测试
单元测试、集成测试与测试自动化
implement
digipulse-engineering
Generate correct, minimal, maintainable code that satisfies a validated Story's acceptance criteria against an execution plan. Activate when a Story is validated, a plan exists, and all prerequisites are unambiguous.
k8s-yaml-generator
akin-ozer
Comprehensive toolkit for generating, validating, and managing Kubernetes YAML resources. Use this skill when creating Kubernetes manifests (Deployments, Services, ConfigMaps, StatefulSets, etc.), working with Custom Resource Definitions (CRDs), or generating production-ready K8s configurations.
gsd-to-autoforge-spec
AutoForgeAI
Convert GSD codebase mapping to AutoForge app_spec.txt. This skill should be used when the user has run /gsd:map-codebase and wants to use AutoForge on an existing project. Triggers: "convert to autoforge", "gsd to spec", "create app_spec from codebase", "use autoforge on existing project", after /gsd:map-codebase completion.
bikeshed-conversion
w3c
Guidelines for converting W3C specs to Bikeshed format. Covers anchor ID preservation, dfn handling, and common pitfalls. Read this before any Bikeshed conversion or migration work.
css-scss-human-made
humanmade
Human Made CSS and SCSS standards. Apply when writing styles, reviewing CSS/SCSS, or working on theme styling. Covers BEM naming, CSS custom properties, theme.json integration, and Stylelint configuration.
eslint-plugin
third774
Author custom ESLint plugins and rules with test-driven development. Supports flat config (ESLint 9+) and legacy formats. Uses @typescript-eslint/rule-tester for testing. Covers problem, suggestion, and layout rules including auto-fixers and type-aware rules. Use when creating or modifying ESLint rules, plugins, custom linting logic, or authoring auto-fixers.
tdd-workflow
sotayamashita
Test-driven development with Kent Beck's canonical 5-step workflow: Test List, Write Test, Make Pass, Refactor, Repeat. Strict vertical-slice cycles with automatic project detection. Use when the user asks to "write tests first", "use TDD", "red-green-refactor", "test-driven development", "build a feature with TDD", "fix a bug with TDD", wants test-first development for any language or framework, or mentions "tracer bullet" or "vertical slice".
abx-dl
ArchiveBox
Use this when working on the standalone ArchiveBox downloader CLI, extractor orchestration, plugin execution, config, and output verification.
test-driven-development
CodingCossack
Red-green-refactor development methodology requiring verified test coverage. Use for feature implementation, bugfixes, refactoring, or any behavior changes where tests must prove correctness.
apple-swift
maroffo
"Apple platform development with Swift 6, SwiftUI, async/await, and performance. Use when working with .swift files, Package.swift, Xcode projects, or building for iOS/macOS/watchOS/visionOS."
ruby
maroffo
"Ruby gem development with modern tooling, testing, and publishing. Use when working with .gemspec, Rakefile, or user asks about gem structure, RSpec for gems, Bundler, or gem publishing. Not for Rails apps (use rails skill)."
jest-react-testing
manutej
Comprehensive React component testing with Jest and React Testing Library covering configuration, mocking strategies, async testing patterns, hooks testing, and integration testing best practices
homebrew-publish
regenrek
Publish CLIs/TUIs to Homebrew via a personal tap. Use when asked to create or manage a Homebrew tap repo, generate or update formulae, compute sha256, test installs, or ship new releases for Go, Rust, Node/TypeScript, Python, or prebuilt binaries.
near-smart-contracts
near
NEAR Protocol smart contract development in Rust. Use when writing, reviewing, or deploying NEAR smart contracts. Covers contract structure, state management, cross-contract calls, testing, security, and optimization patterns. Based on near-sdk v5.x with modern macro syntax.
ab-test-setup
sundial-org
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
adversarial-reasoning
kimasplund
Red-team thinking for robustness testing and edge case discovery. Use when you need to stress-test solutions, find vulnerabilities, anticipate failures, or challenge assumptions. Ideal for security review, system design validation, decision stress-testing, and pre-mortem analysis. Example: "We've designed an auth system" → Attack it from 10 angles before shipping.
code-review
Geeksfino
Reviews code for quality, best practices, and potential issues. Use when asked to review, audit, or check code for problems.
image-assistant
ssdiwu
配图助手 - 把文章/模块内容转成统一风格、少字高可读的信息图提示词；先定"需要几张图+每张讲什么"，再压缩文案与隐喻，最后输出可直接复制的生图提示词并迭代。
dotfile-from-spec
harperreed
Use when you have a spec, design doc, structured plan, or prompt_plan and need to generate a pipeline Graphviz DOT file for headless autonomous building. The agent reads the spec, extracts build pipeline phases, determines tech stack, asks about human gates and model preferences, generates a validated DOT digraph with rich self-contained prompts, and saves it to the project root. Handles any language or framework.
dotfile-brainstorm
harperreed
Use when you want to build a project but don't have a spec yet and need to brainstorm the idea into a design doc structured for pipeline DOT generation. Use when starting from a vague idea, project concept, or feature request that needs to become a headless autonomous build pipeline.
dotfile-hone
harperreed
Use when a pipeline DOT file has passed structural validation but may still have flow inefficiencies, spec fidelity gaps, or information loss in prompts. Use after dotfile-audit or dotfile-from-spec when you want to deeply verify a pipeline captures everything from the original spec. Use when prompts might be missing critical domain rules, data models, or invariants.
fork-test
Geeksfino
Minimal skill for testing context fork behavior. Do not use in production.
dotfile-audit
harperreed
Use when you have an existing pipeline DOT file that needs review, fixing, or validation. Use when validation produces warnings or errors, when a DOT file was hand-written or generated by another tool, or when you want to verify a pipeline covers 100% of a spec before running it.
score-covariance-estimate
microprediction
Score and compare covariance estimates with precise's assessor panel. Use when you need to judge an estimate out-of-sample or rank competing estimators — and especially in high dimensions, where the plain held-out likelihood is misleading.