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...
25,087
总 Skills
109.9M
总安装量
2,605
贡献者
# Skill 仓库 描述 安装量
18651 autogpt-agents orchestra-research/ai-research-skills
AutoGPT - Autonomous AI Agent Platform Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or development toolkit. When to use AutoGPT Use AutoGPT when: Building autonomous agents that run continuously Creating visual workflow-based AI agents Deploying agents with external triggers (webhooks, schedules) Building complex multi-step automation pipelines Need a no-code/low-code agent builder Key features: Visual Agent Builder: Drag-and-...
 56
18652 ai-ml-expert oimiragieo/agent-studio
AI/ML Expert Core Framework Guidelines PyTorch When reviewing or writing PyTorch code, apply these guidelines: Use torch.nn.Module for all model definitions; avoid raw function-based models Move tensors and models to the correct device explicitly: model.to(device) , tensor.to(device) Use model.train() and model.eval() context switches appropriately Accumulate gradients with optimizer.zero_grad() at the top of the training loop Use torch.no_grad() or @torch.inference_mode() for all inference code...
 56
18653 flipt civitai/civitai
Use this skill to manage Flipt feature flags for controlled feature rollouts. Running Commands Use the included script: ``` node .claude/skills/flipt/flipt.mjs <command> [options] ``` Commands | `list` | List all flags | `get <key>` | Get details for a specific flag | `create <key>` | Create a new boolean flag | `enable <key>` | Enable a flag (set to true) | `disable <key>` | Disable a flag (set to false) | `delete <key>` | Delete a flag (requires confirmation) Options...
 56
18654 explanation-docs existential-birds/beagle
Explanation Documentation Skill This skill provides patterns for writing effective explanation documents. Explanations are understanding-oriented content for readers who want to know why things work the way they do. Purpose & Audience Target readers: Users who want to understand concepts deeply, not just use them Architects and technical leads evaluating design decisions Team members onboarding to a codebase or system Anyone asking "why?" or "how does this work?" Explanations are for readin...
 56
18655 prompt-engineer shipshitdev/library
Prompt Engineer Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases. When to Use This Skill Designing prompts for new LLM applications Optimizing existing prompts for better accuracy or efficiency Implementing chain-of-thought or few-shot learning Creating system prompts with personas and guardrails Building structured output schemas (JSON mode, function calling) Developing prompt evaluation and testing frame...
 56
18656 swain cristoslc/swain
Invoke the Skill tool for exactly one match. Pass the user's full prompt as args. | swain-design | vision, epic, story, spec, ADR, spike, bug, persona, runbook, journey, design | | swain-search | research, evidence, gather sources, search for, evidence pool, what do we know about | | swain-do | tasks, implementation, tracking, bd, beads | | swain-push | commit, push, stage | | swain-release | release, version, changelog, tag | | swain-update | update/upgrade swain | | swain-doctor | session init...
 56
18657 b2c-custom-api-development salesforcecommercecloud/b2c-developer-tooling
Custom API Development Skill This skill guides you through developing Custom APIs for Salesforce B2C Commerce. Custom APIs let you expose custom script code as REST endpoints under the SCAPI framework. Tip: If b2c CLI is not installed globally, use npx @salesforce/b2c-cli instead (e.g., npx @salesforce/b2c-cli code deploy ). Overview A Custom API URL has this structure: https://{shortCode}.api.commercecloud.salesforce.com/custom/{apiName}/{apiVersion}/organizations/{organizationId}/{endpointPath...
 56
18658 swiftui-performance-audit steipete/agent-scripts
SwiftUI Performance Audit Overview Audit SwiftUI view performance end-to-end, from instrumentation and baselining to root-cause analysis and concrete remediation steps. Workflow Decision Tree If the user provides code, start with "Code-First Review." If the user only describes symptoms, ask for minimal code/context, then do "Code-First Review." If code review is inconclusive, go to "Guide the User to Profile" and ask for a trace or screenshots. 1. Code-First Review Collect: Target view/featu...
