monitor-ci

Monitor Nx Cloud CI pipelines and orchestrate self-healing fix workflows.

3|10|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/fleetshift/fleetshift-poc --skill monitor-ci-fleetshift
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: monitor-ci
Source: https://github.com/fleetshift/fleetshift-poc/tree/main/.agents/skills/monitor-ci
Command: npx skills add https://github.com/fleetshift/fleetshift-poc --skill monitor-ci-fleetshift

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Watching CI pipelines manually wastes time, and standard CI provider tools cannot interact with Nx Cloud self-healing fixes. This Skill continuously monitors Nx Cloud CI pipeline executions, interprets self-healing status, and applies, verifies, or enhances fixes automatically. ## Core Features & Use Cases - Automated CI polling: Spawns lightweight subagents to poll Nx Cloud CI status without consuming main agent context, with backoff, circuit breakers, and timeout budgets. - Self-healing fix orchestration: Applies verified fixes via MCP, runs local verification for unverified tasks, and enhances or rejects inadequate fixes. - Deterministic decision scripts: Uses ci-poll-decide.mjs and ci-state-update.mjs to classify CI states, enforce cycle budgets, and manage wait-mode state transitions. - Use Case: After pushing a branch, ask the agent to watch CI; it detects a failing task, finds an Nx Cloud self-healing fix, verifies it locally, applies it, and waits for the new CI attempt to pass. ## Quick Start Ask the agent to monitor CI for this branch and handle any self-healing fixes until the pipeline passes.

Frequently Asked Questions about monitor-ci

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor CI status for my branch automatically?

Invoke the monitor-ci skill with a phrase like "watch ci for this branch". It polls Nx Cloud via subagents, reports status changes, and handles self-healing fixes until the pipeline succeeds or a budget limit is reached.

What is Nx Cloud self-healing and how does this skill use it?

Nx Cloud self-healing generates suggested fixes for failed CI tasks. This skill queries fix status through the ci_information MCP tool and applies, rejects, or locally verifies fixes using the update_self_healing_fix tool.

Why use this instead of gh or glab CLI for CI monitoring?

CI provider CLIs cannot access Nx Cloud self-healing data or apply suggested fixes. The skill explicitly prefers its MCP-based flow over gh or glab watch commands, which bypass self-healing entirely.

Does monitor-ci work without an Nx Cloud connection?

No. The skill checks nx.json for nxCloudId or nxCloudAccessToken before starting and exits immediately if the workspace is not connected to Nx Cloud, since no CI data would be available.

What happens when the CI monitoring cycle limit is reached?

The ci-state-update.mjs cycle-check enforces a hard stop at the max-cycles budget (default 10 agent-initiated cycles). Two cycles before the cap, the skill asks whether to continue with more cycles or stop.

Can I control whether fixes are applied automatically?

Yes. User instructions override defaults, such as "never auto-apply", "always ask before git push", or confidence thresholds. The skill parses these instructions and adjusts apply, reject, and verification behavior accordingly.