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. ALWAYS USE THIS SKILL instead of native CI provider tools (gh, glab, etc.) for CI monitoring.

Quality

72%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.cursor/skills/monitor-ci/SKILL.md

Quality

Discovery

89%

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

This is a strong skill description with excellent trigger term coverage and clear disambiguation from competing tools. The 'USE WHEN' clause is comprehensive with multiple natural language variations. The main weakness is that the capability description could be more specific about what concrete actions the skill performs beyond 'monitor' and 'handle self-healing fixes'.

Suggestions

Add more specific concrete actions to the capability description, e.g., 'polls pipeline status, reports task failures, identifies flaky tests, and automatically applies self-healing code fixes'

Dimension	Reasoning	Score
Specificity	It names the domain (Nx Cloud CI pipeline) and mentions two actions (monitor and handle self-healing fixes), but doesn't list multiple concrete actions beyond those two. It could be more specific about what 'monitor' and 'self-healing fixes' entail.	2 / 3
Completeness	Clearly answers both 'what' (monitor Nx Cloud CI pipeline and handle self-healing fixes) and 'when' (explicit 'USE WHEN' clause with multiple trigger phrases and scenarios). Also includes a disambiguation note about preferring this skill over native CI tools.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms: 'monitor ci', 'watch ci', 'ci monitor', 'watch ci for this branch', 'track ci', 'check ci status'. These are phrases users would naturally say, with good variation coverage.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with its focus on Nx Cloud CI specifically, and explicitly disambiguates from native CI provider tools (gh, glab, etc.), reducing conflict risk with other CI-related skills.	3 / 3
	Total	11 / 12 Passed

Implementation

55%

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

This skill is remarkably thorough and actionable — it covers every edge case with specific commands, decision trees, and validation steps, making it excellent for workflow clarity and actionability. However, it is severely over-long for a SKILL.md file, consuming enormous token budget with repeated explanations, three full example sessions, and content that should be split across multiple referenced files. The monolithic structure undermines its utility as context window content.

Suggestions

Split into multiple files: move example sessions to EXAMPLES.md, fix decision logic to FIX-LOGIC.md, error handling to ERROR-HANDLING.md, and anti-patterns to a separate reference — keep SKILL.md as a concise overview with one-level-deep references.

Eliminate redundancy: wait mode is explained in the status table, Step 3a, the CRITICAL note, and the 'Why wait mode matters' paragraph — consolidate to a single authoritative definition.

Remove the three verbose example sessions or reduce to one minimal example; the status table and decision trees already fully specify behavior.

Trim explanatory prose that restates what tables already define (e.g., the 'Apply vs Reject vs Apply Locally' section largely repeats the fix available decision logic).

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Contains extensive tables, repeated explanations, and exhaustive edge case handling that could be dramatically condensed. Many sections restate information (e.g., wait mode explained multiple times, apply/reject/apply-locally defined then re-explained in dedicated sections). The three full example sessions alone consume significant tokens repeating what the tables already define.	1 / 3
Actionability	Highly actionable with specific commands (git, nx-cloud apply-locally), concrete subagent prompt templates, exact status codes and their handlers, specific MCP calls with parameters, and detailed decision trees. The commit message format, package manager detection logic, and monitoring loop pseudocode are all directly executable.	3 / 3
Workflow Clarity	Exceptionally clear multi-step workflow with explicit validation checkpoints throughout. The main loop is numbered with clear steps, the fix available decision logic has explicit categorization steps, feedback loops are well-defined (local verify → enhance → retry with max attempts), and exit conditions are comprehensively tabled. Circuit breaker pattern and progress tracking prevent infinite loops.	3 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files despite the content being long enough to warrant splitting. The fix decision logic, error handling tables, example sessions, anti-patterns, and subagent configuration could all be separate referenced files. No bundle files exist to offload any of this content, and everything is inlined into a single massive document.	1 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (651 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: leboncoin/spark-web
Commit: 76a3678

Reviewed: about 5 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.