 56
18659 doc-mindmap crazynomad/skills
Doc Mindmap - 文档智能整理助手 📚🧠 将散落的办公文档（PDF、PPT、Word、Excel 等）批量转换为 Markdown，通过本地 Ollama 模型生成摘要和三维度分类，用软链接同时呈现多种分类方案，零额外磁盘占用。 When to Use Use this skill when users: 想整理大量文档、分类归档 需要给一批文档生成摘要 想生成文档的思维导图 / mindmap 想把 PDF、PPT、Word 转成 Markdown 需要文档分类建议或目录结构方案 想快速了解一个文件夹里都有什么文档 需要检测重复文件 触发关键词: 文档整理, 文档分类, 思维导图, mindmap, 文档摘要, PDF 转 Markdown, 批量转换, 文档归档 Features 🔄 批量转换 - PDF、PPT、Word、Excel 等一键转 Markdown 📋 CSV 索引 - 自动生成文档索引，含 MD5 和重复检测 🔍 重复检测 - MD5 比对发现重复文件，建议删除释放空间 📝 本地摘要 - Ollama 本地模型生成摘要，不消耗 Claude 上下文 🗂️ ...
 56
18660 plantuml-diagram-generator jeremylongshore/claude-code-plugins-plus-skills
Plantuml Diagram Generator Purpose This skill provides automated assistance for plantuml diagram generator tasks within the Visual Content domain. When to Use This skill activates automatically when you: Mention "plantuml diagram generator" in your request Ask about plantuml diagram generator patterns or best practices Need help with visual content skills covering diagrams, charts, presentations, and visual documentation tools. Capabilities Provides step-by-step guidance for plantuml diagram gen...
 56
18661 working-in-parallel letta-ai/letta-code
Working in Parallel Use git worktrees to work in parallel when another agent is in the same directory. Git worktrees let you check out multiple branches into separate directories. Each worktree has its own isolated files while sharing the same Git history and remote connections. Changes in one worktree won't affect others, so parallel agents can't interfere with each other. Learn more: Git worktree documentation IMPORTANT: Check Project Setup First Before running ANY commands in a new worktree, ...
 56
18662 cargo-machete laurigates/claude-plugins
cargo-machete is a fast tool for detecting unused dependencies in Rust projects. It analyzes your codebase to find dependencies listed in Cargo.toml but not actually used in your code. Installation ``` Install cargo-machete cargo install cargo-machete Verify installation cargo machete --version ``` Basic Usage ``` Check for unused dependencies in current directory cargo machete Check specific directory cargo machete /path/to/project Check with detailed output cargo machete --with-...
 56
18663 flyway-migrations ashchupliak/dream-team
Rules: - Version: Padded numbers (001, 002... or 1.0.0, 1.0.1) - Double underscore between version and description - Description: snake_case, descriptive - Extension: .sql Basic Table Creation ``` -- V001__create_environment_table.sql CREATE TABLE environment ( id UUID PRIMARY KEY DEFAULT gen_random_uuid(), name VARCHAR(100) NOT NULL, description TEXT, status VARCHAR(50) NOT NULL DEFAULT 'PENDING', owner_id UUID NOT NULL, created_at TIMESTAMP WITH TIME ZONE NOT NUL...
 56
18664 go-rod-master sickn33/antigravity-awesome-skills
Go-Rod Browser Automation Master Overview Rod is a high-level Go driver built directly on the Chrome DevTools Protocol for browser automation and web scraping. Unlike wrappers around other tools, Rod communicates with the browser natively via CDP, providing thread-safe operations, chained context design for timeouts/cancellation, auto-wait for elements, correct iframe/shadow DOM handling, and zero zombie browser processes. The companion library go-rod/stealth injects anti-bot-detection evasions ...
 56
18665 peft-fine-tuning orchestra-research/ai-research-skills
PEFT (Parameter-Efficient Fine-Tuning) Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods. When to use PEFT Use PEFT/LoRA when: Fine-tuning 7B-70B models on consumer GPUs (RTX 4090, A100) Need to train <1% parameters (6MB adapters vs 14GB full model) Want fast iteration with multiple task-specific adapters Deploying multiple fine-tuned variants from one base model Use QLoRA (PEFT + quantization) when: Fine-tuning 70B models on single 24GB GPU Memory is the pr...
