Agent Skills 排行榜 · 关键词 + 语义搜索

/ 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
19251 laravel:code-review-requests jpcaparas/superpowers-laravel
Focused review requests get actionable feedback. Vague requests get generic advice. Specify Focus Areas Vague "Review this code" Focused "Review OrderService for security and performance: Focus on: - Authorization checks (are we verifying user owns the order?) - SQL injection risks (any raw queries?) - N+1 query problems (eager loading correct?) - Transaction handling (atomic operations?) - Error handling (graceful failures?) Code: ``` class OrderService { public function cre...
36
19252 animation principles - troubleshooting dylantarre/animation-principles
Animation Troubleshooting Guide Something's off. Use this to find and fix it. Symptom-Based Diagnosis "It feels floaty/weightless" Check: Slow in/out - Is spacing too even? Add bunching at start/end Timing - Need more frames for weight? Fewer for snap? Squash/stretch - Impact reaction visible? Follow through - Settling properly or just stopping? Fix: Add 2-4 frames to settle. Increase spacing variation. Add impact squash. "It feels stiff/robotic" Check: Arcs - Are paths too straight? Overlap - I...
36
19253 tooluniverse-single-cell mims-harvard/tooluniverse
Single-Cell Genomics and Expression Matrix Analysis Comprehensive single-cell RNA-seq analysis and expression matrix processing using scanpy, anndata, scipy, and ToolUniverse. When to Use This Skill Apply when users: Have scRNA-seq data (h5ad, 10X, CSV count matrices) and want analysis Ask about cell type identification, clustering, or annotation Need differential expression analysis by cell type or condition Want gene-expression correlation analysis (e.g., gene length vs expression by cell type...
36
19254 file-uploads eddiebe147/claude-settings
File Uploads & Storage Role: File Upload Specialist Careful about security and performance. Never trusts file extensions. Knows that large uploads need special handling. Prefers presigned URLs over server proxying. ⚠️ Sharp Edges Issue Severity Solution Trusting client-provided file type critical CHECK MAGIC BYTES No upload size restrictions high SET SIZE LIMITS User-controlled filename allows path traversal critical SANITIZE FILENAMES Presigned URL shared or cached incorrectly medium CON...
36
19255 argorollouts julianobarbosa/claude-code-skills
Argo Rollouts Skill Comprehensive guide for Argo Rollouts - a Kubernetes controller providing advanced deployment capabilities including blue-green, canary, and experimentation for Kubernetes. Quick Reference Resource Description Rollout Replaces Deployment, adds progressive delivery strategies AnalysisTemplate Defines metrics queries for automated analysis AnalysisRun Instantiated analysis from template Experiment Runs ReplicaSets for A/B testing ClusterAnalysisTemplate Cluster-scoped AnalysisT...
36
19256 hf-model-inference letta-ai/skills
HuggingFace Model Inference Service Overview This skill provides procedural guidance for setting up HuggingFace model inference services. It covers model downloading, caching strategies, Flask API creation, and service deployment patterns. Workflow Phase 1: Environment Setup Verify package manager availability Check for uv , pip , or conda before installing dependencies Prefer uv for faster dependency resolution when available Install required packages Core: transformers , torch (or tensorflow )...
36
19257 web-archiving jamditis/claude-skills-journalism
Web archiving methodology Patterns for accessing inaccessible web pages and preserving web content for journalism, research, and legal purposes. Archive service hierarchy Try services in this order for maximum coverage: ┌─────────────────────────────────────────────────────────────────┐ │ ARCHIVE RETRIEVAL CASCADE │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ 1. ...
36
19258 newsletter-coach nicepkg/ai-workflow
This skill includes supporting documents. Read them when needed during the process: | Idea Development Questions | Phase 1 - When drilling deeper on experiences | `resources/idea-development-questions.md` | Outliner | Phase 5 - When creating subheads for different post types | `resources/outliner.md` | Section Writer | Phase 6 - When expanding sections with the 14 ways | `resources/section-writer.md` | Newsletter Examples | Phase 7 - For style reference and voice matching | `resou...
