Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/criptogus/Samba-Builder.Loading the repository README…
Showing 30 of 30 collected skills.
Conduz descoberta, priorização e direção de experiência com o jeito Samba: problema real, inovação útil, simplicidade e design marcante. Use para transformar uma ideia ou briefing em produto, definir a primeira versão ou revisar uma proposta; não reinicie a…
Source text: Portuguese
Estruturar briefing de cliente, perguntas e premissas para entregas ágeis e de altíssimo valor (10x mais rápido).
Source text: Portuguese
Converter briefing em plano contratual enxuto, priorizado para entrega 10x mais rápida.
Source text: Portuguese
Aplicar tokens confirmados e padrões de UI Samba aos projetos de clientes para 10x melhor UX e UI.
Source text: Portuguese
Implementar tarefas aprovadas com código 10x superior: limpo, robusto, performático e tipado.
Source text: Portuguese
Add one or more AI models to the language model constants file, researching specs from official docs.
Check GitHub Actions workflow runs from the past day, identify severe or consistent failures, and file an issue if actionable problems are found.
Map a minified error stack trace from a production Samba build back to original source locations using source maps.
Debug E2E tests by taking screenshots at key points to visually inspect application state.
Root-cause flaky or failing E2E tests from a specific CI run by downloading and analyzing the Playwright HTML report (traces, screenshots, errors). Use this when given a GitHub Actions run URL and asked to investigate failures. Diagnose from report artifacts…
Automatically gather flaky E2E tests from recent CI runs on the main branch and from recent PRs by wwwillchen/keppo-bot/samba-assistant, then deflake them.
Identify and fix flaky E2E tests by running them repeatedly and investigating failures.
Rebase E2E test snapshots based on failed tests from the PR comments.
Turn customer feedback (usually an email) into discrete GitHub issues. Checks for duplicates, proposes new issues for approval, creates them, and drafts a reply email.
Create a plan to fix a GitHub issue, then implement it locally.
Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are…
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.
Diagnose and fix failing CI checks on a pull request from its latest GitHub Actions CI run. Use when PR CI has E2E/Playwright failures, macOS or Windows unit-test failures, or presubmit/type/build failures; analyzes the exact run logs and artifacts, invokes…
Read all unresolved GitHub PR comments from trusted authors and address or resolve them appropriately.
Address all outstanding issues on a GitHub Pull Request by handling both review comments and failing CI checks.
Publish local work by committing changes, running checks, pushing the branch, and creating or refreshing a GitHub PR with a reviewer-useful description.
Rebase the current branch on the latest upstream changes, resolve conflicts, and push.
Record a visual demonstration of the key feature of this PR using screenshots and add it as a new comment to the PR.
Promote the latest pre-release to a stable release by creating a release branch, bumping the version, and pushing.
Team-based PR review using Claude Code swarm. Spawns three specialized teammates (correctness expert, code health expert, UX wizard) who review the PR diff, discuss findings with each other, and reach consensus on real issues. Posts a summary with merge…
Swarm planning session with PM, UX, and Engineering agents who debate an idea, ask clarifying questions, and produce a detailed spec written to plans/$plan-name.md.
Preparar código e evidências para outro time operar e manter a aplicação.
Source text: Portuguese
Comparar solicitações ao plano aprovado e registrar decisões de escopo.
Source text: Portuguese
Evitar credenciais no código, contexto público e evidências de entrega.
Source text: Portuguese
Revisar fronteiras de confiança, ameaças STRIDE e segurança dos fluxos aprovados.
Source text: Portuguese
Repository README source: README.md
Read the source README