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...
24,454
总 Skills
90.8M
总安装量
2,582
贡献者
# Skill 仓库 描述 安装量
17501 review-pr mblode/agent-skills
Review PR Skill Review the current pull request and write the output to review.json . Context The working directory is the PR branch checkout. The workflow provides an annotated diff in pr_diff.txt . The workflow provides the PR description in pr_description.txt . Focus on files and lines changed by this PR. Do not post comments or reviews to GitHub directly. Review Scope Prioritize correctness, security, error handling, and meaningful performance issues. Include style or nit comments only when ...
 58
17502 code-review-assistant jorgealves/agent_skills
Code Quality Skills This directory contains skills to maintain high standards in professional codebases. Code Review Assistant : Automates the "toilsome" parts of code review (bugs, style, logic). Refactoring Suggester : Helps turn "Junior" code into "Senior" code with clear transformation steps. Documentation Generator : Ensures that knowledge is shared and not stuck in developer heads.
 58
17503 fix-sentry-issues brianlovin/claude-config
Fix Sentry Issues Philosophy The Sentry error is not the problem. It's a signal. Your goal is not to close the Sentry issue. Your goal is to discover the root cause, understand what's wrong with the application, and fix the underlying defect. Closing the Sentry issue is a side effect of doing that correctly. Ask "Why does this fail?" — not "How do I make Sentry quiet?" Never treat log level changes as fixes. A fallback path means degraded user experience; trace why the primary path fails and fix...
 58
17504 adding-memory volcengine/openviking
OpenViking (OV) add-memory The ov add-memory command adds long persistant memory — turning text and structured conversations into searchable, retrievable memories in the OpenViking context database. When to Use After learning something worth remembering across sessions To persist conversation insights, decisions, or findings To build up a knowledge base from interactions When an agent wants to store context for future retrieval Input Modes choose wisely between plain text and multi-turn mode. Mu...
 58
17505 livewire-development laravel/boost
Livewire Development When to Apply Activate this skill when: Creating or modifying Livewire components Using wire: directives (model, click, loading, sort, intersect) Implementing islands or async actions Writing Livewire component tests Documentation Use search-docs for detailed Livewire 4 patterns and documentation. Basic Usage Creating Components Single-file component (default in v4) {{ $assist->artisanCommand('make:livewire create-post') }} Multi-file component {{ $assist->artisanCommand('ma...
 58
17506 vercel-react-native-skills vercel-labs/claude-skills
React Native Skills Comprehensive best practices for React Native and Expo applications. Contains rules across multiple categories covering performance, animations, UI patterns, and platform-specific optimizations. When to Apply Reference these guidelines when: Building React Native or Expo apps Optimizing list and scroll performance Implementing animations with Reanimated Working with images and media Configuring native modules or fonts Structuring monorepo projects with native dependencies Rul...
 58
17507 umbraco-collection-action umbraco/umbraco-cms-backoffice-skills
Umbraco Collection Action What is it? Collection Actions are buttons that appear in a collection's toolbar, providing actions that can be performed on the collection as a whole (not on individual items - those are Entity Bulk Actions). Common examples include "Create New" buttons or export functionality. Actions can either execute code or navigate to a URL. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-overv...
 58
17508 umbraco-tiptap-statusbar-extension umbraco/umbraco-cms-backoffice-skills
Umbraco Tiptap Statusbar Extension What is it? A Tiptap Statusbar Extension adds components to the status bar at the bottom of the Rich Text Editor. Common uses include showing element path (breadcrumb navigation), word count, character count, or other editor state information. Unlike toolbar extensions, statusbar extensions are purely visual/informational elements. Documentation Always fetch the latest docs before implementing: Extension Types : https://docs.umbraco.com/umbraco-cms/customizing/...
 58
17509 vibe-build khazp/vibe-coding-prompt-template
You are the build agent for the vibe-coding workflow. This is Step 5 - the final step where you build the actual MVP. Your Role Execute the plan in AGENTS.md to build the MVP incrementally, testing after each feature. Prerequisites Check for required files: - `AGENTS.md` - REQUIRED (master plan) - `agent_docs/` directory - REQUIRED (detailed specs) - `docs/PRD-*.md` - Reference for requirements - `docs/TechDesign-*.md` - Reference for implementation If missing, suggest running `/vibe-...
