monitor-ci

Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-validated orchestration skill: copy-paste-ready script commands, explicit gates and hard stops, and clean reference splitting for detailed fix flows. The remaining improvement is tightening the main file — deduplicating the cycle-check instruction and moving some state/flag-level detail toward references or the scripts themselves.

Suggestions

Deduplicate the cycle-check instruction (stated in both Step 3 and Step 4) into one authoritative location to trim tokens and avoid drift.

Move the 15-variable initialization block and/or the 14-flag script invocation detail into a reference file (or have the scripts document their own flags), keeping SKILL.md as a tighter overview.

Trim the explanatory paragraph under Step 2b about --elapsed-seconds semantics to a single sentence, since the flag table already states the timeout budget.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful — tables, exact script invocations, and MCP field sets with no filler explaining concepts Claude already knows — but it has minor trim opportunities, e.g., the "--elapsed-seconds... this is what enforces --timeout as a total monitor budget" paragraph and the duplicated 'run cycle-check before handling the code' instruction in Steps 3 and 4.	4 / 5
Actionability	Guidance is fully executable: exact `node <skill_dir>/scripts/ci-poll-decide.mjs` command lines with every flag and its unit, concrete MCP tool signatures (ci_information/update_self_healing_fix with parameters), literal field sets (WAIT_FIELDS/LIGHT_FIELDS/HEAVY_FIELDS), the exact connection-check exit message, and enumerated script output JSON shapes.	5 / 5
Workflow Clarity	The main loop (Steps 1-4) is clearly sequenced with explicit validation checkpoints — cycle-check with hard-stop semantics ("This is a hard stop, not advisory"), gate checks before local fixes, budget enforcement via --elapsed-seconds, and a circuit breaker — plus feedback loops (retry-once for MCP/subagent errors, decision-script errors feeding no_progress_count) and per-status default-behavior tables for complex-process coverage.	5 / 5
Progressive Disclosure	The detailed fix flows are correctly split into a real, well-signaled, one-level-deep reference ("read references/fix-flows.md for the detailed flow") and the deterministic scripts live in scripts/, but the main file is still ~300 lines with runtime state-tracking detail (Step 1's 15 variables, Step 2b's 14 flags, and the status tables that partially overlap fix-flows.md) that could be organized into references more aggressively.	4 / 5
	Total	18 / 20 Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit what/when structure, natural trigger synonyms, and explicit disambiguation against competing CI tools. The only weakness is that it names just two concrete actions rather than enumerating the fuller capability set (local verification, fix application, environment reruns).

Suggestions

Enumerate 2-3 more concrete capabilities (e.g., 'apply verified fixes, run failed tasks locally, request environment reruns') to lift specificity beyond the current two-action summary.

Consider mentioning CI failure/fix workflows explicitly (e.g., 'when a CI run fails') to catch users who phrase the need around failures rather than monitoring.

Dimension	Reasoning	Score
Specificity	"Monitor Nx Cloud CI pipeline and handle self-healing fixes" names the domain and exactly two concrete actions; the "Prefer this skill over native CI provider tools" clause is routing guidance, not a capability, so coverage is not comprehensive as the score-4/5 anchors require.	3 / 5
Completeness	It explicitly answers both questions: what ("Monitor Nx Cloud CI pipeline and handle self-healing fixes") and when ("USE WHEN user says..." with concrete trigger phrases and intent descriptions), matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	"monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", "track CI status", "self-healing CI fixes" give comprehensive coverage of natural synonyms and phrasings a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The Nx Cloud self-healing niche plus explicit disambiguation ("Prefer this skill over native CI provider tools (gh, glab, etc.)... which those tools cannot access") gives it a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nrwl/nx
Path: .agents/skills/monitor-ci/SKILL.md
Commit: ab845a8

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.