orchestration-pilot
Evaluate the natural-work Codex orchestration pilot from comparable historical and candidate development-run records. Use for the five-day or five-run checkpoint and weekly Development Steward evidence.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- orchestration-pilot
- description
- Evaluate the natural-work Codex orchestration pilot from comparable historical and candidate development-run records. Use for the five-day or five-run checkpoint and weekly Development Steward evidence.
02 资源文件 1
- 参考文档agents/openai.yaml227 B
03 SKILL.md 正文
Orchestration Pilot
Evaluate already-collected development-run records with the deterministic orchestrator-pilot interface. Include direct and sequential runs as well as multi-agent runs; a correct zero-agent choice is evidence.
The first checkpoint occurs after five non-trivial candidate runs or five calendar days. Compare comparable historical work instead of rerunning the same product task. Retain only when verified outcomes do not regress and waits, open lanes, or corrections improve without another coordination signal regressing. Otherwise collect more evidence or adjust the policy.
Return at most one first action per repository for Check-in. Keep the operation read-only. It never edits agent configuration, repositories, Linear, schedules, releases, or production.
04 同仓库更多 Skills
working-backwards
Define a software feature through PRFAQ and staged documents when the user requests working backwards before coding.
flow-implement
Implement a requested software change through verification, corrections, and its authorized delivery endpoint.
development-steward
Run the scheduled, read-only weekly maintenance review for the six explicitly opted-in repositories and prepare one concise private report for Check-in.
grill-with-docs
Run one recoverable interview for functional, visual, or mixed software grills; reuse equivalent answers and offer the shared HTML questionnaire.
global-agent-guardrails
Install, audit, test, or update the Development System's global destructive-command guard for Codex, Claude Code and T3 Code. Use when configuring agent safety hooks or investigating whether dangerous shell operations are blocked.
impeccable
Design or refine frontend UI using project context and a focused design playbook; also handles visual critique and polish.