通过命令行向OmniRoute的A2A服务器发送任务,查看执行历史和日志,监控或取消任务,并交互测试智能体之间的通信。
- 检查服务器状态和可用技能
- 使用JSON输入调用技能
- 查看任务执行历史和日志
Prepare selected pull requests for maintainer review by comparing failures with their current base, fixing authorized defects, and preserving contributor credit. Report complete or partial validation with evidence and outstanding checks before any separately authorized merge.
中文简介正在准备中。当前显示英语简介。
Inspect and prepare the selected PR queue against its exact current base, repair authorized defects with contributor credit, and report full versus partial validation. Use for maintainer pre-greening; merging requires separate owner authorization and the shared merge gates.
安装前可以查看交给 AI 代理的指令内容。
Read ../_shared/base-green.md and ../_shared/validation-gate.md first.
Read ../_shared/protected-surfaces.md before any instruction-surface change or merge.
The current candidate's workflows and versioned policy define required gates;
do not assume release PRs are fast-only or use a handwritten gate count.
Use the owner's PR list. Otherwise consume eligible merge-ready / fix-in-place
plans in _tasks/pipeline/prs/1-analyzed/; use the whole queue only when requested
or no pipeline items exist. Report drafts separately unless the owner included them.
Record current state, author, head SHA, base branch/SHA, freeze and worktree ownership.
An in-flight worktree belonging to another session means HOLD for that item.
Never work in the shared checkout, stash, or silently retarget a frozen release.
Inspect the exact base first. An incident is diagnostic history, not proof of inheritance. Match each failure signature against the exact base under comparable runtime and configuration. Repair confirmed base defects in a dedicated PR before using them to assess contributor changes. Base-red does not waive a required gate.
Use one isolated branch/worktree per PR. Before editing a contributor branch, verify the checked-out SHA equals its observed live head. Before pushing, verify the remote still equals the observed predecessor; a concurrent change means HOLD. Keep the original author's work and attribution, add appropriate co-authorship, and never overwrite or close the PR to take credit. A locked fork needs the owner-reviewed credit-preserving fallback, not a destructive reconstruction.
Run a RED reproduction, implement the proven fix, then focused and affected suites. Dependencies must match the candidate lockfile/toolchain; borrowed tools are diagnostic only. A build needs physical dependencies, not an external symlink. Preserve raw logs, exits, artifacts, test discovery and all existing assertions.
Fast checks may prioritize work, but cannot grant merge readiness. Full acceptance
covers every applicable required lane, including both test runners, coverage,
security and build/package/boot where required. DRIFT is a diagnosis, not PASS;
do not increase baselines, lower thresholds or accept flaky required checks.
Fork action_required is a trust/approval HOLD, never a code failure or automatic
approval instruction. Re-running an old run does not move its recorded candidate.
Do not claim/move pipeline plans on behalf of the merge executor. Record a
structured receipt containing base SHA, head SHA, candidate SHA/tree, policy/profile,
run IDs/attempts, artifact references, validation level and timestamp. A legacy
pre_greened head-only stamp or fast-gates-only note is partial evidence only.
Any relevant identity/policy change invalidates admission and requires revalidation.
Report each PR's causal classification, repairs, exact evidence and remaining lanes.
Separate PASS, PARTIAL, BASE-RED, PR-RED, INFRA-RED and ACTION_REQUIRED/HOLD.
This skill prepares the queue and never closes PRs. If the owner explicitly asks
to merge identified items, first follow the complete ../_shared/merge-gates.md
protocol, including protected-surface and per-group authorization. Do not bypass
required checks because the same failure affects many PRs.
Preserve work until its commits and evidence are safely retained. Teardown only
owned, clean, fully backed-up worktrees under ../_shared/worktree-teardown.md.
Do not delete contributor remote branches or another session's work.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
通过命令行向OmniRoute的A2A服务器发送任务,查看执行历史和日志,监控或取消任务,并交互测试智能体之间的通信。
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
中文简介正在准备中。当前显示原文说明。
Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.
中文简介正在准备中。当前显示英语简介。
Send prompts to LLMs from a terminal, display answers as they arrive, or hold an ongoing conversation. Use files or standard input for prompts, choose models, and set system instructions through OmniRoute.
中文简介正在准备中。当前显示英语简介。
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
中文简介正在准备中。当前显示英语简介。
Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.
中文简介正在准备中。当前显示英语简介。