36
19259 swift-ui-architect pproenca/dot-skills
SwiftUI Modular MVVM-C Architecture Opinionated architecture enforcement for SwiftUI clinic-style apps. This skill aligns to the iOS 26 / Swift 6.2 clinic architecture: modular MVVM-C in local SPM packages, concrete coordinators and route shells in the App target, pure Domain protocols, and Data as the only I/O layer. Mandated Architecture Stack ┌───────────────────────────────────────────────────────────────┐ │ App target: DependencyContainer, Coordinators, Route Shells │ ├───────────────┬───...
36
19260 qwen-delegation athola/claude-night-market
Table of Contents Overview When to Use Prerequisites Delegation Flow Quick Start Using Shared Delegation Executor Direct CLI Usage Save Output Smart Delegation Shared Patterns Qwen-Specific Details Exit Criteria Qwen CLI Delegation Overview This skill implements conjure:delegation-core for the Qwen CLI using shared delegation patterns. It provides Qwen-specific authentication, quota management, and command construction. When to Use After Skill(conjure:delegation-core) determines Qwen is suitab...
36
19261 edge-signal-aggregator tradermonty/claude-trading-skills
Edge Signal Aggregator Overview Combine outputs from multiple upstream edge-finding skills into a single weighted conviction dashboard. This skill applies configurable signal weights, deduplicates overlapping themes, flags contradictions between skills, and ranks composite edge ideas by aggregate confidence score. The result is a prioritized edge shortlist with provenance links to each contributing skill. When to Use After running multiple edge-finding skills and wanting a unified view When cons...
36
19262 dispatch-module-architecture tencentblueking/bk-ci
Dispatch 构建调度模块架构指南 模块定位: Dispatch 是 BK-CI 的构建调度模块,负责接收流水线的构建任务,将任务分发到合适的构建机(第三方构建机、Docker 容器、Kubernetes Pod)上执行。 一、模块整体结构 1.1 子模块划分 src/backend/ci/core/dispatch/ ├── api-dispatch/ API 接口定义层 │ └── src/main/kotlin/com/tencent/devops/dispatch/ │ ├── api/ REST API 接口 │ ├── constants/ 常量定义 │ └── pojo/ 数据对象 │ ├── enums/ 枚举 │ ├── redis/ Redis 数据结构 │ ...
36
19263 brainstorm witooh/skills
/brainstorm — Clarify Goals Before Planning Purpose: Separate WHAT from HOW. Explore the problem space before committing to a solution. Four phases: Assess clarity — Is the goal specific enough? Understand idea — What problem, who benefits, what exists? Explore approaches — Generate options, compare tradeoffs Capture design — Write structured output for /plan Quick Start /brainstorm "add user authentication" full 4-phase process /brainstorm prompts for goal Execution Steps Phase 1: Assess Clar...
36
19264 prowler-attack-paths-query prowler-cloud/prowler
Overview Attack Paths queries are openCypher queries that analyze cloud infrastructure graphs (ingested via Cartography) to detect security risks like privilege escalation paths, network exposure, and misconfigurations. Queries are written in openCypher Version 9 to ensure compatibility with both Neo4j and Amazon Neptune. Input Sources Queries can be created from: pathfinding.cloud ID (e.g., ECS-001 , GLUE-001 ) The JSON index contains: id , name , description , services , permissions , exploita...
36
19265 tdd inkeep/team-skills
/tdd - Test-Driven Development Workflow Strict TDD workflow: tests first, then implementation. When to Use "Implement X using TDD" "Build this feature test-first" "Write tests for X then implement" Any feature where test coverage is critical Bug fixes that need regression tests TDD Philosophy Overview Write the test first. Watch it fail. Write minimal code to pass. Core principle: If you didn't watch the test fail, you don't know if it tests the right thing. Violating the letter of the rules is ...
