AI Agent Skills

Use when generating mock objects with package:mockito and build_runner, or choosing between mocktail and mockito.

Use when migrating test assertions from legacy package:matcher expect() syntax to package:checks fluent assertions.

Use when creating end-to-end integration tests, automating user journey tests, or running tests on real devices and emulators.

Use when writing widget tests, finding UI elements with finders, simulating user gestures, or testing widget state updates.

Semantic code search and navigation using the cix index. Reach for cix when you don't already know where to look. Covers search, definitions, references, symbols, files,…

Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; outputs a structured model with clarifications. Not…

Review existing test cases (legacy, others', AI) for coverage and executability: build a testable-points baseline, assess independently, revise in place with records. No…

Write manual test cases (markmap) from docs, bugs or code — code-first: review code for bugs first; extracts machine-readable schema. Not for: requirement-analysis / tes…

\"How should this be tested?\" Evidence-backed risk map → scope and depth across functional domains and 10 testing-type axes; includes carry signals, excludes reasons. N…

当用户希望启动另一个独立的 Claude Code 实例来分析、审查、讨论或提供第二意见时，使用此 skill。典型表达：'再开一个 claude 看看''用另一个 claude 审查一下''让 claude 给个第二意见''起一个新 claude 分析这个问题'。此 skill 通过 `claude -p` 启动一个独立的 Claud…

当用户在自然语言中提到 codex，并希望它分析、讨论、复核或给方案时，立即使用此 skill。典型表达包括：'和 codex 讨论一下''让 codex 看看''问问 codex''用 codex 给个第二意见''多和 codex 讨论几轮'。此 skill 负责调用 Codex CLI 获取另一模型的独立意见。若用户只是询问 cod…

WHEN deciding whether a PR, branch, diff, or current code satisfies an authoritative issue, specification, or decision contract; NOT for reconstructing meetings, tracing…

WHEN a pushed branch or open PR must reach green CI without the user watching, or WHEN you are about to hand-write a CI poller, watcher, or re-run loop to escort one pus…

WHEN an iOS app fails in the simulator — a build failure, a crash, a wrong screenshot, or wrong behaviour — and either the user reports it or you observe it yourself; NO…

WHEN rendering pseudocode of how code composes—module boundaries, types, signatures, arguments, and execution flow—for code that exists or a change about to be built; NO…

WHEN writing, running, or diagnosing Swift Testing suites, including migrating XCTest tests to them and a crashing or non-reporting test target under xcodebuild; NOT for…