 58
17510 vue-test-utils-skilld harlan-zw/vue-ecosystem-skills
vuejs/test-utils @vue/test-utils Version: 2.4.6 (May 2024) Deps: js-beautify@^1.14.9, vue-component-type-helpers@^2.0.0 Tags: latest: 2.4.6 (May 2024), 2.0.0-alpha.0: 2.0.0-alpha.0 (Apr 2020), 2.0.0-alpha.1: 2.0.0-alpha.1 (Apr 2020), 2.0.0-alpha.2: 2.0.0-alpha.2 (Apr 2020), 2.0.0-alpha.3: 2.0.0-alpha.3 (Apr 2020), 2.0.0-alpha.4: 2.0.0-alpha.4 (May 2020), next: 2.4.0-alpha.2 (Jun 2023), 2.0.0-alpha.8: 2.0.0-alpha.8 (Jul 2020), 2.0.0-beta.1: 2.0.0-beta.1 (Aug 2020), 2.0.0-beta.2: 2.0.0-beta.2 (Aug...
 58
17511 skill-creator oimiragieo/agent-studio
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
 58
17512 browser danielmiessler/personal_ai_infrastructure
Browser Automation Automate browser interactions using the browse CLI with Claude. Setup check Before running any browser commands, verify the CLI is available: which browse || npm install -g @browserbasehq/browse-cli Environment Selection (Local vs Remote) The CLI automatically selects between local and remote browser environments based on available configuration: Local mode (default) Uses local Chrome — no API keys needed Best for: development, simple pages, trusted sites with no bot protectio...
 58
17513 workers-performance secondsky/claude-skills
Techniques for maximizing Worker performance and minimizing latency. Quick Wins ``` // 1. Avoid unnecessary cloning // ❌ Bad: Clones entire request const body = await request.clone().json(); // ✅ Good: Parse directly when not re-using body const body = await request.json(); // 2. Use streaming instead of buffering // ❌ Bad: Buffers entire response const text = await response.text(); return new Response(transform(text)); // ✅ Good: Stream transformation return new Response(response.body.pip...
 58
17514 expo-framework-rule oimiragieo/agent-studio
Expo Framework Rule Skill Expo SDK Features and APIs Core Expo Modules FileSystem: import * as FileSystem from 'expo-file-system' ; // Read file const content = await FileSystem . readAsStringAsync ( FileSystem . documentDirectory + 'file.txt' ) ; // Download file const download = await FileSystem . downloadAsync ( 'https://example.com/file.pdf' , FileSystem . documentDirectory + 'file.pdf' ) ; Camera: import { CameraView , useCameraPermissions } from 'expo-camera' ; function CameraScreen ( ) { ...
 58
17515 emotional-narrative dylantarre/animation-principles
Emotional Narrative Think like a storyteller who draws. Every movement is a sentence. Every pause is punctuation. You're not animating shapes—you're animating feelings. Core Mental Model Before animating anything, ask: What does the audience need to feel right now? The same walk cycle can convey confidence, defeat, nervousness, or joy. Motion is emotion made visible. The 12 Principles Through Emotion Anticipation — The breath before the confession. Anticipation isn't just physical preparat...
 58
17516 creative-frontend-aesthetics seika139/dotfiles
Creative Frontend Aesthetics Skill あなたは、統計的にありがちな「AIが生成したっぽい」デザイン（AI slop）から脱却し、ユーザーを驚かせ、喜ばせる独創的なフロントエンドを構築しなければなりません。 重点項目 1. タイポグラフィ 美しく、ユニークで、興味を惹くフォントを選択してください。 回避: Arial, Inter などの汎用フォント。 推奨: フロントエンドの美学を高める特徴的なフォント。 2. カラー & テーマ 一貫した美学（Cohesive aesthetic）を徹底してください。 CSS変数を使用して一貫性を保ち、ぼやけた配色ではなく「強い主色 + 鋭いアクセント」の構成を優先します。 インスピレーション: IDEのテーマ、文化的な美学（サイバーパンク、レトロ、北欧モダンなど）から着想を得てください。 3. モーション (動き) 効果的なアニメーションとマイクロインタラクションを導入します。 HTMLの場合はCSSのみの解決策を、Reactの場合は framer-motion 等のライブラリを優先してください。 戦略: 散発的な動...
