ci-monitor

Monitor Nx Cloud CI pipeline and handle self-healing fixes automatically. Checks for Nx Cloud connection before starting.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/ci-monitor/SKILL.md

Quality

Content

77%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-sequenced orchestration skill: exact commands, MCP call signatures, decision tables, and feedback loops with circuit breakers throughout. Its weaknesses are token efficiency (duplicated flows and redundant example transcripts) and the absence of any bundle structure for a skill this long.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — status/decision/exit tables and terse step lists rather than prose — but there is real duplication: the Apply-Locally+Enhance flow is written out twice (Step 3b item 4 and its own 'Apply Locally + Enhance Flow' section), no-new-CIPE handling reappears in the Error Handling table, and two full ~30-line example transcripts pad the end. Fits anchor 3 ('mostly efficient but could be tightened'), not 2 since there is no over-explanation of concepts Claude already knows.	3 / 5
Actionability	Fully concrete throughout: exact MCP calls ('update_self_healing_fix({ shortLink, action: "APPLY" })'), exact commands ('nx apply-locally <shortLink>', git commit/push sequences with message formats), subagent spawn prompt templates, and a complete config-defaults table covering every tunable. Matches 'fully executable; copy-paste ready commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The multi-step orchestration is explicitly sequenced (main loop steps, status-to-behavior table, wait-mode state tracking) with strong validation checkpoints: local task verification before applying, retry caps ('local_verify_count >= local_verify_attempts'), a no-progress circuit breaker, and per-error recovery actions — matching the anchor's 'explicit validation steps; feedback loops for error recovery'.	5 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), so everything — including two full example session transcripts and the detailed status-handling prose — is inlined in a 438-line SKILL.md. Section headers are clear, but content that clearly belongs in a separate reference file (the example sessions, per-status handling detail) is inline, matching anchor 3 rather than 4.	3 / 5
	Total	16 / 20 Passed

Description

57%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.

The description clearly states what the skill does within a distinct niche, but lacks any 'when to use' trigger guidance and misses several natural user phrasings. Adding an explicit 'Use when...' clause and common synonyms (CI failed, build broken, PR checks) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when CI fails on a branch, when the user asks to monitor or watch CI, or when Nx Cloud self-healing reports a fix.'

Include natural synonyms users actually say — 'CI failed', 'build is broken', 'flaky tests', 'PR checks' — not just the product terms 'Nx Cloud' and 'self-healing'.

Briefly enumerate the concrete handling actions (apply fix via MCP, apply locally and enhance, reject and fix from scratch, local verification) to raise specificity beyond the current generic 'handle'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Nx Cloud CI pipeline') and 2-3 concrete actions ('Monitor... pipeline', 'handle self-healing fixes', 'Checks for Nx Cloud connection'), but coverage is not comprehensive — it omits the apply/reject/enhance/local-verify behaviors the skill actually implements. Not 4 because the action list has gaps beyond 'minor'.	3 / 5
Completeness	The 'what' is clear (monitor Nx Cloud CI and handle self-healing fixes), but there is no 'Use when...' clause or equivalent trigger guidance — per the judging guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords are present ('CI', 'pipeline', 'Nx Cloud', 'self-healing'), but common natural phrasings users would say are missing ('build failed', 'CI is broken', 'flaky tests', 'fix my PR'). Matches 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The description is anchored to a specific product niche ('Nx Cloud CI pipeline', 'self-healing fixes'), giving it a clear trigger surface with minimal overlap risk against other skills.	5 / 5
	Total	14 / 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: .cursor/skills/ci-monitor/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.