orbit-setup
/orbit-setup
Sets up and maintains Orbit on a user's machine and repositories according to their needs. Use for installation, `orbit workspace init`, onboarding, provider/crew and MCP configuration, the Linux sandbox, the headless browser kit for UI checks, the scheduler (sweep clock, routines, auto-tasks), worktree GC, `orbit doctor`, upgrades, task publication and backup, remote access, the dashboard, or host and service log troubleshooting. Supports existing installations as well as first-time setup; task execution belongs to orbit and backlog dispatch to orbit-orchestrate.
- Author
- constellation-works ↗
- Repository
- orbit ↗
- Licence
- MIT
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 17
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Sets up and maintains Orbit on a user's machine and repositories according to their needs. Use for installation, `orbit workspace init`, onboarding, provider/crew and MCP configuration, the Linux sandbox, the headless browser kit for UI checks, the scheduler (sweep clock, routines, auto-tasks), worktree GC, `orbit doctor`, upgrades, task publication and backup, remote access, the dashboard, or host and service log troubleshooting. Supports existing installations as well as first-time setup; task execution belongs to orbit and backlog dispatch to orbit-orchestrate.
Original author description
Sets up and maintains Orbit on a user's machine and repositories according to their needs. Use for installation, `orbit workspace init`, onboarding, provider/crew and MCP configuration, the Linux sandbox, the headless browser kit for UI checks, the scheduler (sweep clock, routines, auto-tasks), worktree GC, `orbit doctor`, upgrades, task publication and backup, remote access, the dashboard, or host and service log troubleshooting. Supports existing installations as well as first-time setup; task execution belongs to orbit and backlog dispatch to orbit-orchestrate.
How it works
- Establish the target
- Apply and verify
- Preserve existing work
SKILL.md preview
--- name: orbit-setup description: Sets up and maintains Orbit on a user's machine and repositories according to their needs. Use for installation, `orbit workspace init`, onboarding, provider/crew and MCP configuration, the Linux sandbox, the headless browser kit for UI checks, the scheduler (sweep clock, routines, auto-tasks), worktree GC, `orbit doctor`, upgrades, task publication and backup, remote access, the dashboard, or host and service log troubleshooting. Supports existing installations as well as first-time setup; task execution belongs to orbit and backlog dispatch to orbit-orchestrate. --- # Orbit Setup Help the user reach the workflow they want with the smallest necessary setup. Inspect what is already working before proposing changes. Choose a path below; loading this skill is not a request to install every optional component. ## Establish the target Use the request and local evidence to establish the machine/OS, repository, existing Orbit executable/version, and desired use: task tracking, agent-assisted work, unattended delivery, or remote access. Ask only for choices that cannot be inferred, such as the integration branch, provider, or which host owns a shared workspace. Preserve the user's installation method and existing config. | User need | Reference | |---|---| | First installation or another repository | [First run](references/first-run.md); for an agent lane, continue with [Provider setup](references/providers.md#provider-setup) | | Add a Copilot, Antigravity or Muse crew; fix provider authentication | [Configuration — Provider setup](references/providers.md#provider-setup) | | Explain crew selection, provider aliases or a dispatch refusal | [Configuration — Provider identity and resolution](references/providers.md#provider-identity-and-resolution) | | Configure task-pilot explore briefs, choose tasks by tag, or verify whether a brief was stored and delivered | [Configuration — Explore briefs](references/configuration.md#explore-briefs) | | Experiments: `[experiments]` settings, approved config overlays, operator lifecycle, shadow/live modes and readouts | [Configuration — Experiments](references/configuration.md#experiments) | | Host capability labels: set `machine.labels`, understand the implicit OS label and `requires_labels` matching, or inspect placement waits | [Host capability labels](references/configuration.md#host-capability-labels) | | Path leases: enabling or tuning `lease.*`, advisory versus hard coordination, or verifying a lease or a refused hard request | [Configuration — Path-lease policy](references/configuration.md#path-lease-policy) | | Landed-delivery line classes (Analytics › Metrics › Lines changed): `workflow.test_paths`, `workflow.non_code_paths`, their defaults and verification; backfilling missing history with `migrate --backfill-diff-stats` | [Configuration — Landed diff classification](references/configuration.md#landed-diff-classification) | | Tune a repository's workspace policy from evidence: required validation and baseline commands, footprint locks and generated files, task types, type and complexity crew pools, purpose pools, crew selection and performance draws, review layers | [Workspace tuning](references/workspace-tuning.md) | | Crews, policies, workspace settings, executor definitions (host OS support, auth probes, inspection tools, shared Cargo-cache grants), generated-file conflict recovery, prose-only validation, executor admission order, host pressure, stalled providers, command timeouts, per-tag instruction files, review-skip tag mappings, review-finding verification and owed host evidence | [Configuration](references/configuration.md#review-finding-verification-and-owed-host-evidence) | | Linux execution prerequisites or sandbox failure | [Linux sandbox](references/linux-sandbox.md) | | Windows host (Orbit runs inside WSL2) | [Windows through WSL2](references/windows-wsl2.md) | | macOS: Claude worker token and the clock env file | [macOS](references/macos.md) | | Headless browser kit (`orbit browser-kit`) so workers can render and screenshot UI changes | [Browser kit](references/browser-checks.md) | | Scheduled execution | [Automation](references/automation.md) | | Recurring QA and other task templates | [Auto-tasks](references/auto-tasks.md) | | MCP clients, SSH federation, remote dashboard or the lease listener user and its tokens | [Remote access](references/remote-access.md) | | Dashboard browser sessions: enabling `machine.web_terminal.enabled` or setting `machine.web_session.ttl`, one-time URLs from `orbit web open`, or checking whether the running dashboard serves `/api/session` (not the headless browser kit) | [Remote access — Browser sessions](references/remote-access.md#browser-sessions) | | Installing plugins, their `orbit <ns>` commands and dashboard panels, the `.orbit/plugins.yaml` pin file, and decision channels for plugin answer submission | [Plugins](references/plugins.md#decision-channels) | | Owner/replica roles and multiple machines | [Multi-host](references/multi-host.md) | | Single-owner distributed drain setup or claimed-attempt recovery | [Distributed drain](../orbit/references/setup/distributed-drain.md) | | Task snapshots, backup and restore | [Publication](references/publication.md) | | Upgrade, resource sync, doctor, worktree GC, workspace removal or teardown, or source-remote rebinding | [Maintenance](references/maintenance.md#removing-or-re-targeting-a-workspace) | | Scheduler/service logs and host incidents | [Operational logs](references/operational-logs.md) | Task tracking alone does not require a provider, PR credentials, a scheduler or remote hosts. Add those only for the requested workflow. Agent execution needs an authenticated supported provider and working sandbox; PR delivery also needs its Git/PR credentials. Task search uses local SQLite FTS5 and requires no download. ## Apply and verify 1. Inspect installed command help, effective config and relevant prerequisites. Use the owning host's registered tools for durable state; see the shared [tool surface](../orbit/references/tool-surface.md) for authority and routing. 2. Make the authorized configuration changes. Existing approval carries forward; do not ask again for routine steps already covered. New scheduling, downloads, remote roles or credentials are separate choices when the request omits them. Keep secrets out of task records and examples. 3. Verify the requested workflow through its actual client and destination. A version string is not proof of a working MCP connection; discover the intended workspace and exercise an audited operation. Use disposable fixtures for execution checks unless running real work is authorized. 4. Report what changed, what works, and any specific remaining operator action. Distinguish installed, configured and enabled. Return to [orbit](../orbit/SKILL.md) for task work or [orbit-orchestrate](../orbit-orchestrate/SKILL.md) for authorized dispatch. ## Preserve existing work An upgrade must preserve running-client compatibility or refuse before changing live state. Check long-lived MCP and service processes, not only active jobs. Never delete admission/identity files, bypass schema guards, or start a shadow store to recover access. Follow [maintenance](references/maintenance.md). Seeded schedules are disabled until deliberately enabled (except `crew-performance-refresh`, which is seeded enabled and no-ops while `workflow.crew_performance` is `off`); preserve existing schedule and enablement choices on an established host. Shared repositories need an explicit owner; copying a checkout does not migrate its control plane.
Files in this package (17)
- SKILL.md 8 KB
- references/auto-tasks.md 49 KB
- references/automation.md 32 KB
- references/browser-checks.md 8 KB
- references/configuration.md 72 KB
- references/first-run.md 12 KB
- references/linux-sandbox.md 3 KB
- references/macos.md 5 KB
- references/maintenance.md 34 KB
- references/multi-host.md 7 KB
- references/operational-logs.md 19 KB
- references/plugins.md 46 KB
- references/providers.md 8 KB
- references/publication.md 15 KB
- references/remote-access.md 30 KB
- references/windows-wsl2.md 5 KB
- references/workspace-tuning.md 21 KB
Versions
The database has no other skills named orbit-setup.
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version 1aef2c08e156 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90orbit
Creates, executes and reviews Orbit tasks; searches task history and friction records; records evidence. Use for an assigned task or task ID, task authoring, `orbit.task`/`orbit.search` MCP tools, `orbit tool run`, task records under `.orbit/`, or friction. Use orbit-orchestrate… - 100orbit-orchestrate
Prepares and supervises an Orbit backlog. Deduplicates and pilots tasks (task-pilot), assigns crews, promotes ready work, dispatches with `orbit run ship` and `orbit run auto` drains, diagnoses failed or stuck `jrun-*` runs, and routes CI/QA sweep findings into repair tasks. Use… - 100orbit-audio
使用 ORBIT 的命令行或本地 HTTP API 制作、编辑和验证双耳空间音频,支持分轨、声音对象、节点、关键帧及工程导出。用于用户要求通过 ORBIT 处理音频,不用于 ORBIT 软件开发或官网部署。 - 100glab-orbit
Run the managed Orbit CLI through glab for remote graph queries and local code-graph workflows. Use when installing or updating Orbit, checking graph status, querying a remote Orbit graph, indexing or searching a local code graph, forwarding Orbit help, or troubleshooting… - 100orbit-task
Work a bug or feature task from an Orbit task board end to end, one agent per task - read the card, branch, fix, test, open a PR, finish and close - with a stop for the owner at every step that others will see. Uses the Orbit MCP for the card, comments, questions and alerts. Use… - 100orbit-bench
Integrate a benchmark into Orbit and size its tasks — write an adapter executable for a benchmark Orbit does not know (any format, no Orbit rebuild), write or update its resources.json (GPU / memory / CPU / timeout per task), and validate it. Use when asked to make a benchmark…