 58
17517 jest-testing pluginagentmarketplace/custom-plugin-nodejs
Jest Testing Skill Master testing Node.js applications with Jest - the delightful JavaScript testing framework. Quick Start Test in 3 steps: Install - npm install --save-dev jest supertest Write Test - Create *.test.js files Run - npm test Core Concepts Basic Test Structure // sum.test.js const sum = require('./sum'); describe('sum function', () => { test('adds 1 + 2 to equal 3', () => { expect(sum(1, 2)).toBe(3); }); test('adds negative numbers', () => { expect(sum(-1, -2))....
 58
17518 shadcn-vue noartem/skills
Contains Shell Commands This skill contains shell command directives ( !`command` ) that may execute system commands. Review carefully before installing. shadcn-vue A framework for building ui, components and design systems. Components are added as source code to the user's project via the CLI. IMPORTANT: Run all CLI commands using the project's package runner: npx shadcn-vue@latest , pnpm dlx shadcn-vue@latest , or bunx --bun shadcn-vue@latest — based on the project's packageManager . Examples ...
 58
17519 reportlab ovachiever/droid-tings
ReportLab PDF Generation Overview ReportLab is a powerful Python library for programmatic PDF generation. Create anything from simple documents to complex reports with tables, charts, images, and interactive forms. Two main approaches: Canvas API (low-level): Direct drawing with coordinate-based positioning - use for precise layouts Platypus (high-level): Flowing document layout with automatic page breaks - use for multi-page documents Core capabilities: Text with rich formatting and custom...
 58
17520 product-marketing dengineproblem/agents-monorepo
Product Marketing Context You help users create and maintain a product marketing context document. This captures foundational positioning and messaging information that other marketing skills reference, so users don't repeat themselves. The document is stored at .agents/product-marketing.md . Workflow Step 1: Check for Existing Context First, check if .agents/product-marketing.md already exists. Also check .claude/product-marketing.md and the legacy filename product-marketing-context.md (in eith...
 58
17521 dojo-model dojoengine/book
Dojo Model Generation Create Dojo models that define your game's state using Entity Component System (ECS) patterns. When to Use This Skill "Add a Position model" "Create a Player entity with health and level" "Generate an Inventory model" "Define a model for [game concept]" What This Skill Does Generates Cairo model structs with: [dojo::model] attribute Required trait derivations ( Drop , Serde ) Key field configuration ( [key] ) Field types appropriate to your data Quick Start Interactive mode...
 58
17522 csrf-protection secondsky/claude-skills
CSRF Protection Overview Implement comprehensive Cross-Site Request Forgery protection using synchronizer tokens, double-submit cookies, SameSite cookie attributes, and custom headers. When to Use Form submissions State-changing operations Authentication systems Payment processing Account management Any POST/PUT/DELETE requests Implementation Examples 1. Node.js/Express CSRF Protection // csrf-protection.js const crypto = require('crypto'); const csrf = require('csurf'); class CSRFProtection ...
 58
17523 yaml-config-validator jeremylongshore/claude-code-plugins-plus-skills
Yaml Config Validator Purpose This skill provides automated assistance for yaml config validator tasks within the DevOps Basics domain. When to Use This skill activates automatically when you: Mention "yaml config validator" in your request Ask about yaml config validator patterns or best practices Need help with foundational devops skills covering version control, containerization, basic ci/cd, and infrastructure fundamentals. Capabilities Provides step-by-step guidance for yaml config vali...
 58
17524 answers brave/brave-search-skills
Answers — AI Grounding Requires API Key : Get one at https://api.search.brave.com Plan : Included in the Answers plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe When to Use Use Case Skill Why Quick factual answer (raw context) llm-context Single search, returns raw context for YOUR LLM Fast AI answer with citations answers (single-search) streaming, citations Thorough multi-search deep research answers (research mode) Iterative deep research, synthesized cited answer...
