autopilot
SolidUse this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, sub-threshold confidence). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277); implementation lives in scripts/lib/autopilot.mjs (Phase C-1 follow-up).
Install
Quality Score: 90/100
Skill Content
Details
- Author
- Kanevry
- Repository
- Kanevry/session-orchestrator
- Created
- 1 months ago
- Last Updated
- 2 days ago
- Language
- JavaScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
autopilot
Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.
autopilot
Consume a pre-built ticket list (split-plan.md under .simple-workflow/backlog/product_backlog/{parent-slug}/) and drive the per-ticket /scout -> /impl -> /ship pipeline in topological order with policy-based autonomous decision making at each gate. Use when: (1) the user explicitly invokes /autopilot with a parent-slug; (2) another skill chains to /autopilot via the Skill tool after /brief and /create-ticket have populated a split-plan; (3) a resumable autopilot-state.yaml exists and the user re-runs /autopilot to continue from the last checkpoint. Triggers on "autopilot", "run the autopilot", "/autopilot <slug>", "continue the autopilot run", "drive scout impl ship pipeline".
autopilot
Full autonomous execution from idea to working code
autopilot
Autonomous orchestrator that takes a goal, discovers available tools, decomposes into phases, maps phases to skills, executes, and monitors until the project is done. Use when user wants full autonomous execution of a complex goal.
session-plan
Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into configurable waves (default 5) with optimal agent assignment, dependency ordering, and inter-wave checkpoints. Activated by session-start after Q&A phase completes.