Skip to content

스킬 검색.../

Agent Skill Search Engine

검색

검색
카테고리
직업

About

About
Privacy
Terms

© 2026 Skills Pool. All rights reserved.

테스팅 | Skills Pool

카테고리테스팅

카테고리

테스팅

28310개의 스킬

검색 모든 카테고리 보기

AI에게 물어보기

28310개의 스킬

Testing With Sandbox

Use when capturing outbound email in development or staging without delivering to real recipients, inspecting HTML or headers, running spam or structure checks, or automating tests against a fake inbox. Use when testing outgoing mail from an app without committing to a production ESP yet. Use when using Mailtrap Email Sandbox, Sandbox API, or sandbox-mode sending.

Test

Gera testes automatizados (unitários e de feature) para um arquivo, classe ou método Laravel. Use quando o usuário pedir para testar, cobrir ou escrever testes para um trecho de código.

Test

Run pytest tests for the neuromf project

Lara Test

Create Feature or Unit tests for Laravel endpoints. Use when the user asks to write tests or add test coverage.

Test All

Lance les tests Symfony, Laravel, Hono et TanStack du monorepo

Verify

Run project health check — validates structure, env, ports, deps, TypeScript, and backend tests.

Previous 1…940 941 942…944 Next

Bug Fix

Fix bugs with regression prevention using test-first approach

makinsonmjttrt0

Full Audit

Run all 11 audit agents in parallel, then consolidate findings with fix-planner

makinsonmjttrt0

Preamble (run first)

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack)

Remediation Micro Roles Workflow

Aplica sub-micro-tarefas por papel (foco único) quando o trabalho envolve planos de dev, correcções, testes ou marcos remediation/distribution. Keywords: micro-tarefas, papel, arquiteto, testador, Camada A, remediation-milestones, single_focus.

Mcp Workflow

FastMCP + DSIM workflow for UVM test execution. Use when compiling tests, running simulations, executing regression suites, or troubleshooting MCP integration.

Assertion Design

SystemVerilog Assertions (SVA) as executable specifications. Use when defining timing requirements, protocol specifications, or formal properties for RTL verification.

Implement Spec

Implementiert eine Spezifikation aus docs/specs/. Liest die Spec-Datei, implementiert den Code gemäß der Vorgaben und schreibt Tests. Verwende diesen Skill wenn du eine Phase des Projekts umsetzen willst.

Eval Bootstrap — Generate Evaluator Code from Production Traces

Bootstrap SDK-based evaluators from production traces. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", or wants to generate BaseEvaluator/LLMJudge code from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.

managementmaars-art0

Agent Test

Engenheiro de testes — cria, mantém e executa testes automatizados para o projeto. Prioriza cobertura de src/domain/ com funções puras, fixtures de pptx.Presentation e pytest. Segue as convenções de AGENTS.md. Use quando o usuário pedir criação de testes, cobertura de código, pytest, fixtures ou análise de testes existentes.

Gsd Validate Phase

Retroactively audit and fill Nyquist validation gaps for a completed phase

marcos-vinicius-mafei0

Tdd Rust

TDD workflow for RTK filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.

martinstannard0

Test Coverage Analysis

Run pytest unit tests with coverage analysis and identify gaps. Use when: checking test coverage, finding untested code, planning what to test next, evaluating test quality, improving unit test coverage.

matthieumarshall0

Test

Use this skill to run host-side unit tests. Triggers during TDD red/green cycles, before finishing a development branch, and when verifying logic changes. Tests compile with gcc and mock GBDK headers — no hardware required.

Csharp Mstest

Generate MSTest unit tests for C# classes following strict naming conventions, assertion patterns, and structural standards. Use this skill whenever asked to write, scaffold, or review C# unit tests.

Pentest Checklist

Provide a comprehensive checklist for planning, executing, and following up on penetration tests. Ensure thorough preparation, proper scoping, and effective remediation of discovered vulnerabilities.

Spring Boot Domain Tester

Generates high-quality unit tests for Spring Boot domain objects (Entities). Focuses on logic, immutability, equality (ID-based), and 100% branch coverage without requiring a Spring context.

Test Pattern Analysis

Analyze existing tests to identify patterns, fixtures, and conventions before writing new tests

Buildkite Test Engine

This skill should be used when the user asks to "split tests across machines", "set up test splitting", "parallelize test suite", "detect flaky tests", "quarantine flaky tests", "configure test collectors", "speed up tests", "set up bktec", "configure test engine", or "reduce flaky test failures". Also use when the user mentions bktec, Test Engine, test suites, BUILDKITE_TEST_ENGINE_* environment variables, BUILDKITE_ANALYTICS_TOKEN, test-collector plugin, test reliability scores, test timing data, or asks about Buildkite test splitting and flaky test management.

Playwright Test

Creates or modifies Playwright E2E tests. Use when testing user flows or verifying UI behavior.

Full Research Workflow

Coase 工作流 W1 完整研究管线（经管 Research Co-pilot）。从研究方向和数据出发，依次执行：读 readme / 扫描数据 → 生成 X 个假设 → 多模型对抗分析与评分迭代 → 阈值过滤 → 研究方案设计 → 模型对抗审方案 → 主回归 → 判定（p < 0.05 + effect size 双重）→ 通过则进入机制 + 鲁棒性检验；不通过则有限迭代或进入淘汰库 → 对检验结果再次模型对抗 → 保存最终表图 → 处理下一个候选假设。全程可选 human-in-the-loop。遵循《经管 Research Co-pilot 产品讨论书》第三节的 14 步流程。

Load Test Scenario Planner

Load Test Scenario Planner - Auto-activating skill for Performance Testing. Triggers on: load test scenario planner, load test scenario planner Part of the Performance Testing skill category.

Repo Verify Hard

Executable — discover registry hard skills; run verify or fallback static/test/harness/build chain.

Validate Harness Doc Hard

Executable check — docs/HARNESS.md exists with minimum substance.

Repo Verify Hard

Executable — discover harness hard skills; run verify or fallback static/test/harness/build chain.