ls-wf-server-triage-patch-planning
Use when capturing a Linux server baseline, diagnosing service issues from read-only evidence, and producing a patch plan without executing changes.
Install / Use
npx skills add CruxExperts/LocalSetup --skill ls-wf-server-triage-patch-planningInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of ls-wf-server-triage-patch-planning
ls-wf-server-triage-patch-planning scores 48/100 on our quality scale, 4274th of 4,595 Development & Engineering skills we index.
Its SKILL.md is 2.3 KB long, split into 3 sections and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-23. Automated pattern scan on 2026-10-23. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
ls-wf-server-triage-patch-planning compared with similar skills
All 4 of these similar skills score higher than ls-wf-server-triage-patch-planning; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| ls-wf-server-triage-patch-planning (this skill)by CruxExperts | 48 | 0 | — | SKILL.md |
| taste-skillby Leonxlnx | 100 | 101.6k | 3d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 64.0k | 2d ago | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 44.0k | 3d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 31d ago | SKILL.md |
Frequently asked questions
- How do I install ls-wf-server-triage-patch-planning?
- Run
npx skills add CruxExperts/LocalSetup --skill ls-wf-server-triage-patch-planning. The install tabs above show the steps for each supported agent. - Which AI agents does ls-wf-server-triage-patch-planning work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is ls-wf-server-triage-patch-planning safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is ls-wf-server-triage-patch-planning still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubname: ls-wf-server-triage-patch-planning description: Use when capturing a Linux server baseline, diagnosing service issues from read-only evidence, and producing a patch plan without executing changes. metadata: version: "1.1"
Server Triage And Patch Planning
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.
Workflow
- Use
ls-system-baseline-diagnosticsto 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. - Use
ls-linux-service-triageto classify the observed failure from status and log evidence. Produce a minimal fix plan; do not restart, reload, edit, or otherwise mutate the service. - Use
ls-linux-patch-planningto generate a host or multi-host patch plan. Its bundled helper emits plans only and never executes SSH, package-manager, container, or PatchMon operations. - Return the baseline, triage findings, patch plan, verification criteria, maintenance constraints, and unresolved blockers. Label every command as plan output rather than executed evidence.
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.
Optional Manual Execution Boundary
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:
- every exact command and value;
- every target host, service, package, and container;
- expected consequences and verification checks;
- backup evidence and an exact rollback path; and
- the immediate explicit user approval for that unchanged payload.
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.
Related Skills
taste-skill
101.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
64.0kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
44.0kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
