Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
8,868 results · page 266 of 296
- View details
dotnet-testing-autofixture-nsubstitute-integrationSkillAI & models
AutoFixture 與 NSubstitute 整合指南 - 實現自動模擬 (Auto-Mocking)。當需要自動建立 Mock 物件、簡化複雜相依性注入測試時使用。涵蓋 AutoNSubstituteDataAttribute、Frozen 機制、Greedy 建構策略。包含 IMapper (AutoMapper/Mapster) 等特殊相依性的客製化處理。 Make sure to use this skill whenever the user mentions AutoFixture with NSubstitute, auto-mocking, AutoNSubstitute
Ready to connect
- View details
dotnet-testing-awesome-assertions-guideSkillAI & models
使用 AwesomeAssertions 進行流暢且可讀的測試斷言技能。當需要撰寫清晰的斷言、比對物件、驗證集合、處理複雜比對時使用。涵蓋 Should()、BeEquivalentTo()、Contain()、ThrowAsync() 等完整 API。 Make sure to use this skill whenever the user mentions assertions, Should(), BeEquivalentTo, fluent assertions, AwesomeAssertions, or wants more readable test assertions, e
Ready to connect
- View details
dotnet-testing-complex-object-comparisonSkillAI & models
處理複雜物件比對與深層驗證的專門技能。當需要比對深層物件、排除特定屬性、處理循環參照、驗證 DTO/Entity 時使用。涵蓋 BeEquivalentTo、Excluding、Including、自訂比對規則等。 Make sure to use this skill whenever the user mentions deep object comparison, BeEquivalentTo, DTO comparison, Excluding properties, or complex object validation in tests, even if they don't e
Ready to connect
- View details
dotnet-testing-datetime-testing-timeproviderSkillAI & models
使用 TimeProvider 測試時間相依邏輯的專門技能。當需要測試 DateTime、控制時間流逝、處理時區轉換、測試過期邏輯時使用。涵蓋 TimeProvider 抽象化、FakeTimeProvider 時間控制、時間凍結與快轉等。 Make sure to use this skill whenever the user mentions DateTime testing, TimeProvider, FakeTimeProvider, time-dependent logic, cache expiration, or token expiration testing, even
Ready to connect
- View details
dotnet-testing-fluentvalidation-testingSkillAI & models
測試 FluentValidation 驗證器的專門技能。當需要為 Validator 類別建立測試、驗證業務規則、測試錯誤訊息時使用。涵蓋 FluentValidation.TestHelper 完整使用、ShouldHaveValidationErrorFor、非同步驗證、跨欄位邏輯等。 Make sure to use this skill whenever the user mentions FluentValidation testing, Validator testing, ShouldHaveValidationErrorFor, TestHelper, or testing
Ready to connect
- View details
dotnet-testing-nsubstitute-mockingSkillAI & models
使用 NSubstitute 建立測試替身（Mock、Stub、Spy）的專門技能。當需要隔離外部依賴、模擬介面行為、驗證方法呼叫時使用。涵蓋 Substitute.For、Returns、Received、Throws 等完整指引。 Make sure to use this skill whenever the user mentions mock, stub, spy, NSubstitute, test double, 測試替身, Substitute.For, Returns, Received, or dependency isolation, even if they don't
Ready to connect
- View details
dotnet-testing-test-data-builder-patternSkillAI & models
Test Data Builder Pattern 完整實作指南。當需要使用建構者模式建立可維護的測試資料或簡化複雜物件的測試準備時使用。涵蓋流暢介面、語意化方法、預設值設計與 Builder 組合模式。 Make sure to use this skill whenever the user mentions test data builder, builder pattern, fluent interface, Object Mother, or test data preparation for complex objects, even if they don't explicit
Ready to connect
- View details
dotnet-testing-test-naming-conventionsSkillAI & models
測試命名規範與最佳實踐的專門技能。當需要為測試方法命名、改進測試可讀性、建立命名標準時使用。涵蓋三段式命名法、中文命名建議、測試類別命名等。 Make sure to use this skill whenever the user mentions test naming, how to name tests, test readability, or test method naming conventions, even if they don't explicitly ask for naming guidance. Keywords: test naming, 測試命名, namin
Ready to connect
- View details
dotnet-testing-unit-test-fundamentalsSkillAI & models
.NET 單元測試基礎與 FIRST 原則的專門技能。當需要建立單元測試、了解測試基礎、學習 3A Pattern、掌握測試最佳實踐時使用。涵蓋 FIRST 原則、AAA Pattern、Fact/Theory、測試金字塔等。 Make sure to use this skill whenever the user mentions unit testing fundamentals, FIRST principles, AAA/3A pattern, or wants to learn how to write basic .NET tests, even if they don't ex
Ready to connect
- View details
dotnet-testing-xunit-project-setupSkillAI & models
xUnit 測試專案建立與設定的專門技能。當需要建立測試專案、設定專案結構、配置 NuGet 套件、組織測試資料夾時使用。涵蓋 csproj 設定、套件管理、專案結構、xunit.runner.json 配置等。 Make sure to use this skill whenever the user mentions creating a test project, xUnit setup, project structure for tests, NuGet test packages, or csproj configuration for testing, even if they
Ready to connect
- View details
effect-ts-patternsSkillAI & models
Mandatory Effect-TS coding patterns for the Reactive Agents framework. Use when writing any TypeScript code, creating services, defining types, handling errors, or composing layers in this project.
