Agent Skills › nixopus/nixopus › self-heal

self-heal

GitHub

自动修复部署失败的Skill。通过诊断、应用已知修复或创建PR重试，最多3次后回滚或升级。支持S3和GitHub源，无需用户干预即可执行自愈流程。

api/skills/self-heal/SKILL.md nixopus/nixopus

Trigger Scenarios

部署失败构建错误

Install

npx skills add nixopus/nixopus --skill self-heal -g -y

More Options

Non-standard path

npx skills add https://github.com/nixopus/nixopus/tree/master/api/skills/self-heal -g -y

Use without installing

npx skills use nixopus/nixopus@self-heal

指定 Agent (Claude Code)

npx skills add nixopus/nixopus --skill self-heal -a claude-code -g -y

安装 repo 全部 skill

npx skills add nixopus/nixopus --all -g -y

预览 repo 内 skill

npx skills add nixopus/nixopus --list

SKILL.md

Frontmatter

{
    "name": "self-heal",
    "metadata": {
        "version": "1.0"
    },
    "description": "Self-healing loop for failed deployments — diagnose, fix, redeploy up to 3 attempts, then escalate or rollback. Load when a deployment fails or build errors occur."
}

Self-Heal

Flow (max 3 attempts)

On build_failed: check [deploy-patterns] for a known fix first → if no match, get_deployment_logs → diagnose → apply fix → redeploy → resume monitoring. Known fixes from [deploy-patterns] have cross-org confidence scores. Prefer high-confidence fixes (>70%) before investigating from scratch.

Applying the fix

S3 sources: Use write_workspace_files to save the fix — files sync automatically.
GitHub sources: Do NOT use write_workspace_files (it only writes locally and the fix will not reach the repo). Instead, use the GitHub tools: read_skill("github-workflow") and follow the Fix-via-PR flow (create branch → github_create_or_update_file → open PR → ask user to merge → redeploy).

Rules

Do not stop to ask the user unless the fix is ambiguous or requires credentials you do not have.
After each failed attempt, tell the user what broke and what you are trying next.
Maximum 3 self-heal attempts.
After 3 failures, read_skill("rollback-strategy") to decide whether to rollback or escalate.
If escalation is required, tell the user plainly that you could not complete the deployment automatically and that a Nixopus team member will reach out shortly to help finish it.