Testing
Unit tests, integration tests, test automation
starchain
by mouseroser
星链（StarChain）— OpenClaw 多 agent 协作锻造流水线 v1.8。从 Step 1 分级到 Step 7 交付的全自动编排，覆盖 spec-kit 门控、交叉审查、修复循环、测试回归和 Epoch 回退。
test-generator
by nimiusrd
Generate or update tests for changed files in the current git branch, using statement coverage as the evaluation metric (target: 80%+). Use when: (1) the user asks to "write tests for my changes", "add tests for the current branch", or "improve coverage", (2) after implementing a feature to ensure adequate test coverage, (3) before a PR to verify changed code is tested. Supports Vitest and Cargo projects. Invoked with /test-generator or phrases like "generate tests", "test my changes", "cover the diff".
writing-quality-tests
by ederheisler
Use when designing or refactoring automated tests to make them high-signal, reliable, and maintainable across unit, integration, and end-to-end suites.
discovering-alternatives
by squirrel289
"Exhaustive discovery of build, buy, and hybrid options for a stated problem, using pretrained knowledge plus RAG (local memory, repo search, user-provided details, and web search). Use when you need a comprehensive alternatives list and a decision matrix with ranked options. Trigger phrases: discover alternatives, build vs buy, solution landscape, option discovery, vendor shortlist."
java-unit-test-expert
by Xunzi229
按严格的 Mock 与断言规则，基于 JUnit 5 和 Mockito 生成高质量 Java 单元测试。适用于编写或评审 Spring Boot 2.1.x 的 service、controller 单元测试，或当用户提到 Java 单元测试、JUnit、Mockito、测试覆盖率时使用。
Waiona — SKILL: Generación de Código
by rodrigozucchini
¿Hay spec de service y controller?
feature-summary
by prulloac
Create comprehensive feature documentation summaries that describe current and future capabilities. Use after feature-breakdown to document what a feature does, its business value, technical implementation, and roadmap. Ideal for creating user-facing documentation and feature catalogs in docs/features/<feature-name>/ format.
mdtest
by PeronGH
Write and maintain tests as Markdown files that AI agents execute. Use when adding test coverage, validating features, or deciding on a testing strategy — especially during early development or for flows that are expensive to test in code.
arinhub-verify-requirements-coverage
by arinhubcom
Use this skill to verify requirements when using the "ah" prefix. Use when asked to "ah verify requirements", "ah verify requirements issue 42", "ah verify requirements PR 123", or "ah verify requirements PR 123, issue 42". Verify that a PR or local changes fully implement requirements from a linked GitHub issue.
uade-docker
by rib1
Work on the UADE Docker repository for Amiga module playback and conversion. Use when editing this repo's Docker setup, Flask backend, vanilla JavaScript frontend, tests, CI workflows, deployment configuration, or documentation, especially when repo-specific conventions and architecture matter.
devdocs-test-cases
by ab300819
Design test cases based on requirements. Use when users need test case design, testing strategy, or QA planning. Triggers on keywords like "test cases", "test design", "unit test", "integration test", "e2e test".
clojure-write
by aiagentskills
Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript code.
ad-pre-launch-scoring
by tonyflo79
Probabilistic evaluation and variant prioritization for ad testing sequences. Use after the variant matrix (A09) is assembled and you need to determine which variants to test first. Scores variants with probability ranges (not false precision) and assigns Tier 1/2/3 priority for testing sequence. Every score traces to evidence from A01 intelligence, A06 Arena results, benchmarks, or historical data. The goal is prioritization, not perfection — tier assignment matters, decimal precision does not. Trigger when users mention ad scoring, variant prioritization, which ads to test first, pre-launch evaluation, or predicting ad performance. Requires A09 variant matrix.
ai-sdk
by dinequickly
Build or refactor apps using the Vercel AI SDK (core or RSC). Use when implementing tool calling, returning JSON for UI rendering, mapping tool outputs to React components, or streaming UI with @ai-sdk/rsc in Next.js App Router.
deepmind
by UZUB18
Enforce a strict "strong reasoner & planner" workflow before any tool call, code change, or user-facing response; use when the user asks to apply their system prompt, wants more rigorous planning, debugging via hypotheses, careful dependency/risk analysis, or assumption documentation only when ambiguity is high-impact.
ad-arena
by tonyflo79
Multi-persona adversarial evaluation of complete ad concepts using 7 ad-specific personas across 3 competitive rounds. Use after visual direction (A05) is complete and you need to stress-test ad concepts before production. Evaluates the COMPLETE concept (hook + script + visual as an atomic unit) — never isolated elements. Seven personas provide adversarial critique, and quality peaks in Round 3. Human selects the winners; the Arena recommends with transparent scoring. Produces AD-ARENA- RESULTS.md with scored candidates and synthesis. Trigger when users mention ad testing, concept evaluation, Arena for ads, ad review, or stress-testing ad creative. Requires A04 scripts and A05 visual direction as complete concepts.
traffic-channel-finder
by ntdrun
Design traffic strategy, build data-backed channel lists, or plan audience acquisition using algorithmic evaluation. Activates for "build my traffic plan," "create promotion strategy," "evaluate marketing channels," or traffic acquisition planning requests.
sonarqube-quality-gate-playbook
by AgustinAlbonico
Playbook iterativo para llevar proyectos Node y TypeScript (NestJS + React en monorepo) a cumplir Quality Gates de SonarQube sin romper build ni pipelines. Usar cuando se necesite subir cobertura priorizando New Code, eliminar issues nuevos (Bugs, Vulnerabilities, Code Smells), revisar Security Hotspots y controlar duplicacion y deuda tecnica.
vox-best-practice
by fleek-fitness
"vox.ai development best practices. (1) Voice agent system prompt design, authoring, and refactoring (template, {{...}} variable injection, filler options, character normalization, tools/silence actions, testing/production). (2) vox MCP server integration for ChatGPT, Claude Desktop, Claude Code, Cursor, OpenCode, Codex, VS Code Copilot."
feature-planner
by withAIcolleague
Creates phase-based feature plans with quality gates and incremental delivery structure. Use when planning features, organizing work, breaking down tasks, creating roadmaps, or structuring development strategy. Keywords: plan, planning, phases, breakdown, strategy, roadmap, organize, structure, outline.
UX Researcher
by anorbert-cmyk
Pragmatic UX Researcher focusing on fast, risk-reducing research methods and actionable insights.
database-testing
by karchtho
Database testing with Prisma and PostgreSQL, repository testing, transaction testing, migration testing, test data management. Activates when user mentions "database testing", "Prisma testing", "repository test", "PostgreSQL test", "transaction testing", "test database", or wants to test database operations.
m11-ecosystem
by lywa1998
"Use when integrating crates or ecosystem questions. Keywords: E0425, E0433, E0603, crate, cargo, dependency, feature flag, workspace, which crate to use, using external C libraries, creating Python extensions, PyO3, wasm, WebAssembly, bindgen, cbindgen, napi-rs, cannot find, private, crate recommendation, best crate for, Cargo.toml, features, crate 推荐, 依赖管理, 特性标志, 工作空间, Python 绑定"
Backstage Custom Resource
by kadel
This skill should be used when the user asks to "create Backstage CR", "create RHDH custom resource", "configure rhdh-operator", "create Backstage manifest", "modify Backstage CR", "configure RHDH deployment", "add dynamic plugins to CR", "configure Backstage database", "set up Backstage route", "configure app-config for RHDH", "create rhdh.redhat.com/v1alpha Backstage", or mentions creating or modifying a Backstage Custom Resource for the rhdh-operator.