Ready to connect
- View details
evaluationSkillAI & models
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
Ready to connect
- View details
fastapi-senior-devSkillAI & models
Senior Python Backend Engineer skill for FastAPI. Use when scaffolding production-ready APIs, enforcing clean architecture, optimizing async patterns, or auditing FastAPI codebases.
Ready to connect
- View details
github-cliSkillAI & models
Safety-first GitHub CLI skill wrapping `gh` (v2.86+). Use when performing GitHub operations — PRs, issues, releases, repos, Actions, API calls. Enforces risk classification with mandatory confirmation for destructive/forbidden operations.
Ready to connect
- View details
grill-meSkillAI & models
One move you can run on anything: point grill-me at a target and it makes you defend your thinking from first principles until the true matter is clear. Point it at your working contract and it rewrites the weak lines in place. Point it at a brief and it produces a Requirements Handshake. Point it a
Ready to connect
- View details
harness-improvement-loopSkillAI & models
Agentic harness diagnostic + improvement loop. Probes the framework with real model runs, uses the rax-diagnose CLI to root-cause failures from structured trace data, ships ONE coordinated architectural fix, verifies via before/after diff, commits with empirical evidence. Use at the start of any har
Ready to connect
- View details
implement-serviceSkillAI & models
Create a new Effect-TS service following the mandatory Reactive Agents patterns. Use when adding a service to any package.
Ready to connect
- View details
implement-testSkillAI & models
Write tests for a Reactive Agents package or service using Bun test runner and Effect-TS patterns. Use when creating tests for any module in this project.
Ready to connect
- View details
installing-skill-trackerSkillAI & models
Installs Claude Code hooks for automatic skill usage measurement. Use when setting up skill tracking infrastructure in a new project. NOT when hooks are already installed (run verify.py to check).
Ready to connect
- View details
interaction-autonomySkillAI & models
Control agent autonomy with durable human-in-the-loop approval gates, agent-initiated user-input pauses, and runtime pause/resume/stop controls.
Ready to connect
- View details
kernel-extensionSkillAI & models
Add new behavior to the composable kernel — new Phase, Guard, MetaTool, or custom kernel variant. Use when extending agent reasoning, adding tool call filtering, or building a custom kernel for a new strategy.
Ready to connect
- View details
llm-api-contractSkillAI & models
LLMService API contract — the correct signatures for complete(), stream(), embed(), and response types. Use when calling LLMService from any layer, writing reasoning strategies, or building LLM-dependent features.
Ready to connect
- View details
local-llm-claude-codeSkillAI & models
Set up a FREE local LLM (via Ollama) and connect Claude Code to it so it runs offline with no API costs. Use this whenever the user wants to run Claude Code on a local/self-hosted model, use Ollama/Qwen/Llama/Mistral/DeepSeek with Claude Code, get a "free" or "offline" coding agent, avoid Anthropic
Ready to connect
- View details
materialreacttable-masterySkillAI & models
Material React Table V3 expert skill. Use when building feature-rich data tables w/ MUI styling, server-side ops, CRUD editing, virtualization, or complex filtering/sorting.
Ready to connect
- View details
mission-briefSkillAI & models
Compose a MissionBrief YAML block to prepend to any Agent dispatch during the team-ownership dev-contract pilot (2026-05-23 → 2026-06-15). Use BEFORE spawning kernel-warden or any future warden. Fails if missing end-state, why, authority-bounds, or success-criteria.
Ready to connect
- View details
multi-agent-orchestrationSkillAI & models
Compose multiple agents as callable tools, spawn dynamic sub-agents at runtime, and wire remote A2A agents into a coordinated pipeline.
Ready to connect
- View details
multi-agent-patternsSkillAI & models
Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures
Ready to connect
- View details
multi-model-reviewSkillAI & models
Multi-Model Code Review: consensus-based analysis patterns, consolidation methodology, conflict resolution, and false positive triage.
Ready to connect
- View details
n8n-cliSkillAI & models
Safety-first n8n management skill — list/inspect workflows, executions, credentials, tags, projects, variables, source-control status; trigger runs (CLI/webhook); activate/deactivate; backup/restore; audit; diff. Two backends auto-detect: REST API (cloud + remote self-hosted, urllib stdlib) & `n8n`
Ready to connect
- View details
natural-languageSkillAI & models
Shapes how every reply to the user gets written - plain everyday words instead of corporate or AI-sounding phrasing, real sentences instead of bullet-heavy formatting, no forced dash punctuation, and at most a rare bit of dry humor when it genuinely fits. Use this for every conversational response w
Ready to connect
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.