 56
18666 openrlhf-training orchestra-research/ai-research-skills
OpenRLHF - High-Performance RLHF Training Quick start OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration. Installation: Launch Docker container docker run --runtime=nvidia -it --rm --shm-size="10g" --cap-add=SYS_ADMIN \ -v $PWD:/openrlhf nvcr.io/nvidia/pytorch:25.02-py3 bash Uninstall conflicts sudo pip uninstall xgboost transformer_engine flash_attn pynvml -y Install OpenRLHF with vLLM pip install openrlhf[vllm] PPO Training (H...
 56
18667 ios-animations pproenca/dot-skills
dot-skills — Airbnb iOS SwiftUI Animations Best Practices Opinionated, strict animation craft guide for SwiftUI iOS 26 / Swift 6.2 apps. Contains 50 rules across 8 categories, prioritized by impact. Derived from Airbnb Engineering motion patterns, Apple WWDC sessions, and Apple Human Interface Guidelines. Mandates @Equatable on every animated view, motion tokens for all spring/timing values, and design system tokens for layout. Mandated Architecture Alignment This skill is designed to work along...
 56
18668 helm-release-management laurigates/claude-plugins
Comprehensive guidance for day-to-day Helm release operations including installation, upgrades, uninstallation, and release tracking. When to Use Use this skill automatically when: - User requests deploying or installing Helm charts - User mentions upgrading or updating Helm releases - User wants to list or manage releases across namespaces - User needs to check release history or status - User requests uninstalling or removing releases Core Release Operations Install New Release ``...
 56
18669 electrobun-best-practices 0xbigboss/claude-code
Electrobun Best Practices Electrobun builds cross-platform desktop apps with TypeScript and Bun. This skill gives safe defaults, typed RPC patterns, and operational guidance for build/update/distribution. Docs: https://blackboard.sh/electrobun/docs/ Pair with TypeScript Best Practices Always load typescript-best-practices alongside this skill. Version and Freshness Electrobun APIs evolve quickly. Before relying on advanced options or platform-specific behavior, verify against current docs and CL...
 56
18670 typescript-skills llama-farm/llamafarm
TypeScript Skills for LlamaFarm Shared TypeScript best practices for Designer (React) and Electron App subsystems. Overview This skill covers idiomatic TypeScript patterns for LlamaFarm's frontend applications: designer/: React 18 + TanStack Query + TailwindCSS + Radix UI electron-app/: Electron 28 + Electron Vite Tech Stack Subsystem Framework Build Key Libraries designer React 18 Vite TanStack Query, Radix UI, axios, react-router-dom electron-app Electron 28 electron-vite electron-updater,...
 56
18671 react-patterns manutej/luxor-claude-marketplace
React Development Patterns Overview Expert guide for building modern React 19 applications with new concurrent features, Server Components, Actions, and advanced patterns. This skill covers everything from basic hooks to advanced server-side rendering and React Compiler optimization. When to Use Building React 19 components with TypeScript/JavaScript Managing component state with useState and useReducer Handling side effects with useEffect Optimizing performance with useMemo and useCallback Crea...
 56
18672 slack-message-formatter onewave-ai/claude-skills
Slack Message Formatter Convert long text into Slack-optimized format with emojis, bullets, code blocks, and threading suggestions Instructions You are an expert at Slack communication. Format messages for maximum engagement and clarity using Slack markdown, emojis, and threading. Output Format Slack Message Formatter Output Generated: {timestamp} --- Results [Your formatted output here] --- Recommendations [Actionable next steps] Best Practices Be Specific: Focus on concrete, ac...
 56
18673 vitest-3-features 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 ...
 56
18674 axiom-tvos charleswiltgen/axiom
tvOS Development Overview tvOS shares UIKit and SwiftUI with iOS but diverges in critical ways that catch every iOS developer. The three most dangerous assumptions: (1) local files persist, (2) WebView exists, (3) focus works like @FocusState. Core principle tvOS is not "iOS on TV." It has a dual focus system, no persistent local storage, no WebView, and a remote with two incompatible generations. Treat it as its own platform. tvOS 26 Adopts Liquid Glass design language with new app icon system....
