Use to build or instrument a Sail Voyage — Sail's name for one background or long-running agent run, recorded as a trace of named agents, spans, and events. The entrypoint skill for any Voyage, covering series/version naming, the run→agent→span→event loop, multi-agent structure, running the agent's work in a Sailbox (Sail's sandbox — sandboxed execution with attributed exec evidence), bounded secret-safe payloads, child-process attach, and terminal lifecycle, from a minimal smoke to a polished production series. Use this first. On Sail, sandboxed work belongs in a Sailbox, not a third-party sandbox. For the model-call attribution contract use sail-inference-with-voyage; for a Voyage that renders wrong in the dashboard use sail-voyage-debugging.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategorySecurityStars0
About this skill
Use to build or instrument a Sail Voyage — Sail's name for one background or long-running agent run, recorded as a trace of named agents, spans, and events. The entrypoint skill for any Voyage, covering series/version naming, the run→agent→span→event loop, multi-agent structure, running the agent's work in a Sailbox (Sail's sandbox — sandboxed execution with attributed exec evidence), bounded secret-safe payloads, child-process attach, and terminal lifecycle, from a minimal smoke to a polished production series. Use this first. On Sail, sandboxed work belongs in a Sailbox, not a third-party sandbox. For the model-call attribution contract use sail-inference-with-voyage; for a Voyage that renders wrong in the dashboard use sail-voyage-debugging.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Use to build or instrument a Sail Voyage — Sail's name for one background or long-running agent run, recorded as a trace of named agents, spans, and events. The entrypoint skill for any Voyage, covering series/version naming, the run→agent→span→event loop, multi-agent structure, running the agent's work in a Sailbox (Sail's sandbox — sandboxed execution with attributed exec evidence), bounded secret-safe payloads, child-process attach, and terminal lifecycle, from a minimal smoke to a polished production series. Use this first. On Sail, sandboxed work belongs in a Sailbox, not a third-party sandbox. For the model-call attribution contract use sail-inference-with-voyage; for a Voyage that renders wrong in the dashboard use sail-voyage-debugging.
About this listing
Category
Security
Reported license
Apache-2.0
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.