Explorar skills

Guides root cause investigation before proposing fixes. Use when debugging, diagnosing failures, investigating test errors, or tracing unexpected behaviour.

Initialize Bulwark infrastructure in a project: language-aware Justfile (8 langs), bun + eval-framework toolchain, logs/ subdirectories, and optional hooks.

Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.

Auto-activate for Dockerfile, docker-compose.yml, railway.json, railway.toml, Procfile, cloudbuild.yaml, app.yaml, service.yaml, deploy.sh, systemd units, Kubernetes manifests, Terraform, or granian/litestar run in deployment context. Use when deploying Litestar apps to containers, Railway, Cloud Run, GKE, systemd, or CI/CD release targets. Not for non-Litestar Python apps or build artifact packag

Plan a new feature from concept to approved implementation plan. Activates Product Council for strategic evaluation, then Feature Council for technical planning. Produces a documented decision and scoped task breakdown. Use when starting any new feature work.

<!-- @include templates/prompts/iron-law.md --> 根据最近的 git 提交记录，更新指定服务或应用的 CHANGELOG.md。 运行 git log 查看最近的提交记录 按约定式提交分类：feat / fix / docs / chore / refactor / test 更新对应服务/应用的 CHANGELOG.md，使用…

End-to-end statistical proof loop. Use when the user asks to prove a statistical proposition, when a hypothesis is promoted to a theorem, or when the empirical trunk's reviewer demands a theorem-side gate. This SOP is suggestion-only (per ADR 0007); skip, loop, or interleave with empirical work as the situation calls for.

Um sistema de design de IA completo com mais de 190 estilos testados, geração de imagens por IA e exportação pixel-perfect. Ele cria conteúdo para redes sociais, PDFs e sites completos a partir de linguagem natural, incluindo integração de marca e um sistema de qualidade de autoavaliação.

End-to-end research loop. Use at the start of any new research task; triggers literature review, hypothesis generation, Elo selection, experimentation, and verification.

Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b], [project-c], Claude Code), requests investigations, or queries past lessons. Ret

Background knowledge about reverse WebFinger discovery — finding a WebFinger address from an ActivityPub actor — based on FEP-2c59 (DRAFT status). Covers the `webfinger` property on actors, the forward vs reverse discovery problem, why `preferredUsername` is insufficient for reverse lookups, domain mismatch use cases, validation requirements (no-redirect string comparison), security considerations

Gates completion claims with mandatory evidence — no "should work" or "probably passes" without fresh verification output. Use when verifying test results, confirming builds pass, checking linter output, or validating acceptance criteria.