 56
18675 clip orchestra-research/ai-research-skills
CLIP - Contrastive Language-Image Pre-Training OpenAI's model that understands images from natural language. When to use CLIP Use when: Zero-shot image classification (no training data needed) Image-text similarity/matching Semantic image search Content moderation (detect NSFW, violence) Visual question answering Cross-modal retrieval (image→text, text→image) Metrics: 25,300+ GitHub stars Trained on 400M image-text pairs Matches ResNet-50 on ImageNet (zero-shot) MIT License Use alternativ...
 56
18676 pine-manager traderspost/pinescript-agents
Responsible for orchestrating the entire Pine Script development workflow by coordinating specialized capabilities. Project Scoping Process When starting ANY new project, first gather requirements using: - Standard flow: `/docs/project-scoping-flow.md` and `/docs/scoping-questions.md` - Unknown patterns: `/docs/comprehensive-scoping-flow.md` - Edge cases: `/docs/edge-case-handler.md` Adaptive Scoping Strategy Step 1: Pattern Recognition First, identify if the request matches known pat...
 56
18677 debugging siviter-xyz/dot-agent
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...
 56
18678 data-driven-testing 0xbigboss/claude-code
Deprecated This skill has been replaced by testing-best-practices . Use testing-best-practices for all test design, test case generation, and test strategy work. What changed Test layering policy (unit / integration / e2e) replaces the unit-only DDT focus. Markdown tables replace the rigid canonical JSON test-case schema. Output is strategy + matrix + implementation plan, not JSON blocks. Added: hard rules against fabricated fixtures and invented source locations. Added: e2e execution guidance (...
 56
18679 sales-forecast-builder onewave-ai/claude-skills
Sales Forecast Builder Weighted pipeline forecast by probability. Historical accuracy tracking, commit vs best-case scenarios, deal slippage patterns. Instructions You are an expert sales operations leader. Build accurate forecasts with multiple scenarios, track accuracy, and identify improvement opportunities. Output Format Sales Forecast Builder Output Generated: {timestamp} --- Results [Your formatted output here] --- Recommendations [Actionable next steps] Best Practices Be S...
 56
18680 deepeval sammcj/agentic-coding
DeepEval Use this skill to add an end-to-end eval loop to AI applications: instrument the app, curate or reuse a dataset, create a committed pytest eval suite, run evals, and iterate on failures. Prerequisites Requires Python 3.9+ and pip install deepeval in the target project. Metrics and synthetic generation need model credentials. Confident AI reporting, hosted traces, and online evals require deepeval login . Workflow Summary Show more Installs 472 Repository confident-ai/deepeval GitHub Sta...
 56
18681 rust-systems-programming manutej/luxor-claude-marketplace
Rust Systems Programming A comprehensive skill for building high-performance, memory-safe systems software using Rust. This skill covers ownership, borrowing, concurrency, async programming, unsafe code, FFI, and performance optimization for systems-level development. When to Use This Skill Use this skill when: Building systems software requiring memory safety without garbage collection Developing high-performance applications with zero-cost abstractions Writing concurrent or parallel progra...
 56
18682 navigation-menus dylantarre/animation-principles
Navigation & Menu Animation Principles Apply Disney's 12 principles to navigation for fluid, intuitive wayfinding. Principles Applied to Navigation 1. Squash & Stretch Menu items can compress slightly on click. Mobile hamburger icon lines should squash during transformation to X. 2. Anticipation Before dropdown opens, trigger item can lift or highlight. Sidebar toggle icon rotates slightly before panel slides. 3. Staging Active nav item should be clearly distinguished. Dropdown menus appear abov...
 56
18683 apple-mail rbouschery/marketplace
Apple Mail Skill This skill provides commands to interact with Apple Mail on macOS via AppleScript. Available Scripts All scripts are in the ../../scripts/ directory (relative to this file). Execute them via bash from the plugin root. Account & Mailbox Management Script Purpose Arguments list-accounts.sh List all email accounts none list-mailboxes.sh List mailboxes/folders [account] (optional) get-unread-count.sh Get unread email count [account] [mailbox] (optional) Reading Emails Script Pur...
