Run a team workflow in one process without interactive questions, such as in CI or on a cloud agent. Provide inputs before starting, resume stopped runs, and report the outcome, failed step, and any opened pull requests.
Run a team workflow unattended with the local driver. Use in CI or a cloud agent, when a describe reply routed the run to the local driver, or to continue a run on this machine without a coding session.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
The local driver runs a whole run in one process on this machine: each command step as a process, each prompt step through a headless tool. Nobody is asked anything while it runs, so every answer the run needs is decided before it starts.
teamai workflow start --describe <name> --driver skill answered ask.kind: local: a coding session cannot run some step, and ask.reason says which.teamai workflow start <name> --describe and read the inputs it lists.teamai workflow start <name> --driver local, with the inputs as one JSON object in --inputs. teamai workflow start --help lists the other options, such as answering optional approvals and picking the prompt tool.teamai workflow resume <run>.The command exits when the run ends: 0 when it succeeded, 1 when it failed or was cancelled. Done when it has exited and the outcome, the failing step's message and the pull requests the run opened are reported where the person reads them: the job log, or your reply.
Without a terminal, nobody answers a gate during the run:
hitl_required, and so does the run.--auto-approve, or the member's workflows.auto_approve, an optional approval is answered yes and a choice takes its default.hitl_required.A coding agent's session may start or continue only a workflow whose invoke allows it, with start or resume. invoke: allow goes on. invoke: ask goes on once the person agreed, with --confirmed, and never in an unattended run (CI or a cloud agent), where it answers unattended_denied. invoke: deny, the default, answers invoke_denied. Tell the person the message, which names the command for their own terminal.
Inside a workflow step, every teamai workflow command that changes a run answers nested_workflow. Do the step's own work there instead.
A step gets the team env keys its requires.env lists, and no other team key. A key with no value on this machine fails the step missing_env before it runs; the message offers teamai env set only for a key the team declares, and otherwise the environment, or teamai env add KEY --secret to declare it. A CI job exports each secret under its key name instead. TeamAI masks the value of every key in env/secrets.yaml in run files and output.
When you set up a CI job that starts a run, or one that takes the runs members offer, read references/ci.md.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Manage shared team skills, rules, and documents through TeamAI. This skill guides syncing, publishing, checking differences, and diagnosing configuration problems, while directing setup and knowledge-sharing requests to the appropriate workflows.
Set up TeamAI for a new team or join an existing one. The skill guides installation checks, shared resource management, member and role administration, and removal, with diagnostic checks to verify setup.
Turn an AI coding session into a concise team learning document. Summarize the problem, decisions, solution, useful tools, and pitfalls, then publish the Markdown document to the team knowledge base through TeamAI.
Access TeamAI workflows for sharing skills, rules, documents, and environment settings across AI coding tools. This entry skill loads version-matched guidance for team setup, synchronization, codebase knowledge, and sharing lessons from a session.
Turn a large codebase spanning multiple repositories or services into a structured knowledge base. It documents architecture, business rules, and dependencies, links conclusions to source lines, labels confidence in relationships, and supports incremental updates.
Coordinate a team workflow from an agent session. Start a named workflow, route each step to the right command or agent, relay status and required choices, and continue until the run finishes or hands control to a person.