36
19266 zendesk-automation davepoon/buildwithclaude
Zendesk Automation via Rube MCP Automate Zendesk operations through Composio's Zendesk toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/zendesk Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Zendesk connection via RUBE_MANAGE_CONNECTIONS with toolkit zendesk Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint ...
36
19267 ha-energy nodnarbnitram/claude-code-extensions
Home Assistant Energy Skill Configure Home Assistant energy monitoring with dashboards, solar, grid, and device tracking. Before You Start This skill prevents 8 common errors and saves ~45% tokens. Metric Without Skill With Skill Setup Time 45+ min 15 min Common Errors 8 0 Token Usage ~10000 ~5500 Known Issues This Skill Prevents Incorrect state_class values (must be total , total_increasing , or measurement ) Missing device_class: energy on energy sensors Wrong state_class for utility_meter ent...
36
19268 multi-agent-patterns eyadsibai/ltk
Multi-Agent Architecture Patterns Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division. When to Activate Activate this skill when: Single-agent context l...
36
19269 jj-todo-workflow ypares/agent-skills
JJ TODO Workflow The core idea is to use a DAG of empty revisions as TODO markers, representing tasks to be done, and then come back later to edit these revisions to actually do the tasks. This enables structured development with clear milestones. Revision descriptions (i.e. commit messages) act as specifications for what to implement. JJ makes it easy to create such a structure, and then to fill each revision afterwards. For more information on JJ basics, see the working-with-jj skill. We reuse...
36
19270 gateway joelhooks/joelclaw
You are "Gateway" - an API design specialist who ensures consistent, well-documented, and future-proof APIs. Your mission is to design, review, and document ONE API or endpoint, ensuring it follows best practices, is properly versioned, and has complete specifications. API Design Philosophy Gateway answers five critical questions: | What does this API do? | Clear purpose, resource definition | How should it be used? | Request/response examples, error handling | Is it consistent? | Nam...
36
19271 nansen-general-search nansen-ai/nansen-cli
Search nansen research search "jupiter" --type token nansen research search "Vitalik" --type entity --limit 5 nansen research search "bonk" --chain solana --fields address,name,symbol,chain Flag Purpose --type token or entity --chain Filter by chain --limit Number of results (default 25, max 50) --fields Select specific output fields Case-insensitive. Does NOT match by address — use profiler labels for address lookup.
36
19272 note-taker luongnv89/skills
Note Taker (Git-managed) This skill maintains a private notes system in a dedicated git-backed notes repository. Setup: The notes repo path must be configured. Look for a NOTES_REPO variable in the project's CLAUDE.md or AGENTS.md, or ask the user for the path on first use. Rule: This skill has side effects (writes + commits + pushes) so it must be user-invoked. Repo Sync Before Edits (mandatory) Before creating/updating/deleting files in an existing repository, sync the current branch with remo...
36
19273 nansen-token-screener nansen-ai/nansen-cli
Token Discovery Answers: "What tokens are trending and worth a deeper look?" CHAIN = solana Screen top tokens by volume nansen research token screener --chain $CHAIN --timeframe 24h --limit 20 → token_symbol, price_usd, price_change, volume, buy_volume, market_cap_usd, fdv, liquidity, token_age_days Smart money only nansen research token screener --chain $CHAIN --timeframe 24h --smart-money --limit 20 Search within screener results (client-side filter) nansen research token screener --chain ...
36
19274 agent-generator-tutor rysweet/amplihack
Agent Generator Tutor Skill Interactive teaching agent for the goal-seeking agent generator and eval system. What This Skill Does Loads the GeneratorTeacher from src/amplihack/agents/teaching/generator_teacher.py and guides users through a structured 14-lesson curriculum with exercises and quizzes. Curriculum (14 Lessons) Lesson Title Topics L01 Introduction to Goal-Seeking Agents Architecture, GoalSeekingAgent interface L02 Your First Agent (CLI Basics) Prompt files, CLI invocation, pipeline L0...
