SHAFT_ENGINE

Use when analyzing SHAFT Allure results, Doctor reports, trace evidence, healer output, flaky locator/wait/assertion failures, retries, or test-fix recommendations.

Use when creating, reviewing, refactoring, repairing, or generating SHAFT web/mobile locators, smart locators, ARIA locators, XPath/CSS replacements, or codegen element identifiers.

Use when recording browser, Playwright, mobile, Appium Inspector, or user-performed flows into SHAFT tests with MCP Capture, replay, code blocks, or codegen insertion.

Use when reviewing, previewing, applying, guardrail-checking, or verifying generated SHAFT Java before or after inserting it into a repository, especially the coding-partner diff/apply/verify loop from IntelliJ.

Use when writing, reviewing, or repairing SHAFT Java tests, page objects, API tests, mobile tests, CLI/DB tests, assertions, waits, or TestNG/JUnit/Cucumber scenarios.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Ten distilled expert domains for working on SHAFT_ENGINE (Java test-automation framework). Load the ONE matching chapter from references/ before deep work on: Selenium/WebDriver BiDi or the recorder (selenium-bidi), Allure report internals (allure-internals), Appium/mobile toolchains (appium-mobile), Maven Central release engineering (maven-release), TestNG/JUnit listeners and forked-JVM properties (testng-lifecycle), IntelliJ Platform plugin dev (intellij-plugin), MCP protocol engineering (mcp-protocol), GitHub Actions CI forensics (ci-forensics), flaky-test stabilization and wait strategies (wait-strategies), or locator design and self-healing (locator-healing). Read only the chapter you need; each is self-contained and grounded in real SHAFT incidents.

Use when implementing any feature or bugfix, before writing implementation code

Think, plan, verify, and communicate the way Claude Fable 5 did. Use this skill at the start of ANY nontrivial engineering task — debugging, planning a feature, investigating a failure, reviewing code, or any multi-step work where judgment matters more than typing speed. Also use it whenever the user says "act as fable", "think like fable", "channel fable", "what would fable do", or asks for more careful, evidence-driven work. It encodes a complete working methodology: evidence over inference, hypothesis-driven debugging, risk-first planning, empirical verification, and outcome-first communication. If in doubt whether a task is "nontrivial enough", it is — load the skill.

Use for failed GitHub Actions, failed-run Allure reports, or provider E2E failures; find the first actionable cause.

Use for shaft-mcp manifests, fixtures, installers, Dockerfiles, tool schemas, startup, or transport behavior.

Use when auditing shaft-mcp tool manifests, client fixtures, installers, containers, startup, or local transport contracts.

Use when planning or producing SHAFT ads needing scripts, scenes, demo capture, reports, captions, music, code visuals, edits, or reusable assets.

Use for SHAFT PDCA, Kevin/Bob/Bruce roles, or refinement loops.

Map SHAFT_ENGINE before broad search.

Map SHAFT_ENGINE before broad search.

Use for SHAFT UI design/review/validation across tools, reports, plugin UI, or public guide; include UX and evidence rules.

Use for AGENTS.md, CLAUDE.md, .agents, .github skills/instructions, .codex, or .memory guidance changes.

Use for SHAFT PDCA, Kevin/Bob/Bruce roles, or refinement loops.

Use for SHAFT Allure/Extent reports, artifacts, summaries, upload actions, failure extraction, or report paths.

Use for intermittent, retry-only, parallel-only, or environment-sensitive SHAFT tests; fix causes without weakening assertions.

Use for SHAFT src/main Java edits/reviews; apply public API, properties, logging, Allure, concurrency, and WebDriver rules.

Use for SHAFT src/test Java edits/reviews; apply lifecycle, isolation, Allure, browser, mocking, and regression rules.

Use for SHAFT module wiring, POMs, BOM, legacy coordinates, examples, or consumer fixtures.

Use for public SHAFT API/config/behavior, README/release text, or docs routing sync.

Use for SHAFT releases, version alignment, dependency/plugin updates, or Maven Central safeguards; never deploy locally.

Use for SHAFT ad strategy, scripts, scenes, demo capture, captions, music, code visuals, edits, or reusable assets.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.

UI/UX design intelligence with searchable database

Use for SHAFT UI design, redesign, optimization, review, visual QA, UX copy, accessibility, responsive behavior, reports, core tools, and public guide work.

Use when auditing SHAFT agent guidance, host adapters, skill bridges, guidance budgets, Codex config, or Memory setup.

Use when operating SHAFT report generation, Allure/Extent artifacts, CI summaries, upload actions, or failure extraction.

Use when auditing Maven module boundaries, BOM wiring, legacy coordinates, bundled examples, or clean consumer fixtures.

Use when planning or verifying user-guide updates for public SHAFT behavior, docs links, release text, or API/config changes.

Use when preparing or reviewing a SHAFT release, dependency updates, static versions, or Maven Central safeguards.

Investigate GitHub Actions and SHAFT Allure failures from a run, PR, or job; separate code defects from infrastructure and provider failures.

Diagnose and stabilize intermittent SHAFT tests, especially TestNG parallelism, shared state, files, drivers, timing, and external dependencies.