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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A highly actionable, clearly sequenced orchestration skill with strong workflow clarity and concrete MCP/git commands. Its weaknesses are conciseness (duplication and padded examples) and progressive disclosure (everything inline in one large file with no references).

Suggestions

De-duplicate the Apply-Locally+Enhance flow (it appears both inside Fix Available Decision Logic and as its own section) and move the three full example sessions into a separate references file to tighten the body.

Split the per-status handling tables and example sessions into one-level-deep reference files (e.g., EXAMPLES.md, STATUS-HANDLING.md) referenced from the overview to improve progressive disclosure.

Trim repeated commit-message and apply/reject explanations that restate the same MCP calls across multiple sections.

Dimension	Reasoning	Score
Conciseness	Most of the ~650 lines are non-obvious operational detail Claude would not know (MCP calls, status enums, wait-mode logic), but the Apply-Locally+Enhance flow is stated twice and the three full example sessions are padded; could be tightened. Not level 1 because the bulk earns its place, not level 3 because of clear duplication and verbosity.	2 / 3
Actionability	Fully concrete and executable: exact MCP calls (update_self_healing_fix({ shortLink, action: 'APPLY' })), precise commands (nx-cloud apply-locally <shortLink>, git commit --allow-empty), and copy-paste subagent spawn prompts.	3 / 3
Workflow Clarity	Clear sequenced main loop with explicit validation checkpoints, circuit breakers (3 consecutive no-progress), retry caps (local_verify_count), and feedback loops (validate -> fix -> retry) for the destructive/batch git operations. Not level 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	Well-sectioned with clear tables, but it is a single monolithic ~650-line file with no bundle files and no one-level-deep references; example sessions and per-status handling that should be split out are inline. Not level 1 because organization is good, not level 3 because nothing is split into references.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, well-structured description with explicit 'USE WHEN' triggers and good natural-phrase coverage. Its only weakness is specificity: it names the domain and two actions rather than enumerating concrete capabilities.

Suggestions

Expand the capability list beyond 'Monitor' and 'handle self-healing fixes' to concrete actions (e.g., apply/verify/reject self-healing fixes, retry failed CI attempts, update lockfiles) to lift specificity to 3.

Soften the absolute 'ALWAYS USE THIS SKILL instead of native CI provider tools' to a scoped guidance so it reads less like an over-claim.

Dimension	Reasoning	Score
Specificity	Names the domain ('Nx Cloud CI pipeline') and two concrete actions ('Monitor', 'handle self-healing fixes'), but stops at two verbs rather than listing multiple specific concrete actions; not a level-1 vague phrase and not a level-3 comprehensive action list.	2 / 3
Completeness	Explicitly answers both what ('Monitor Nx Cloud CI pipeline and handle self-healing fixes') and when via a clear 'USE WHEN ...' clause with concrete triggers. Not level 2 because 'when' is explicit, not implied.	3 / 3
Trigger Term Quality	Good coverage of natural phrases users would say: 'monitor ci', 'watch ci', 'ci monitor', 'track ci', 'check ci status'. Not level 2 because common variations are present, not level 1 because these are natural user terms rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Nx Cloud self-healing CI) with distinct triggers unlikely to fire for unrelated skills. The 'ALWAYS USE THIS SKILL instead of native CI provider tools' phrasing borders on over-claim but reinforces a distinct, narrow niche.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 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	15 / 16 Passed

Repository: leboncoin/spark-web
Commit: 13e119c

Reviewed: about 19 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.