 58
17525 umbraco-unit-testing umbraco/umbraco-cms-backoffice-skills
Umbraco Unit Testing What is it? Unit testing for Umbraco backoffice extensions using @open-wc/testing - a testing framework designed for Web Components and Lit elements. This is the fastest and most isolated testing approach. When to Use Testing context logic and state management Testing Lit element rendering and shadow DOM Testing observable subscriptions and state changes Testing controllers and utility functions Fast feedback during development
 58
17526 domain-dns-ops steipete/agent-scripts
Domain/DNS Ops (Peter) This skill is a thin router: use ~/Projects/manager as truth, run the repo scripts, follow the checklists. Source of truth (read first) ~/Projects/manager/DOMAINS.md (domain -> target map; registrar hints; exclusions) ~/Projects/manager/DNS.md (Cloudflare onboarding + DNS/redirect checklist) ~/Projects/manager/redirect-worker.ts + ~/Projects/manager/redirect-worker-mapping.md (worker redirects) Golden path (new vanity domain -> Cloudflare -> redirect) Decide routing mode...
 58
17527 chatbot designer eddiebe147/claude-settings
Chatbot Designer Design conversational AI chatbots with optimal flows and user experience When to Use This Skill Use this skill when you need to: Automate workflows and processes Integrate tools and systems Optimize technical operations Not recommended for: Tasks requiring creative content manual processes Quick Reference Action Command/Trigger Create chatbot designer chatbot design Review and optimize review chatbot designer Get best practices chatbot designer best practices Core Workflows Work...
 58
17528 umbraco-conditions umbraco/umbraco-cms-backoffice-skills
Umbraco Conditions What is it? Extension Conditions enable developers to declare requirements that must be met before an extension becomes available in the backoffice. They function as gatekeeping mechanisms controlling when and where extensions appear based on context like section, workspace, user permissions, or content type. Multiple conditions use AND logic—all must pass for the extension to display. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umb...
 58
17529 cloud-aliyun-ecs teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 58
17530 defender-for-devops josiahsiegel/claude-plugin-marketplace
🚨 CRITICAL GUIDELINES Windows File Path Requirements MANDATORY: Always Use Backslashes on Windows for File Paths When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Examples: ❌ WRONG: D:/repos/project/file.tsx ✅ CORRECT: D:\repos\project\file.tsx This applies to: Edit tool file_path parameter Write tool file_path parameter All file operations on Windows systems Documentation Guidelines NEVER create new documentation files unless ...
 58
17531 concept-mastery-validator jorgealves/agent_skills
Concept Mastery Validator Purpose and Intent The concept-mastery-validator is a quality assurance tool for educators and mentors. It ensures that the learning journey is logically sound and that students are not asked to perform tasks for which they haven't yet received foundational training. When to Use Curriculum Auditing : Run this after designing a new module to ensure the learning objectives match the suggested projects. Project Refinement : Use this to identify if a project is too difficul...
 58
17532 code-quality-principles athola/claude-night-market
Table of Contents KISS (Keep It Simple, Stupid) YAGNI (You Aren't Gonna Need It) SOLID Principles Quick Reference When Principles Conflict Integration with Code Review Code Quality Principles Guidance on KISS, YAGNI, and SOLID principles with language-specific examples. KISS (Keep It Simple, Stupid) Principle: Avoid unnecessary complexity. Prefer obvious solutions over clever ones. Guidelines Prefer Avoid Simple conditionals Complex regex for simple checks Explicit code Magic numbers/strings...
 58
17533 hig-components-menus raintree-technology/apple-hig-skills
Apple HIG: Menus and Buttons Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Menus should be contextual and predictable. Standard items in standard locations. Follow platform conventions for ordering and grouping. Use standard button styles. System-defined styles communicate affordance and maintain visual consistency. Prefer them over custom designs. Toolbars for frequent actions. Most common...
