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...
30,000
总 Skills
303.3M
总安装量
2,871
贡献者
# Skill 仓库 描述 安装量
29301 backend-agent first-fluke/oh-my-ag
Backend Agent - API & Server Specialist When to use Building REST APIs or GraphQL endpoints Database design and migrations Authentication and authorization Server-side business logic Background jobs and queues When NOT to use Frontend UI -> use Frontend Agent Mobile-specific code -> use Mobile Agent Core Rules DRY (Don't Repeat Yourself) : Business logic in Service , data access logic in Repository SOLID : Single Responsibility : Classes and functions should have one responsibility Dependency In...
35
29302 query-optimize letta-ai/skills
SQL Query Optimization This skill provides procedural guidance for optimizing SQL queries effectively, with emphasis on proper benchmarking, query plan analysis, and iterative refinement. Core Optimization Workflow 1. Establish Performance Baselines Before making any changes, establish clear performance metrics: Identify the target : Determine what "optimal" performance looks like. Look for reference implementations, documented benchmarks, or theoretical analysis of query complexity. Measure the...
35
29303 sober-addict-protector erichowens/some_claude_skills
Sober Addict Protector Daily companion for protecting your sobriety through proactive strategies, trigger management, and sustainable recovery practices. When to Use This Skill Use for: Daily check-ins and accountability Identifying high-risk situations before they happen Managing triggers in real-time Remembering why therapy and couples counseling matter Building protective habits and routines Processing close calls without judgment Maintaining motivation during hard days NOT for: Active crisis...
35
29304 fd-file-finding laurigates/claude-plugins
fd File Finding Expert knowledge for using fd as a fast, user-friendly alternative to find with smart defaults and powerful filtering. Core Expertise fd Advantages Fast parallel execution (written in Rust) Colorized output by default Respects .gitignore automatically Smart case-insensitive search Simpler syntax than find Regular expression support Basic Usage Simple File Search Find all files named config fd config Find files with extension fd -e rs All Rust files fd -e md All Markdown files...
35
29305 rr-redshift-query emplifi/eng
No SKILL.md available for this skill. View on GitHub
35
29306 quantitative-analysis poemswe/co-researcher
1. Statistical Test Selection Question Data Type Recommended Test Compare 2 groups Continuous (Normal) Independent t-test Compare 2+ groups Continuous (Normal) One-way ANOVA Relationship Continuous Pearson's r Prediction Continuous Multiple Regression Categorical diff Counts Chi-square 2. Power & Effect Size Analysis Power Analysis : Calculating required $N$ for given $\alpha$ and $(1-\beta)$. Effect Sizes : Cohen's $d$, Pearson's $r$, $\eta^2$, Odds Ratios. 3. Advanced Modeling Multilevel Model...
35
29307 claudeception blader/claudeception
Claudeception You are Claudeception: a continuous learning system that extracts reusable knowledge from work sessions and codifies it into new Claude Code skills. This enables autonomous improvement over time. Core Principle: Skill Extraction When working on tasks, continuously evaluate whether the current work contains extractable knowledge worth preserving. Not every task produces a skill—be selective about what's truly reusable and valuable. When to Extract a Skill Extract a skill when you en...
35
29308 codeql-expert personamanagmentlayer/pcl
CodeQL Expert Expert guidance for CodeQL static analysis, custom query development, vulnerability detection, and integration with CI/CD pipelines. Core Concepts CodeQL Overview Semantic code analysis engine Treats code as data (queryable database) Supports C/C++, C, Go, Java, JavaScript/TypeScript, Python, Ruby Powers GitHub Code Scanning Custom query development with QL language CodeQL Workflow Extract code to database Write QL queries Run analysis Review results Fix vulnerabilities Integrate i...
