Desenvolvimento

Review execution approach for feasibility, architecture, data flow, edge cases, test coverage, performance, and security risks. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) for technical feasibility before any scaffolding; milestone-mode reviews slice-plans (M###-S##-PLAN.md) before plan-task. Use concept-mode optionally after plan-ceo-review to sanity-check the pitched approa

O framework de ensino Agentic Control Stack explica os princípios de design de sistemas de codificação agentic sob a ótica da teoria de controle. Ele abrange uma arquitetura de cinco camadas, patologias de loop, fundamentos MAPE-K e inclui uma implementação completa do sd0x-dev-flow.

🦆 rubber duck debugging, but the duck has opinions. and memory.

Publishing the yoke plugin: quality checks, documentation validation, version bump, tag, push, GitHub release. Used when the user writes "release", "publish", "ship version", "make a release", "prepare a release", "new version".

Export Claude Hangar skills and rules to other AI coding tool formats. Use when: "export rules", "cursor rules", "windsurf rules", "export-rules", "convert to mdc".

Full-view project dashboard. Shows plugin version and update status, sprint health, story pipeline, quality summary, memory health, and analysis progress. Read-only.

Debug systematically when tests, builds, or runtime/browser checks fail — deterministic feedback loop, reproduce, 3-5 ranked hypotheses, instrument, fix root cause, regression-test. Use when the user says "debug this", "why is it failing", "it broke", "the build is red", "the tests fail". Not for code review or flaky tests (fix the flake first).

Use when preparing a codebase for public/open-source release, reviewing a repo for openness, or auditing for secrets and missing documentation before making code public. Triggers on "open source", "public release", "prepare repo", "openness", "repo review", "make public", "open-source prep".

Habilidade Claude Code: Adiciona 1 ou 500 logotipos de marcas a qualquer registro, com um fallback de 3 níveis que nunca falha. É agnóstica a agentes.

Run verification commands and confirm output before claiming work is complete. Evidence before assertions. Thin ytstack wrapper around the vendored superpowers verification-before-completion procedure, injecting the current task's verification command. Use before commit, before PR, before summarize-task, before any 'done' claim.

Deploy and manage applications on VPS servers with Dokploy. Use when the user wants to: set up a new VPS server, deploy a project from GitHub, manage domains/DNS, create databases, check server status, view logs, or remove deployed projects. Also use when the user mentions re-deploying, checking deploy status, adding environment variables, or troubleshooting a deployed app. Also triggers when user

Orchestrate a parallel multi-agent build with mandatory cross-review across Claude and Codex. Splits a multi-component coding task into ~equal Claude and Codex subtasks, runs them in parallel in isolated git worktrees, then has the OPPOSITE model review each diff before consolidation. Use for multi-file features, refactors with parallel slices, batch fixes, or audit-and-fix passes — bail to a sing