36
19275 feishu-docs m1heng/feishu-doc-cli
Feishu Open Platform Docs Read Feishu developer documentation directly from the terminal via feishu-doc CLI. Prerequisites Install once (requires Node.js >= 18): npm install -g feishu-doc-cli Commands feishu-doc search "<keyword>" Search docs by title feishu-doc read "<path>" Read a document (outputs Markdown) feishu-doc tree --depth 2 Browse the doc tree feishu-doc tree "<path>" Browse a subtree Add --lang en for English. Workflow Start with search to find relevant documents: feishu-doc sea...
36
19276 vercel-composition-patterns guanyang/antigravity-skills
React Composition Patterns Composition patterns for building flexible, maintainable React components. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. These patterns make codebases easier for both humans and AI agents to work with as they scale. When to Apply Reference these guidelines when: Refactoring components with many boolean props Building reusable component libraries Designing flexible component APIs Reviewing component architecture W...
36
19277 shadcn-hooks debbl/shadcn-hooks
shadcn-hooks This skill is a decision-and-implementation guide for shadcn-hooks in React projects. It maps requirements to the most suitable hook, applies the correct usage pattern, and prefers hook-based solutions over bespoke code to keep implementations concise, maintainable, and performant. When to Apply Apply this skill whenever assisting user development work in React / Next.js. Always check first whether a shadcn-hooks function can fulfill the requirement. Prefer shadcn-hooks over custom ...
36
19278 laravel:internationalization-and-translation jpcaparas/superpowers-laravel
Build your Laravel application with internationalization in mind from the start. Even if you're only supporting one language initially, wrapping strings in translation functions makes future localization much easier. Why Translate From the Start? ``` // BAD: Hardcoded strings are difficult to change later return view('welcome', [ 'message' => 'Welcome to our application!' ]); // GOOD: Translatable from day one return view('welcome', [ 'message' => __('Welcome to our application!') ])...
36
19279 regex-chess letta-ai/skills
This skill provides strategic guidance for implementing chess move generators using only regular expressions. These tasks require transforming board state (typically in FEN notation) through pattern matching and substitution rather than traditional programming constructs. Core Approach Phase 1: Understand the String Representation Before writing any patterns, thoroughly understand the board representation: - Parse the FEN structure: FEN notation encodes rank 8 to rank 1 (top to bottom), wi...
36
19280 vercel-react-best-practices andrelandgraf/fullstackrecipes
Vercel React Best Practices Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 62 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new React components or Next.js pages Implementing data fetching (client or server-side) Reviewing code for performance issues Refactoring existing React/Next.js code Optimizing bundle size or load tim...
36
19281 paper-compilation lingzhi227/agent-research-skills
Paper Compilation Compile a LaTeX paper to PDF with error detection and correction. Input $ARGUMENTS — Path to the main .tex file Scripts Compile paper python ~/.claude/skills/paper-compilation/scripts/compile_paper.py paper/main.tex python ~/.claude/skills/paper-compilation/scripts/compile_paper.py paper/main.tex --check-style python ~/.claude/skills/paper-compilation/scripts/compile_paper.py paper/main.tex --output paper/output.pdf Reports: compilation status, page count, warnings, citation/re...
36
19282 network-tools chaterm/terminal-skills
Network Tools and Diagnostics Overview Linux network diagnostics, port scanning, traffic analysis and other tool usage skills. Network Configuration View Configuration IP address ip addr ip a ifconfig Legacy command Routing table ip route route -n netstat -rn DNS configuration cat /etc/resolv.conf systemd-resolve --status Configure Network Temporary IP configuration ip addr add 192.168 .1.100/24 dev eth0 ip addr del 192.168 .1.100/24 dev eth0 Enable/Disable interface ip link set eth0 up ip...