35
29309 add-skill htlin222/dotfiles
Add Skill (Meta Skill) Create new Claude Code skills by fetching the latest official documentation and generating properly structured skill files. Workflow Step 1: Fetch Latest Documentation Always fetch official docs first to ensure compliance with current spec: WebFetch: https://code.claude.com/docs/en/skills Prompt: Extract skill file format, required fields, naming rules, and best practices If WebFetch fails due to length, use WebSearch: WebSearch: "Claude Code skills SKILL.md format site:co...
35
29310 claude-code-expert sickn33/antigravity-awesome-skills
CLAUDE CODE EXPERT - Potencia Maxima Overview Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas. Ativar para: configurar Claude Code, criar hooks, otimizar CLAUDE.md, usar MCPs, criar sub-agentes, resolver erros do CLI, workflows avancados, duvidas sobre qualquer feature. When to Use This Skill When you need specialized assistance w...
35
29311 higgsfield-operator eddiebe147/claude-settings
No SKILL.md available for this skill. View on GitHub
35
29312 mastering-confluence spillwavesolutions/mastering-confluence-agent-skill
Type: Project | Version: 2.2.0 Manage Confluence documentation: download pages to Markdown, upload with images, convert between formats, integrate diagrams, search with CQL. Contents - [Critical Constraints](critical-constraints) - [Quick Start](quick-start) - [Core Capabilities](core-capabilities) - [Checklists](checklists) - [Reference Documentation](reference-documentation) - [Scripts](scripts) Critical Constraints DO NOT USE MCP FOR PAGE UPLOADS - Size limits apply (~10-20KB max)...
35
29313 deep-research cnemri/google-genai-skills
Deep Research Drift-prone skill. Firecrawl/Exa MCP tool names, quotas, and result shapes change. Verify the configured MCP tools and current API docs before promising coverage or quoting live source counts. Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools. When to Activate User asks to research any topic in depth Competitive analysis, technology evaluation, or market sizing Due diligence on companies, investors, or technologies Any question req...
35
29314 syncable-entity-types-and-constants twentyhq/twenty
Syncable Entity: Types & Constants (Step 1/6) Purpose : Define all types, entities, and register in central constants. This is the foundation - everything else depends on these types being correct. When to use : First step when creating any new syncable entity. Must be completed before other steps. Quick Start This step creates: Metadata name constant (twenty-shared) TypeORM entity (extends SyncableEntity ) Flat entity types Action types (universal + flat) Central constant registrations (5 const...
35
29315 war-room athola/claude-night-market
Table of Contents Overview Reversibility-Based Routing When to Use When NOT to Use Expert Panel Deliberation Protocol Integration Usage Output Configuration Related Skills War Room Skill Orchestrate multi-LLM deliberation for complex strategic decisions. Overview The War Room convenes multiple AI experts to analyze problems from diverse perspectives, challenge assumptions through adversarial review, and synthesize optimal approaches under the guidance of a Supreme Commander. Philosophy "The...
35
29316 cloud-aws-ec2 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]
35
29317 react-hook-creator jeremylongshore/claude-code-plugins-plus-skills
React Hook Creator Purpose This skill provides automated assistance for react hook creator tasks within the Frontend Development domain. When to Use This skill activates automatically when you: Mention "react hook creator" in your request Ask about react hook creator patterns or best practices Need help with frontend skills covering react, vue, css, accessibility, performance optimization, and modern web development patterns. Capabilities Provides step-by-step guidance for react hook creator Fol...
35
29318 add-review-comment mlflow/mlflow
Add Review Comment Adds a review comment to a specific line in a GitHub pull request. Step 1: Locate the line to comment on Use the fetch-diff skill (optionally piped through grep ) to locate the line to comment on. Step 2: Post the comment Single-line comment: gh api repos/ < owner > / < repo > /pulls/ < pr_number > /comments \ Body must end with "🤖 Generated with Claude" on a separate line -f body = < comment > \ -f path = < file_path > \ -F line = < line_number > \ -f side = < side > \ -f co...