 58
17534 cli-builder eddiebe147/claude-settings
CLI Builder Skill Overview This skill helps you build professional command-line interfaces with excellent user experience. Covers argument parsing, interactive prompts, progress indicators, colored output, and cross-platform compatibility. CLI Design Philosophy Principles of Good CLI Design Predictable: Follow conventions users expect Helpful: Provide clear help text and error messages Composable: Work well with pipes and other tools Forgiving: Accept common variations in input Design Guidelin...
 58
17535 create-meta-prompts glittercowboy/taches-cc-resources
Every execution produces a SUMMARY.md for quick human scanning without reading full outputs. Each prompt gets its own folder in .prompts/ with its output artifacts, enabling clear provenance and chain detection. <quick_start> Intake: Determine purpose (Do/Plan/Research/Refine), gather requirements Chain detection: Check for existing research/plan files to reference Generate: Create prompt using purpose-specific patterns Save: Create folder in .prompts/{number}-{topic}-{purpose}/ Present: Show...
 58
17536 mcp-builder shipshitdev/library
MCP Server Development Guide Overview Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. Process 🚀 High-Level Workflow Creating a high-quality MCP server involves four main phases: Phase 1: Deep Research and Planning 1.1 Understand Modern MCP Design API Coverage vs. Workflow Tools: Balance comprehensive API endpoint coverag...
 58
17537 pnpm-upgrade openai/openai-agents-js
Use these steps to update pnpm and CI pins without blunt search/replace. Steps (run from repo root) - Update pnpm locally Try `pnpm self-update`; if pnpm is missing or self-update fails, run `corepack prepare pnpm@latest --activate`. - Capture the resulting version as `PNPM_VERSION=$(pnpm -v)`. - Align package.json Open `package.json` and set `packageManager` to `pnpm@${PNPM_VERSION}` (preserve trailing newline and formatting). - Find latest pnpm/action-setup tag Query GitHub API: `c...
 58
17538 chroma orchestra-research/ai-research-skills
Chroma - Open-Source Embedding Database The AI-native database for building LLM applications with memory. When to use Chroma Use Chroma when: Building RAG (retrieval-augmented generation) applications Need local/self-hosted vector database Want open-source solution (Apache 2.0) Prototyping in notebooks Semantic search over documents Storing embeddings with metadata Metrics: 24,300+ GitHub stars 1,900+ forks v1.3.3 (stable, weekly releases) Apache 2.0 license Use alternatives instead: Pin...
 58
17539 controller-setup cartridge-gg/docs
Controller Setup Cartridge Controller is a gaming-focused smart contract wallet for Starknet with session keys, passkeys, and paymaster support. Installation Basic Controller usage pnpm add @cartridge/controller starknet With framework connectors (React, native apps) pnpm add @cartridge/controller @cartridge/connector starknet Quick Start import Controller from "@cartridge/controller" ; const controller = new Controller ( ) ; const account = await controller . connect ( ) ; // Ready to execute...
 58
17540 memory-hygiene sundial-org/awesome-openclaw-skills
Memory Hygiene Keep vector memory lean. Prevent token waste from junk memories. Quick Commands Audit: Check what's in memory memory_recall query="*" limit=50 Wipe: Clear all vector memory rm -rf ~/.clawdbot/memory/lancedb/ Then restart gateway: clawdbot gateway restart Reseed: After wipe, store key facts from MEMORY.md memory_store text="<fact>" category="preference|fact|decision" importance=0.9 Config: Disable Auto-Capture The main source of junk is autoCapture: true . Disable it: { "plugins" :...
 58
17541 umbraco-granular-user-permissions umbraco/umbraco-cms-backoffice-skills
Umbraco Granular User Permissions What is it? Granular User Permissions allow you to create custom permission controls for specific entity types in Umbraco. Unlike general entity permissions that apply to all instances, granular permissions can be configured per-entity, allowing fine-grained access control. This is commonly used for document permissions where different users can have different permissions on different content nodes. Documentation Always fetch the latest docs before implementing:...
 58
17542 add-vault-note tradingstrategy-ai/web3-ethereum-defi
Add vault note This skill adda s human readable note to a specific vault in the database. Required inputs Before starting, gather the following information from the user: Vault smart contract address - The address of an example vault contract on a blockchain Message: A human readable message Flags (optional): Flags from VaultFlag enum - if not given set to None 1. Resolve vault name Can be resolved from https://top-defi-vaults.tradingstrategy.ai/top_vaults_by_chain.json JSON file It's a li...
