ops-inspector

AIOps-style CloudBase inspection skill (v3). Use when users need health checks, log diagnosis, alarm interpretation (CPU alert normal?, peak QPS), metrics via queryEnv(action=metrics), or fault playbooks for 429 / function 404 / ACCESS_TOKEN_INVALID / zero invocations. Triggers on 巡检, 诊断, 告警, 峰值 QPS, 限频, 调用量为 0, troubleshooting.

Quality

94%

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

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.

The content is highly actionable with concrete tool calls, clear sequenced workflows, and validation checkpoints, supported by well-signaled reference files. Minor conciseness and progressive-disclosure gains remain from trimming conceptual sections and externalizing the report template.

Suggestions

Trim the 'AIOps Methodology' section — it restates principles Claude already applies via the workflow steps, saving tokens without losing guidance.

Move the full Markdown report template (Step 7) into a reference file and keep only the key table headers inline, reducing body bulk while preserving actionability.

Consolidate the 'Preferred Tool Map' and 'Common CLS Query Patterns' tables into a single reference if they grow further, to keep SKILL.md a true overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, actionable reference material (tool-call tables, query patterns, workflow steps) rather than concept padding, but sections like 'AIOps Methodology' and the fully inlined report template add length that could be trimmed, so it sits just below the score-5 anchor.	4 / 5
Actionability	Provides copy-paste-ready MCP calls (e.g., queryEnv(action="metrics", metricName="GatewayTraceEnvQPS")), concrete CLS queryString patterns, exact console URLs, and a structured report template — fully executable guidance covering common cases per the score-5 anchor.	5 / 5
Workflow Clarity	The Full Inspection is a 7-step sequenced workflow with explicit validation checkpoints (Step 3 CLS check with a warning fallback) and a minimal checklist; pattern-to-playbook feedback loops are present, matching the score-5 anchor.	5 / 5
Progressive Disclosure	The body clearly signals one-level-deep references to real files (references/alarm-interpretation.md, references/fault-playbooks.md — both present) plus sibling skills, but the large inlined report template and multiple full tables are bulk that could be partly externalized, placing it just below the score-5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

100%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 is specific, trigger-rich, and clearly delineates both capability and activation conditions in third-person voice. It is a strong, low-conflict description with bilingual natural-language triggers.

Dimension	Reasoning	Score
Specificity	Names the CloudBase inspection domain plus multiple concrete capabilities — 'health checks, log diagnosis, alarm interpretation', 'metrics via queryEnv(action=metrics)', and fault playbooks for four enumerated faults (429 / function 404 / ACCESS_TOKEN_INVALID / zero invocations) — for comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (AIOps-style inspection / diagnosis / alarm interpretation) and 'when' via 'Use when users need...' and 'Triggers on...', satisfying the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural bilingual trigger phrases users would say — '巡检, 诊断, 告警, 峰值 QPS, 限频, 调用量为 0, troubleshooting' plus 'health checks' — covering synonyms and the specific fault codes, matching the comprehensive score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Narrowed to CloudBase AIOps inspection with specific fault codes (429, function 404, ACCESS_TOKEN_INVALID) and bilingual triggers, giving it a clear niche with minimal overlap with other skills.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: plugin/cloudbase/skills/ops-inspector/SKILL.md
Commit: ef9f182

Reviewed: 3 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.