发现优质的 AI Agent 技能

Use this skill to detect workflows that rely too heavily on manual triggers (`workflow_dispatch` / `repository_dispatch`) instead of automated CI events.

Use this skill to detect unstable workflows on protected branches (main/master/release) before they silently degrade delivery confidence.

Use this skill to catch workflows that recently degraded (new flaky tests, broken deploy gates, bad dependency updates, or infra outages) before they become long-running incidents.

Use this skill to detect accidental duplicate workflow execution bursts (for example trigger overlap, force-push storms, or retried dispatches) and measure wasted CI minutes.

Use this skill to rank deployment workflows that are currently risky to trust for production releases.

Use this skill to detect unstable workflows that frequently flip between success and failure-like outcomes.

Use this skill to quantify wasted GitHub Actions runtime from cancelled or timed-out runs so flaky workflow churn gets fixed before it burns CI budget.

Use this skill to statically audit `.github/workflows/*.yml` for risky cache patterns that can cause cache poisoning, stale cache churn, or secret leakage.

Run this workflow when handling Realist podcast episode publishing.

Use this skill when a user wants realtor CRM actions in GoHighLevel (GHL), including lead follow-up, pipeline movement, appointment booking context, and messaging workflows.

Use this workflow for PR-comment-driven changes.

> **Purpose**: Guide agents to decompose complex user requests into atomic, executable tasks.