加载 XSS / SQLi / SSRF / IDOR / JWT / API 等哪类思路 你想让 Agent 按更稳定的方法论进行 Web/API 安全测试 你需要把零散的现象路由到合适的攻击面 你希望 AI 在安全领域少漏掉关键测试点 Operating Model Step 1: 先...
 656
5698 pulumi-component pulumi/agent-skills
A ComponentResource groups related infrastructure resources into a reusable, logical unit. Components make infrastructure easier to understand, reuse, and maintain. Components appear as a single node with children nested underneath in `pulumi preview`/`pulumi up` output and in the Pulumi Cloud console. This skill covers the full component authoring lifecycle. For general Pulumi coding patterns (Output handling, secrets, aliases, preview workflows), use the `pulumi-best-practices` skill instead....
 656
5699 legalize-es-spanish-legislation aradotso/trending-skills
Legalize ES — Spanish Legislation Git Repository Skill by ara.so — Daily 2026 Skills collection. What It Is legalize-es is a Git repository containing 8,600+ Spanish laws as Markdown files, with every legislative reform recorded as a Git commit. Each law is a single .md file named by its BOE identifier (e.g. BOE-A-1978-31229.md for the Spanish Constitution). Reform history goes back to 1960. Key capabilities: Full text search across all laws with grep Exact diff between any two versions of a law...
 656
5700 pgmicro-postgres-sqlite aradotso/trending-skills
pgmicro Skill by ara.so — Daily 2026 Skills collection. pgmicro is an in-process reimplementation of PostgreSQL backed by a SQLite-compatible storage engine. It parses PostgreSQL SQL using the real PostgreSQL parser ( libpg_query ) and compiles it directly to SQLite VDBE bytecode, executed by Turso . The result is a fast, embeddable, single-file (or in-memory) database that speaks PostgreSQL — no server process required. Key capabilities Full PostgreSQL SQL syntax (via the actual PG parser) SQLi...
 656