36
19283 agent-fullstack-developer tony363/superclaude
Fullstack Developer Agent You are a senior fullstack developer specializing in complete feature development with expertise across backend and frontend technologies. Your primary focus is delivering cohesive, end-to-end solutions that work seamlessly from database to user interface. Domain Core Development Tools Primary: Read, Write, MultiEdit, Bash, Docker, database Key Capabilities Database schema aligned with API contracts Type-safe API implementation with shared types Frontend components matc...
36
19284 structured-logging-standardizer patricio0312rev/skills
Structured Logging Standardizer Implement consistent, queryable, correlated logs. Log Schema interface LogEntry { timestamp: string; // ISO 8601 level: "debug" | "info" | "warn" | "error" | "fatal"; message: string; service: string; environment: string; // Request context requestId?: string; traceId?: string; userId?: string; // Additional context [key: string]: any; } Request ID Middleware import { v4 as uuidv4 } from "uuid"; app.use((req, res, next) => { // Genera...
36
19285 excalidraw rnjn/cc-excalidraw-skill
Excalidraw Subagent Delegation Overview Core principle: Main agents NEVER read Excalidraw files directly. Always delegate to subagents to isolate context consumption. Excalidraw files are JSON with high token cost but low information density. Single files range from 4k-22k tokens (largest can exceed read tool limits). Reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of budget). The Problem Excalidraw JSON structure: Each shape has 20+ properties (x, y, w...
36
19286 senhasegura-skill julianobarbosa/claude-code-skills
Comprehensive guide for integrating with senhasegura (Segura) Privileged Access Management platform. Covers A2A APIs, DevOps Secrets Management (DSM), MySafe, credential management, SSH key rotation, and Kubernetes integration. Platform Overview Core Modules | PAM Core | Credential vaulting, password rotation, session management | Enterprise credential management | A2A | Application-to-Application API authentication | Programmatic secrets access | DSM | DevOps Secret Manager for CI...
36
19287 m365-agents-dotnet sickn33/antigravity-awesome-skills
Microsoft 365 Agents SDK (.NET) Overview Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft.Agents SDK with ASP.NET Core hosting, agent routing, and MSAL-based authentication. Before implementation Use the microsoft-docs MCP to verify the latest APIs for AddAgent, AgentApplication, and authentication options. Confirm package versions in NuGet for the Microsoft.Agents.* packages you plan to use. Installation dotnet add package Microsoft.Agents.Hosting.AspNetC...
36
19288 building-mechanics bbeierle12/skill-mcp-claude
3D Building Mechanics Complete building system for Three.js games with performance optimization, structural physics, and multiplayer networking. Quick Start import { SpatialHashGrid } from './scripts/spatial-hash-grid.js'; import { HeuristicValidator } from './scripts/heuristic-validator.js'; // Spatial indexing for fast queries const spatialIndex = new SpatialHashGrid(10); spatialIndex.insert(piece, piece.position); const nearby = spatialIndex.queryRadius(position, 15); // Structural valida...
36
19289 magento-alpine-specialist maxnorm/magento2-agent-skills
Magento 2 Alpine.js Specialist Expert specialist in creating modern, reactive user interfaces for Magento 2 applications using Alpine.js's declarative approach. When to Use Building Alpine.js components Working with Hyvä themes Creating reactive UI components Implementing lightweight JavaScript solutions Building interactive frontend features Alpine.js Mastery Reactive Programming Reactive Data : Expert in Alpine.js reactive data and state management Declarative Syntax : Master Alpine.js directi...
36
19290 game-ai-behavior omer-metin/skills-for-antigravity
Game Ai Behavior Identity Role: Game AI Architect Personality: You are a veteran game AI programmer who has shipped multiple AAA titles. You think deeply about player experience - AI should be fun to play against, not just technically impressive. You balance sophistication with performance, always considering target hardware. You have battle scars from debugging emergent AI behaviors at 3 AM before launch. You speak with authority but acknowledge that game AI is as much art as science. Expert...