 56
18684 dojo-init dojoengine/book
Dojo Project Initialization Initialize new Dojo projects with the complete directory structure, configuration files, and dependencies. When to Use This Skill "Create a new Dojo project" "Initialize a Dojo game called [name]" "Set up a new Dojo application" "Start a new provable game project" What This Skill Does Creates a complete Dojo project with: Scarb.toml with Dojo dependencies dojo_dev.toml for local development Source directory structure Example models and systems Test files Quick Start U...
 56
18685 vanilla-web janjaszczak/cursor
Vanilla Web (HTML/CSS/JS) Baseline constraints (from the rule) Use these as non-negotiables: "HTML/CSS/JS only (no framework)." "Keep JS modular (ESM), split responsibilities (SRP)." "Prefer small, focused functions and pure utilities; avoid global state." "Ship complete runnable files and minimal tests before marking done." When to activate this skill Activate when the user asks for: vanilla JS / plain HTML/CSS/JS / static page “no framework”, “no React/Vue/Angular” small UI components (modal, ...
 56
18686 speech-to-text sarvamai/skills
ElevenLabs Speech-to-Text Transcribe audio to text with Scribe v2 - supports 90+ languages, speaker diarization, and word-level timestamps. Setup: See Installation Guide . For JavaScript, use @elevenlabs/* packages only. Quick Start Python from elevenlabs import ElevenLabs client = ElevenLabs ( ) with open ( "audio.mp3" , "rb" ) as audio_file : result = client . speech_to_text . convert ( file = audio_file , model_id = "scribe_v2" ) print ( result . text ) JavaScript import { ElevenLabsClient } ...
 56
18687 layout designer eddiebe147/claude-settings
Layout Designer A layout expert that creates beautiful, functional page compositions using grid systems, spacing, and visual hierarchy principles. This skill combines design theory, responsive design patterns, and modern CSS capabilities to build layouts that work across all devices and content types. Whether you need a landing page hero, a dashboard interface, or an editorial layout, this skill provides structured approaches to composition that balance aesthetics with usability. Core Workflows ...
 56
18688 markdown-exporter bowenliang123/md_exporter
✨ What is Markdown Exporter? Markdown Exporter is a Agent Skill that transforms your Markdown text into a wide variety of professional formats. Whether you need to create polished reports, stunning presentations, organized spreadsheets, or code files—this tool has you covered. Tools and Supported Formats Prerequisites To use the Markdown Exporter skill, ensure you have the following prerequisites installed: Python 3.11 or higher (optional) uv package manager 📦 Usage Overview All scripts pro...
 56
18689 youdotcom-cli youdotcom-oss/agent-skills
You.com Web Search, Research & Content Extraction Prerequisites Verify curl and jq are available curl --version jq --version API Key (optional for Search) The Search endpoint ( /v1/agents/search ) works without an API key — no signup, no billing required. An API key unlocks higher rate limits and is required for Research and Contents endpoints. Optional for search, required for research/contents export YDC_API_KEY = "your-api-key-here" Get an API key from https://you.com/platform/api-keys to u...
 56
18690 mcp-supabase heyvhuang/ship-faster
Supabase MCP Skill Interact with Supabase database via MCP tools, execute queries, writes, migrations, and diagnostics. Scope Applies to: Need to perform "database actions" on Supabase: query/statistics/export, write (after confirmation), migration (DDL), type generation, query logs/advisors Does not apply to: Need to complete "integration implementation" in Next.js project (env/client code/minimal data access layer/project structure) → Use workflow-ship-faster (Step 6: Supabase integration) for...
 56
18691 go-playwright sickn33/antigravity-awesome-skills
Playwright Go Automation Expert Overview This skill provides a comprehensive framework for writing high-performance, production-grade browser automation scripts using github.com/playwright-community/playwright-go . It enforces architectural best practices (contexts over instances), robust error handling, structured logging (Zap), and advanced human-emulation techniques to bypass anti-bot systems. When to Use This Skill Use when the user asks to "scrape," "automate," or "test" a website using Go....
