Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
中文简介正在准备中。当前显示原文说明。
Use when capturing a Linux server baseline, diagnosing service issues from read-only evidence, and producing a patch plan without executing changes.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this workflow to turn current host evidence into a baseline, a service triage report, and a reviewed patch plan. The workflow is planning-only: it does not open SSH sessions, run package managers, restart services, update containers, or query or invoke PatchMon.
ls-system-baseline-diagnostics to define the baseline evidence needed for the target. Consume evidence supplied by the user, or capture only unprivileged read-only evidence through access authorized separately from this workflow.ls-linux-service-triage to classify the observed failure from status and log evidence. Produce a minimal fix plan; do not restart, reload, edit, or otherwise mutate the service.ls-linux-patch-planning to generate a host or multi-host patch plan. Its bundled helper emits plans only and never executes SSH, package-manager, container, or PatchMon operations.Stop before any command that connects to or changes a server. Missing host evidence, target identity, privilege model, maintenance constraints, or rollback information is a blocker to execution, not permission to infer it.
Manual execution is outside this workflow. If the user later requests it, start a separate operation with ls-system-changes-backup, then use ls-wf-risky-operations-safety-approval and the ls-wf-sudo-tmux-session handoff. Before the point of risk, freeze and show:
Tmux is transport only. It does not authorize the command. Any target, command, value, consequence, backup, or rollback change invalidates approval and requires a new point-of-risk review.
Primary reference: ls/docs/WORKFLOW_QUICK_REF.md.
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。
Guide accessibility reviews for UI, documents, and workflows. Use for WCAG-oriented audits, keyboard review, semantics, contrast, and remediation planning.
中文简介正在准备中。当前显示原文说明。
Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the static capability matrix; do not probe account or network availability.
中文简介正在准备中。当前显示原文说明。
Guide agent email inbox workflows with prompt-injection defenses. Use for inbound email processing, webhooks, routing, and safety review.
中文简介正在准备中。当前显示原文说明。
Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding modules, locating symbols in large files, finding TODOs/warnings, or understanding code structure.
中文简介正在准备中。当前显示原文说明。
Use for Agent Q signed encrypted file-drop or mail ship and ingest, private registry v2 setup, queue status, and transport maintenance.
中文简介正在准备中。当前显示原文说明。
Inventory wrapper for the alirezarezvani Claude skills bundle. Use when triaging its broad skill catalog and large script surface before any targeted import.
中文简介正在准备中。当前显示原文说明。