Aprenda uma tarefa de cada vez
Guias curtos baseados em gravações reais do CLI do SpecWeave e do SpecWithCode. Cada um nomeia o resultado, mostra o vídeo com capítulos, lista os passos e traz a transcrição.
19 guias2 trilhas de aprendizadoVer todos os guias
Trilhas de aprendizado
Siga uma trilha do primeiro passo até um resultado pronto. Cada passo é um guia próprio; uma trilha aparece aqui quando tem pelo menos dois.
Run work across agents
SpecWeave CLI · 5 guias · 6:58
Plan an increment, prove each task, hand off between tools and get a review from another model.
Run SpecWithCode
SpecWithCode · 12 guias · 17:53
Understand the setup, run a project through its coordinator, then add plans, memory and a second provider.
Mais um guia está planejado para este caminho.
2:53Passo 1: See how SpecWithCode runs your agents
1:48Passo 2: Start SpecWithCode with a coordinator and two workers
1:29Passo 3: Run a project with a coordinator and workers
1:35Passo 4: Plan, verify and schedule project work
1:06Passo 5: Keep project memory and read honest usage
1:01Passo 6: Continue a thread on Codex at a usage limit
1:39Passo 7: Keep working when a provider runs out
1:13Passo 8: Add a second machine
1:26Passo 9: Join a new Mac to your main machine
1:19Passo 10: Finish a thread with a pull request and auto-merge
1:10Passo 11: Let agents use a browser
1:09Passo 12: One Chrome extension for every agent
Todos os guias
19 guias
1:00Plan, prove and hand off a task with the CLI
You see the whole loop once: the plan, the claim, the test evidence and the handoff all travel with the repository.
SpecWeave CLIAny agentNarrado
1:36Install SpecWeave and plan your first increment
You end with an increment whose spec.md lists numbered acceptance criteria and tasks with their files and test, and specweave pickup tells you which task to claim first.
SpecWeave CLIAny agentNarrado
1:30Claim, prove, verify and complete a task
You end with a completed increment that has its test evidence and a passing verify report.
SpecWeave CLIAny agentNarrado
1:18Claude Code handoff to Codex at a usage limit
You end with Codex running the next task from the ledger, and the ledger shows who handed off, who picked up and who finished.
SpecWeave CLIClaude Code and CodexNarrado
1:33Review with the other model before you ship
You end with a review report from a model of another family and a clean second run.
SpecWeave CLIClaude Code and CodexNarrado
2:53See how SpecWithCode runs your agents
You know how machines, subscriptions, usage limits, the coordinator and its threads fit together before you install.
SpecWithCodeClaude Code and CodexNarrado
1:48Start SpecWithCode with a coordinator and two workers
You end with a project whose coordinator has started two workers and returned a report.
SpecWithCodeCodexNarrado
1:39Keep working when a provider runs out
You end with a thread that continued on another provider under a rule you set for the project.
SpecWithCodeClaude Code and CodexNarrado
1:13Add a second machine
You end with your second machine listed as reachable and allowed to run workers.
SpecWithCodeCodexNarrado
1:26Join a new Mac to your main machine
You end with the new Mac listed under Your private machines on your main machine and allowed to run workers.
SpecWithCodeAny agentNarrado
1:19Finish a thread with a pull request and auto-merge
You end with a thread whose pull request merged automatically once its conflict was resolved and the required test check passed.
SpecWithCodeCodexNarrado
1:10Let agents use a browser
You end with an agent that checks a local page in a tab beside its thread, which you can watch, take over and screenshot.
SpecWithCodeCodexNarrado
1:09One Chrome extension for every agent
You end with one paired Chrome profile that every agent in SpecWithCode can use, in tabs of their own, and a Pause button that stops them all.
SpecWithCodeAny agentNarradoInterface antiga, adicionada em 19 October 2026
1:29Run a project with a coordinator and workers
You can tell the coordinator and worker models apart, follow the routing history, resolve and reopen a thread, and read token usage by model.
SpecWithCodeClaude Code and CodexNarradoInterface antiga, adicionada em 9 October 2026
1:35Plan, verify and schedule project work
You add a plan with one acceptance criterion, see a failed verification stay failed, record a passing attempt, and keep routines scoped to their project.
SpecWithCodeAny agentNarradoInterface antiga, adicionada em 9 October 2026
1:06Keep project memory and read honest usage
You keep a project goal, instructions and decisions in small memory files and read usage that comes only from recorded provider turns.
SpecWithCodeAny agentNarradoInterface antiga, adicionada em 9 October 2026
1:01Continue a thread on Codex at a usage limit
You see a coordinator split work between Codex and Claude, and a Claude thread at its limit continue on Codex with its context.
SpecWithCodeClaude Code and CodexNarradoInterface antiga, adicionada em 10 October 2026
1:21Set up a personal project with folders and tools
You create a personal project, add a folder and a repository, and grant a local MCP command exactly the tools it may use.
SpecWithCodeAny agentNarradoInterface antiga, adicionada em 9 October 2026
0:50Check what an agent actually did
You can find the recorded tool call, its exit code and the file change behind an agent’s answer.
SpecWithCodeAny agentNarradoInterface antiga, adicionada em 8 October 2026
Dos outros produtos
Os guias para encontrar, testar e publicar skills de agentes ficam em verified-skill.com. Tutoriais do Verified Skill
O que todo guia inclui
- Uma gravação realImagens do app em execução ou saída real de comandos, com projetos de exemplo. Cada guia diz qual versão mostra e quando foi adicionado; as gravações da versão atual vêm primeiro.
- Legendas, capítulos e transcriçãoUma faixa de legendas WebVTT, capítulos para os quais você pode pular pelo teclado e uma transcrição gerada a partir das legendas.
- Hospedado neste siteVídeos e pôsteres são carregados de spec-weave.com, sem player nem rastreamento de terceiros.