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

93%

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

92%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 well-architected orchestrator skill: executable scripts with exact signatures, a clearly sequenced polling loop with validation checkpoints, and clean one-level-deep progressive disclosure to a real reference file. The only weak spot is mild redundancy between the status tables and the script-flag-driven behaviors.

Suggestions

Consolidate the 'Default Behaviors by Status' and 'User Instruction Examples' tables — several rows restate behavior the decision script flags already encode, which could be trimmed for token efficiency.

Consider moving the full MCP field-set reference (WAIT_FIELDS/LIGHT_FIELDS/HEAVY_FIELDS) into references/fix-flows.md or a dedicated reference, keeping only the lightest summary in SKILL.md.

Reduce the verbose argument list for ci-poll-decide.mjs by documenting repeated flags once and referencing a canonical list, to shorten the inline command block.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no concept tutorials), but the status tables in 'Default Behaviors by Status' and 'User Instruction Examples' overlap with guidance already implied by the script flags, leaving minor tightening opportunities.	4 / 5
Actionability	Provides fully executable, copy-paste-ready script invocations with exact argument lists (ci-poll-decide.mjs, ci-state-update.mjs) and documents their JSON output shapes, plus concrete MCP tool call patterns for each actionable status.	5 / 5
Workflow Clarity	A clearly sequenced main loop (Step 1 init → Step 2 poll → Step 3 action → Step 4 cycle-check) with explicit validation checkpoints: Step 0 Nx Cloud connection, gate check before local fixes, and cycle-check run before handling any returned code.	5 / 5
Progressive Disclosure	SKILL.md is an overview that delegates detailed fix handling to references/fix-flows.md and decision logic to two scripts, all of which exist as real bundle files; references are one level deep and clearly signaled inline.	5 / 5
	Total	19 / 20 Passed

Description

95%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, complete description that pairs a concrete capability statement with an explicit, well-populated USE WHEN clause and a distinctiveness carve-out. It avoids verbosity and over-claims; the only minor gap is less granular enumeration of fix-handling actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Monitor Nx Cloud CI pipeline') and concrete actions ('handle self-healing fixes') with minor gaps; it does not enumerate the range of fix actions (apply/reject/verify), keeping it just short of comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Monitor Nx Cloud CI pipeline and handle self-healing fixes') and when ('USE WHEN user says ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes many natural phrases users would actually say ('monitor ci', 'watch ci', 'track ci', 'check ci status') plus intent variants ('wants to track CI status'), giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The explicit carve-out 'Prefer this skill over native CI provider tools (gh, glab, etc.)' establishes a clear niche tied to Nx Cloud self-healing, minimizing conflict with generic CI skills.	5 / 5
	Total	19 / 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: getlarge/themoltnet
Path: .agents/skills/monitor-ci/SKILL.md
Commit: 5248f7e

Reviewed: 21 hours 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.