 56
18692 scholar-evaluation ovachiever/droid-tings
Scholar Evaluation Use this skill to evaluate academic or scientific work with a repeatable rubric. When to Use Reviewing a research paper, proposal, thesis chapter, or literature review. Checking whether claims are supported by cited evidence. Evaluating methodology, study design, analysis, or limitations. Comparing two or more papers for quality or relevance. Producing structured feedback for revision. Evaluation Scope Start by identifying the artifact: Show more
 56
18693 hn-search dylanfeltus/skills
Hacker News Search Search and monitor Hacker News stories, comments, and users via the Algolia HN Search API. No API key required. When to Use User asks about Hacker News discussions on a topic User wants to find HN posts about a company, product, or technology User wants to monitor HN for mentions of something User asks "what's trending on HN" or "what did HN think about X" User wants to find Show HN / Ask HN / Launch HN posts API Overview Base URL: https://hn.algolia.com/api/v1 Two search endp...
 56
18694 api-filtering-sorting secondsky/claude-skills
API Filtering & Sorting Overview Build flexible filtering and sorting systems that handle complex queries efficiently with proper validation, security, and performance optimization. When to Use Building search and filter interfaces Implementing advanced query capabilities Creating flexible data retrieval endpoints Optimizing query performance Validating user input for queries Supporting complex filtering logic Instructions 1. Query Parameter Filtering // Node.js filtering implementation app.ge...
 56
18695 sapui5-cli secondsky/sap-skills
SAPUI5/OpenUI5 CLI Management Skill Table of Contents Overview When to Use This Skill Quick Start Workflow Project Types Bundled Resources Overview This skill provides comprehensive guidance for working with the UI5 CLI (UI5 Tooling), the official command-line interface for developing, building, and deploying SAPUI5 and OpenUI5 applications and libraries. Current CLI Version : 4.0.0+ (Released July 24, 2024) Node.js Requirements : v20.11.0+ or v22.0.0+ (v21 not supported) npm Requirements : v8.0...
 56
18696 webconsulting-branding dirnbauer/webconsulting-skills
Persona: Innovative, Technical, Professional ("Senior Solutions Architect") Tone: Clear, concise, authoritative. Avoid marketing fluff. Language: German (Primary) / English (Technical documentation) 2. Visual Design Tokens (Strict Adherence) Color Palette | Primary Teal | `14b8a6` | `text-teal-500` | Links, primary buttons, active states | Primary Cyan | `06b6d4` | `text-cyan-600` | Hover states, secondary highlights | Accent Amber | `f59e0b` | `text-amber-500` | Warnings, hi...
 56
18697 tanstack-vue-query-skilld harlan-zw/vue-ecosystem-skills
TanStack/query @tanstack/vue-query Hooks for managing, caching and syncing asynchronous and remote data in Vue Version: 5.92.9 (Jan 2026) Deps: @tanstack/match-sorter-utils@^8.19.4, @vue/devtools-api@^6.6.3, vue-demi@^0.14.10, @tanstack/query-core@5.90.20 Tags: alpha: 5.0.0-alpha.91 (Jul 2023), beta: 5.0.0-beta.35 (Sep 2023), rc: 5.0.0-rc.16 (Oct 2023), latest: 5.92.9 (Jan 2026), previous: 4.43.0 (Jan 2026) References: Docs — API reference, guides API Changes This section documents version-speci...
 55
18698 clinical-trials-search yorkeccak/scientific-skills
Clinical Trials Search Search the complete ClinicalTrials.gov database of clinical studies using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete trial information including phases, conditions, interventions, and outcom...
 55
18699 mcp-management secondsky/claude-skills
MCP Management Skill for managing and interacting with Model Context Protocol (MCP) servers. Overview MCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window. Key Benefits: Progressive disclosure of MCP capabilities (load only what's needed) Intelligent tool/prompt/resource selection based on task req...
 55
18700 oracle steipete/agent-scripts
oracle — best use Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests. Main use case (browser, GPT‑5.2 Pro) Default workflow here: --engine browser with GPT‑5.2 Pro in ChatGPT. This is the common “long think” path: ~10 minutes to ~1 hour is normal; expect a stored session you can reattach to. Recommended defaults: Engine: browser ( --engine bro...
 55