Explorar skills

Architecture planning workflow for establishing code structure, patterns, and principles before any code is written. Runs after brainstorm: and before new: on every project. Triggers on "architect:" prefix, "plan the architecture", "architect this", "how should we structure this", "what patterns should we use". Always runs on every project — no exceptions, no shortcuts. Reads BRIEF.md stack decisi

Esta skill Humanizer de italiano torna o texto natural e não gerado por IA, utilizando diversos recursos estilísticos. Diferente de um simples busca e substitui, ela também garante que o texto seja correto, claro e eficaz.

Refresh the file counts in .qualflare/test-state.md by re-globbing each framework row. Updates File count values and the Generated at timestamp in-place. Does not re-detect frameworks or change any other content. Use when the user runs /qf-update, asks to "refresh test counts", or after adding new test files without wanting to re-run full /qf-init.

综合软件测试技能，涵盖单元测试、集成测试、TDD/BDD、Mock 策略和跨多种语言的测试自动化。使用此技能编写测试用例、设计测试策略、实现测试自动化，或需要测试框架和最佳实践指导时使用。适合通过综合测试方法确保代码质量。

Run an 8-step iterative pre-execution evaluation of a quantitative marketing research idea targeting the Marketing Science / JMR / JCR / Management Science (Marketing) quality bar. Use whenever the user wants to "evaluate a research idea", "score this idea", "is this idea publishable in MKSCI/JMR/JCR/MS", "pivot my idea", "stress-test my project", "find threats to my idea", or pastes a research-qu

Prefer Text over String for text data, and use ByteString for binary or non-Unicode data. Use when writing or reviewing Haskell code that handles strings, text, or byte data.

Testes e CI/CD para bioinformática, abordando padrões pytest, fixtures, fluxos de trabalho do GitHub Actions e estratégias de teste específicas para a área.

Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly - called by cookoff/omakase-off.

Maintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md. Supports five source types: verifier (qualitative), tester (qualitative), orchestrator (numeric), planner (qualitative), survey (mixed). Handles both numeric results (eval scores, KEEP/DISCARD, delta) and qualitative results (PASS/FAIL/PARTIAL,

When testing Either values, compare the value directly with shouldBe instead of checking isLeft, so test failures show the actual value. Use when writing or reviewing Haskell test code that asserts on Either or similar values.

Full spec-driven workflow for adding a feature to an existing codebase with an AI coding agent. Triggers on "feature:" prefix, "I want to add a feature", "add X to my project", "new feature", "build a feature for". Always use when adding functionality to an existing project — even without the exact prefix. Reads PLAN.md feature map before drafting — checks build order, dependencies, shared data. S

Generates complete handoff packages for every transition scenario in a vibe-* project. Five modes: client (project completion), milestone (phase sign-off), dev (new developer onboarding), internal (team handoff between BetaCraft developers), maintenance (handing to client's own dev team). Each mode produces markdown documents plus a single self-contained index.html portal — clean, light-mode, clie