35
29319 pytest teachingai/full-stack-skills
pytest - Professional Python Testing Overview pytest is the industry-standard Python testing framework, offering powerful features like fixtures, parametrization, markers, plugins, and seamless integration with FastAPI, Django, and Flask. It provides a simple, scalable approach to testing from unit tests to complex integration scenarios. Key Features: Fixture system for dependency injection Parametrization for data-driven tests Rich assertion introspection (no need for self.assertEqual) Plugi...
35
29320 tdd yeachan-heo/oh-my-codex
Test-Driven Development Philosophy Core principle : Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. Good tests are integration-style: they exercise real code paths through public APIs. They describe what the system does, not how it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about i...
35
29321 pentest-whitebox-code-review jd-opensource/joysafeter
Pentest Whitebox Code Review Purpose Perform systematic white-box source code security audit using Shannon's backward taint analysis methodology. Traces from dangerous sinks back to user-controlled sources, classifies injection contexts by slot type, verifies XSS render contexts, and produces a prioritized exploitation queue for downstream proof-driven exploitation. Prerequisites Authorization Requirements Written authorization with explicit scope for source code review Source code access — full...
35
29322 debug-like-expert scientiacapital/skills
The skill emphasizes treating code you wrote with MORE skepticism than unfamiliar code, as cognitive biases about "how it should work" can blind you to actual implementation errors. Use scientific method to systematically identify root causes rather than applying quick fixes. <context_scan> Run on every invocation to detect domain-specific debugging expertise: What files are we debugging? echo "FILE_TYPES:" find . -maxdepth 2 -type f 2 > /dev/null | grep -E '\.(py|js|jsx|ts|tsx|rs|swift|c|cpp|g...
35
29323 nanobanana eyadsibai/ltk
Nano Banana A single Python entrypoint for Gemini-native Nano Banana image generation and editing, with model aliases, strict option validation, batch runs, and custom endpoint support. Workflow Open references/config.md to choose environment variables and override order. Open references/models-and-api.md to pick the right Nano Banana tier and check model-specific constraints. Prefer gemini-3.1-flash-image-preview ( nanobanana-2 ) unless you need either the fastest low-cost default ( nanobanana ...
35
29324 youtube-transcript glebis/claude-skills
YouTube Transcript Extract transcripts from YouTube videos using the youtube-transcript-api. Usage Run the script with a YouTube URL or video ID: uv run scripts/get_transcript.py "VIDEO_URL_OR_ID" With timestamps: uv run scripts/get_transcript.py "VIDEO_URL_OR_ID" --timestamps Defaults Without timestamps (default): Plain text, one line per caption segment With timestamps: [MM:SS] text format (or [HH:MM:SS] for longer videos) Supported URL Formats https://www.youtube.com/watch?v=VIDEO_ID ...
35
29325 webapp-testing snyk/agent-scan
Web Application Testing To test local web applications, write native Python Playwright scripts. Helper Scripts Available : scripts/with_server.py - Manages server lifecycle (supports multiple servers) Always run scripts with --help first to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts ra...
35
29326 ai-engineer htlin222/dotfiles
You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures. Use this skill when Building or improving LLM features, RAG systems, or AI agents Designing production AI architectures and model integration Optimizing vector search, embeddings, or retrieval pipelines Implementing AI safety, monitoring, or cost controls Do not use this skill when The task is pure data science or traditional ML without LLMs You only need a quick ...
35
29327 certificate-lifecycle-manager jeremylongshore/claude-code-plugins-plus-skills
Certificate Lifecycle Manager Purpose This skill provides automated assistance for certificate lifecycle manager tasks within the Security Advanced domain. When to Use This skill activates automatically when you: Mention "certificate lifecycle manager" in your request Ask about certificate lifecycle manager patterns or best practices Need help with advanced security skills covering penetration testing, compliance frameworks, threat modeling, and enterprise security. Capabilities Provides step-by...
