agentleFS
Sign inStart free
GustavoAlecioGustavoAlecio/claude-setup/skills/ado-close/SKILL.md

ado-close

Skill0 starsChanged 27 days agoMITView on GitHub

Fecha (move para estado final) um work item do Azure DevOps. Pede confirmacao antes. Usa o MCP azure-devops.

The file

Create a free account to mount
Files
SKILL.md

Move um work item para estado final (Done / Closed / Resolved, dependendo do tipo).

Defaults

  • Org / Project: os do tracker da org do repo (orgs[].tracker no .dashboard.json, configurado no app; python3 ~/.claude/bin/tracker.py resolve). Passe-os às tools do MCP.

Argumentos: primeiro numerico = ID. --state=<estado> opcional. --comment="..." opcional (deixa coment no card antes de fechar).

Passos

  1. Validar entrada. Sem ID → pergunte e pare.
  2. Buscar o work item para entender tipo (Bug / User Story / Task / etc) e estado atual via MCP.
  3. Decidir estado destino:
    • Se --state= foi passado, use.
    • Senao, baseado no tipo: Bug → Resolved, Task/User Story → Closed ou Done (dependendo do template do projeto).
    • Se nao tiver certeza do estado valido, liste os estados validos consultando o MCP (work item type states) e pergunte.
  4. Confirmar antes de aplicar (gate humano obrigatorio — esta acao e visivel para o time):
    • Mostre: Vai mover #<id> ("<titulo>") de <estado-atual> para <estado-destino>.
    • Se houver --comment, mostre o comentario.
    • Pergunte: "Confirmar? (s/N)".
  5. Executar:
    • Se --comment, postar coment primeiro via MCP add-comment.
    • Atualizar System.State via MCP update work item.
  6. Confirmar sucesso com a URL do work item.

Notas

  • Nunca feche em massa. Esta skill opera em um item por vez.
  • Se o item ja estiver no estado destino, avise e nao faca nada.
  • Erros do MCP (estado invalido no fluxo, regra de campo obrigatorio) — mostre cru e sugira fix.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free