36
19291 effect-client-wrapper rhyssullivan/effect-client-wrapper-skill
Effect Client Wrapper Pattern Wrap third-party SDK clients with Effect using the "use" pattern for consistent error handling, tracing, and dependency injection. Pattern Structure import { Context , Data , Effect , Layer , Config , Redacted } from "effect" ; // 1. Define tagged errors export class MyClientError extends Data . TaggedError ( "MyClientError" ) < { cause : unknown ; } > { } export class MyClientInstantiationError extends Data . TaggedError ( "MyClientInstantiationError" ) < { cause :...
36
19292 terraform-provider-config jeremylongshore/claude-code-plugins-plus-skills
Terraform Provider Config Purpose This skill provides automated assistance for terraform provider config tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "terraform provider config" in your request Ask about terraform provider config patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance for terrafor...
36
19293 popo-doc-loader api/git
No SKILL.md available for this skill. View on GitHub
36
19294 literature-review jackspace/claudeskillz
Literature Review Overview Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats. This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and do...
36
19295 torch-tensor-parallelism letta-ai/skills
This skill provides guidance for implementing tensor parallelism patterns in PyTorch, specifically for ColumnParallelLinear and RowParallelLinear layers that distribute computation across multiple devices. Core Concepts Tensor Parallelism Overview Tensor parallelism splits individual layers across multiple devices to parallelize computation within a single forward/backward pass. The two primary patterns are: - ColumnParallelLinear: Shards weights along the output dimension (columns). Each...
36
19296 nansen-smart-money-trend nansen-ai/nansen-cli
TOKEN = < address > CHAIN = ethereum nansen research smart-money netflow --chain $CHAIN --limit 200 → filter by token_address; net_flow_1h_usd, net_flow_24h_usd, net_flow_7d_usd, net_flow_30d_usd nansen research token holders --token $TOKEN --chain $CHAIN --smart-money --limit 20 → address_label, value_usd, balance_change_24h, balance_change_7d, balance_change_30d nansen research token flow-intelligence --token $TOKEN --chain $CHAIN → smart_trader_net_flow_usd, whale_net_flow_usd, fund_net_fl...
36
19297 animation principles - teaching others dylantarre/animation-principles
Teaching the 12 Principles Effectively Teaching animation principles requires meeting students where they are. Here's how to communicate each principle at different levels. Teaching Strategies by Principle 1. Squash and Stretch Show first: Bouncing ball exercise - universal, immediate, undeniable. Common confusion: Students preserve shape instead of volume. Use clay demonstration. Key phrase: "Volume stays the same, shape changes." 2. Anticipation Show first: Video of real athletes - every jump ...
36
19298 claim-evidence-matrix willoscar/research-units-pipeline-skills
Claim–Evidence Matrix Make the survey’s claims explicit and auditable before writing prose. This should stay bullets-only (NO PROSE). The goal is to make later writing easy and to prevent “template prose” from sneaking in. Inputs outline/outline.yml papers/paper_notes.jsonl Optional: outline/mapping.tsv Output outline/claim_evidence_matrix.md Workflow (heuristic) Uses: outline/outline.yml, outline/mapping.tsv. For each subsection, write 1–3 claims that are: specific (mechanism / assumption ...
36
19299 security-check schroneko/security-check
Security Check Perform a security analysis of the current environment. Instructions Read scripts/check.sh Display the message in the user's language
36
19300 near-api-js near/agent-skills
near-api-js Skill JavaScript/TypeScript library for NEAR blockchain interaction. Works in browser and Node.js. Quick Start import { Account , JsonRpcProvider , KeyPairString } from "near-api-js" ; import { NEAR } from "near-api-js/tokens" ; // Connect to testnet const provider = new JsonRpcProvider ( { url : "https://test.rpc.fastnear.com" } ) ; // Create account with signer const account = new Account ( "my-account.testnet" , provider , "ed25519:..." as KeyPairString , ) ; // View call (read-on...
36