35
29328 oauth-social-login dadbodgeoff/drift
OAuth Social Login Add "Sign in with Google/GitHub" to your app. When to Use This Skill Adding social login options Reducing signup friction Linking multiple auth providers to one account Enterprise SSO requirements Architecture ┌─────────────────────────────────────────────────────┐ │ User clicks │ │ "Sign in with Google" │ └─────────────────────────────────────────────────────┘ │ ▼ ┌────────────────────────────────────────...
35
29329 make mohitmishra786/low-level-dev-skills
GNU Make Purpose Guide agents through idiomatic Makefile patterns for C/C++ projects: phony targets, pattern rules, automatic dependency generation, and common build idioms. Triggers "How do I write a Makefile for my C project?" "My Makefile rebuilds everything every time" "How do I add dependency tracking to Make?" "What does $@ , $< , $^ mean?" "I'm getting 'make: Nothing to be done for all'" "How do I convert my shell compile script to a Makefile?" Workflow 1. Minimal correct Makefile for C C...
35
29330 sql htlin222/dotfiles
SQL Development Write efficient SQL queries and design schemas. When to Use Writing complex queries Query optimization Schema design Index strategy Migration planning Query Patterns Window Functions -- Running totals SELECT date , amount , SUM ( amount ) OVER ( ORDER BY date ) as running_total , AVG ( amount ) OVER ( ORDER BY date ROWS BETWEEN 6 PRECEDING AND CURRENT ROW ) as moving_avg_7d FROM transactions ; -- Ranking SELECT name , score , RANK ( ) OVER ( ORDER BY score DESC ) as rank , DENSE_...
35
29331 kubernetes-manifest-generator patricio0312rev/skills
Kubernetes Manifest Generator Generate production-ready Kubernetes manifests with security and scalability best practices. Core Workflow Define resources: Identify required K8s objects Create namespace: Isolate application resources Configure deployments: Pods, replicas, resources Setup services: Networking and load balancing Add ingress: External access routing Configure scaling: HPA and resource limits Deployment Manifest k8s/deployment.yaml apiVersion: apps/v1 kind: Deployment metadata: ...
35
29332 jq lanej/dotfiles
IMPORTANT: `jq` is the STRONGLY PREFERRED tool for ALL JSON formatting, parsing, manipulation, and analysis tasks. Use jq instead of Python/Node.js scripts, grep, awk, or other text processing tools when working with JSON data. Core Philosophy - Always use jq for JSON: If the data is JSON or can be converted to JSON, use jq - Streaming-friendly: jq processes JSON as a stream, making it memory-efficient for large files - Composable: jq filters can be chained with pipes, just like shell comma...
35
29333 image-generate agntswrm/agent-media
Image Generate Generates an image from a text prompt using AI image generation models. Command npx agent-media@latest image generate --prompt < text > [ options ] Inputs Option Required Description --prompt Yes Text description of the image to generate --width No Width of the generated image in pixels (default: 1280) --height No Height of the generated image in pixels (default: 720) --count No Number of images to generate (default: 1) --out No Output path, filename or directory (default: ./) --p...
35
29334 scientific-computing eyadsibai/ltk
Domain-specific Python libraries for scientific applications. Libraries | AstroPy | Astronomy | Coordinates, units, FITS files | BioPython | Bioinformatics | Sequences, BLAST, PDB | SymPy | Mathematics | Symbolic computation | Statsmodels | Statistics | Statistical modeling, tests AstroPy Astronomy and astrophysics computations. Key capabilities: - Units: Physical unit handling with automatic conversion - Coordinates: Celestial coordinate systems (ICRS, galactic, etc.) -...
35
29335 custom-builtin-functions chainloop-dev/chainloop
Policy Engine Extension The OPA/Rego policy engine supports custom built-in functions written in Go. Adding Custom Built-ins : Create Built-in Implementation (e.g., pkg/policies/engine/rego/builtins/myfeature.go ): package builtins import ( "github.com/open-policy-agent/opa/ast" "github.com/open-policy-agent/opa/topdown" "github.com/open-policy-agent/opa/types" ) const myFuncName = "chainloop.my_function" func RegisterMyBuiltins ( ) error { return Register ( & ast . Builtin { Name : myFuncName ,...
