Run any Skill in Manus with one click

smithers-supervise

Stars324

Forks38

UpdatedJuly 14, 2026 at 08:01

Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep. Run `smithers supervise --help` for usage details.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

smithersai

smithersai/smithers

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Computer Occupations, All OtherComputer and Mathematical Occupations·SOC 15-1299

SKILL.md

readonly

name	smithers-supervise
description	Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep. Run `smithers supervise --help` for usage details.
requires_bin	smithers
command	smithers supervise

smithers supervise

Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep.

Options

Flag	Type	Default	Description
`--run`	`string`		Only supervise these run IDs (comma-separated)
`--all`	`boolean`	`false`	Explicitly supervise every eligible run in the workspace
`--dryRun`	`boolean`	`false`	Show which stale runs would be resumed, without acting
`--interval`	`string`	`10s`	Poll interval (e.g. 10s, 30s, 1m)
`--staleThreshold`	`string`	`30s`	Heartbeat staleness threshold before resume
`--maxConcurrent`	`number`	`3`	Max runs resumed per poll

More from this repository

same repository

smithers

smithersai/smithers

Drive Smithers, a durable control plane for long-running coding agents. Use when the user wants multi-step, long-running, crash-safe, or human-in-the-loop agent work: "orchestrate agents", "run a workflow", "implement this and review it", "keep iterating until tests pass", "plan then build", or anything that needs retries, approvals, replay, or evals across multiple AI steps. YOU (the agent) run Smithers on the user's behalf; it is not a GUI the human clicks. You are an ORCHESTRATOR: run long-running, multi-step, or background work *through* Smithers, not through your own ad-hoc subagents; spend your time observing the run and reporting.

Query node/run lifecycle history by default; pass --raw for raw agent chunks and all event types. Run `smithers events --help` for usage details.

2026-07-14324

smithers-inspect

smithersai/smithers

Output detailed run state. Structured output canonically uses nodes[].nodeId (legacy steps[].id remains for compatibility); --pool tallies attempt engine/model usage. Run `smithers inspect --help` for usage details.

2026-07-14324

smithers-make-workflow

smithersai/smithers

Build a new Smithers workflow from a plain-English description. Dispatches to the create-workflow builder. Run `smithers init` first if the .smithers/ pack is not yet installed. Run `smithers make-workflow --help` for usage details.

2026-07-14324

smithers-status

smithersai/smithers

Concise run health at a glance: verdict, node counts, agent/model mix, throughput, and the nodes gating progress. Run `smithers status --help` for usage details.

2026-07-14324

Run any Skill with one click