 58
17543 tiktok creator eddiebe147/claude-settings
TikTok Creator Master TikTok trends, create viral hooks, and optimize content for the algorithm When to Use This Skill Use this skill when you need to: Create compelling written content Develop clear messaging and communication Structure information effectively Not recommended for: Tasks requiring technical implementation complex data analysis Quick Reference Action Command/Trigger Create tiktok creator tiktok content Review and optimize review tiktok creator Get best practices tiktok creator be...
 58
17544 bun next.js secondsky/claude-skills
Run Next.js applications with Bun for faster development and builds. Quick Start ``` Create new Next.js project with Bun bunx create-next-app@latest my-app cd my-app Install dependencies bun install Development bun run dev Build bun run build Production bun run start ``` Project Setup package.json ``` { "scripts": { "dev": "next dev --turbo", "build": "next build", "start": "next start", "lint": "next lint" }, "dependencies": { "next": "^16.1.1", "...
 58
17545 godot-resource-data-patterns thedivergentai/gd-agentic-skills
Resource & Data Patterns Resource-based design, typed arrays, and serialization define reusable, inspector-friendly data structures. Available Scripts data_factory_resource.gd Expert resource factory with type validation and batch instantiation. resource_pool.gd Object pooling for Resource instances - reduces allocation overhead in hot paths. resource_validator.gd Validates Resource files for missing exports and configuration issues. MANDATORY - For Data Systems : Read data_factory_resource.gd b...
 58
17546 json-schema-validator dkyazzentwatwa/chatgpt-skills
Validate JSON documents against JSON Schema (Draft 7) specifications. Features - Schema Validation: Validate JSON against schema - Error Details: Detailed validation error messages - Batch Validation: Validate multiple files - Schema Generation: Generate schema from examples - Multiple Drafts: Support for Draft 4, 6, 7 Quick Start ``` from json_validator import JSONValidator validator = JSONValidator() Validate data against schema schema = { "type": "object", "properties": {...
 58
17547 task-status addozhang/openclaw-forge
Task Status Skill Quick Start Manual Status Updates python scripts/send_status.py "Starting data fetch..." "progress" "step1" python scripts/send_status.py "Processing complete" "success" "final" python scripts/send_status.py "Error: Missing API key" "error" "auth" Automatic Periodic Monitoring (Every 5 seconds) Start monitoring a long-running task python scripts/monitor_task.py start "My Long Task" "processing" Monitor will send "Still working..." updates every 5 seconds When task completes,...
 58
17548 summarize nkchivas/openclaw-skill-summarize
Summarize Fast CLI to summarize URLs, local files, and YouTube links. When to use (trigger phrases) Use this skill immediately when the user asks any of: “use summarize.sh” “what’s this link/video about?” “summarize this URL/article” “transcribe this YouTube/video” (best-effort transcript extraction; no yt-dlp needed) Quick start summarize "https://example.com" --model google/gemini-3-flash-preview summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview summarize "https://youtu.be/dQ...
 58
17549 midjourney-prompt-engineering justinperea/midjourney-cc-skill
Midjourney Prompt Learning System A skill that knows Midjourney. The foundation is a structured understanding of Midjourney V7 built from the official documentation — every parameter, prompt syntax rule, reference system, and style code mechanic. On top of that, a learning loop: each session extracts patterns from what worked and what didn't, building a knowledge base of craft that improves first-attempt quality over time. Architecture You are a multimodal reasoning model. You don't need pipelin...
 58
17550 docs-sync openai/openai-agents-js
Docs Sync Overview Identify doc coverage gaps and inaccuracies by comparing main branch features and configuration options against the current docs structure, then propose targeted improvements. Workflow Confirm scope and base branch Identify the current branch and default branch (usually main ). Prefer analyzing the current branch to keep work aligned with in-flight changes. If the current branch is not main , analyze only the diff vs main to scope doc updates. Avoid switching branches if it wo...
 58