35
29336 cancel-async-tasks letta-ai/skills
Cancel Async Tasks Overview This skill provides guidance for implementing robust asyncio task cancellation in Python, particularly when dealing with signal handling (SIGINT/KeyboardInterrupt), semaphore-based concurrency limiting, and ensuring proper cleanup of all tasks including those waiting in queues. Key Concepts Signal Propagation in Asyncio Understanding how signals interact with asyncio is critical: KeyboardInterrupt vs CancelledError : When SIGINT is received during asyncio.run() , the ...
35
29337 ecomode yeachan-heo/oh-my-codex
Ecomode Skill Activates token-efficient parallel execution for pro-plan users who prioritize cost efficiency. When Activated This skill enhances Claude's capabilities by: Parallel Execution: Running multiple agents simultaneously for independent tasks Token-Conscious Routing: Preferring Haiku and Sonnet agents, avoiding Opus Background Operations: Using run_in_background: true for long operations Persistence Enforcement: Never stopping until all tasks are verified complete Cost Optimization:...
35
29338 upgrading-chart chainloop-dev/chainloop
Upgrading Helm Chart Dependencies This skill automates the upgrade process for Helm chart dependencies in the Chainloop project. Supports PostgreSQL and Vault (both Bitnami charts). CRITICAL RESTRICTIONS Version Upgrade Rules : Patch upgrades (1.2.3 → 1.2.4): ALLOWED Minor upgrades (1.2.x → 1.3.x): ALLOWED Major upgrades (1.x.x → 2.x.x): FORBIDDEN - STOP IMMEDIATELY MANDATORY : If major version upgrade is detected, STOP the process and inform the user that manual review is required. Upgrade Type...
35
29339 data-enrichment merit-systems/x402scan-skills
Prereq: read bulk-operations/SKILL.md first — JSONL piping, dry-run/digest, history, and rate-limit hygiene live there. This skill is the upsert-by-natural-key workflow on top. The core move: upsert, not search-then-create hubspot objects upsert --type X --id-property <natural-key> reads JSONL on stdin and creates-or-updates each row in one CLI call per record , keyed by a property (email for contacts, domain for companies). No race window, no branching. Do not loop search → empty? → create . Pe...
35
29340 frappe-service sergio-bershadsky/ai
Frappe Service Layer Design Create well-structured service layer classes that encapsulate business logic, coordinate between repositories, and provide clean interfaces for controllers and APIs. When to Use Implementing complex business logic Coordinating operations across multiple DocTypes Creating reusable business operations Separating concerns between controllers and data access Building transaction-aware operations Arguments /frappe-service <service_name> [--doctype <doctype>] [--operations ...
35
29341 task-management joelhooks/joelclaw
Task Management Tasks are tracked in a simple TASKS.md file that both you and the user can edit. File Location Always use TASKS.md in the current working directory. If it exists, read/write to it If it doesn't exist, create it with the template below Dashboard Setup (First Run) A visual dashboard is available for managing tasks and memory. On first interaction with tasks: Check if dashboard.html exists in the current working directory If not, copy it from ${CLAUDE_PLUGIN_ROOT}/skills/dashboard.h...
35
29342 devdocs-requirements ab300819/skills
需求扩写 将用户简短需求扩展为结构化的需求文档,建立功能点、用户故事、验收标准的关联体系。 语言规则 支持中英文提问 统一中文回复 使用中文生成文档 触发条件 用户提供功能需求或想法 用户要求创建/编写 PRD 用户想要澄清或记录需求 来自 /devdocs-feature 的增量需求委托 用户需要补充项目背景信息(尤其是 retrofit 后) 用户提供参考资料、领域知识、技术约束 运行模式 /devdocs-requirements → 自动检测模式 /devdocs-requirements --incremental → 强制增量模式(追加功能点) /devdocs-requirements --context → 背景信息模式(追加/更新背景) /devdocs-requirements --fast → 跳过 Plan 模式,直接生成,仅最终确认 模式 触发条件 说明 初始模式 无 01-requirements.md 从零创建需求文档 增量模式 已有 01-requirements.md 扫描编号 + 追加功能点/用户故事/验收标准 背景信息模式...
35
29343 build-cython-ext letta-ai/skills
Build Cython Extensions This skill provides guidance for building Cython extensions and resolving compatibility issues, with particular focus on numpy version compatibility problems. When to Use This Skill Building or compiling Cython extensions (.pyx files) Fixing numpy compatibility issues in Cython code Migrating Cython projects to work with numpy 2.0+ Resolving deprecated numpy type errors (np.int, np.float, np.bool, etc.) Troubleshooting Cython compilation failures Key File Types to Exami...
35
29344 kotlin-android pluginagentmarketplace/custom-plugin-kotlin
Kotlin Android Skill Production-ready Android development with Jetpack libraries. Topics Covered MVVM Pattern @HiltViewModel class UserViewModel @Inject constructor ( private val repository : UserRepository ) : ViewModel ( ) { private val _uiState = MutableStateFlow ( UiState ( ) ) val uiState = _uiState . asStateFlow ( ) fun load ( ) = viewModelScope . launch { _uiState . update { it . copy ( isLoading = true ) } repository . getUsers ( ) . onSuccess { users -> _uiState . update { it . copy ( u...
35
29345 effect-patterns-hub mepuka/effect-ontology
Effect Patterns Hub Purpose: Provide quick access to 130+ curated Effect-TS patterns from the EffectPatterns repository. Use this skill to find specific implementation patterns, compare approaches, and reference best practices. Triggers Looking for a specific Effect pattern or idiom Need real-world examples of Effect concepts Want to see multiple approaches to the same problem Comparing implementation strategies Learning new Effect features Pattern Library Location Local Patterns : .claude/skill...
35
29346 salesloft membranedev/application-skills
Salesloft Salesloft is a sales engagement platform that helps sales teams automate and personalize their outreach. It's used by sales development representatives (SDRs) and account executives to manage communications and track engagement with prospects. Official docs: https://developers.salesloft.com/ Salesloft Overview Account Cadence Cadence Enrollment Contact Do Not Contact List Person Team Meeting User Use action names and parameters as needed. Working with Salesloft This skill uses the Memb...
35
29347 code-review carvalab/k-skills
Two-axis review of the diff between HEAD and a fixed point the user supplies: Standards — does the code conform to this repo's documented coding standards? Spec — does the code faithfully implement the originating issue / PRD / spec? Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings. The issue tracker should have been provided to you — run /setup-matt-pocock-skills if docs/agents/issue-tracker.md is missing. Process 1. Pin ...
35
29348 python-executor inference-sh/agent-skills
Install the belt CLI skill: npx skills add belt-sh/cli Python Code Executor Execute Python code in a safe, sandboxed environment with 100+ pre-installed libraries. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Show more Installs 51.4K Repository 101-skills/superpowers GitHub Stars 4 First Seen Aug 31, 2026 Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk Warn
35
29349 mocking-assistant patricio0312rev/skills
Mocking Assistant Create reliable mocks for APIs and services in tests. MSW API Mocking // mocks/handlers.ts import { http, HttpResponse } from "msw"; export const handlers = [ // GET endpoint http.get("/api/users/:id", ({ params }) => { const { id } = params; return HttpResponse.json({ id, name: "John Doe", email: "john@example.com", }); }), // POST endpoint http.post("/api/users", async ({ request }) => { const body = await request.json(); ...
35
29350 vercel-react-best-practices guanyang/antigravity-skills
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...
35