CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is ops-inspector in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

85%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-structured, highly actionable diagnostic skill body with explicit workflows, validation checkpoints, and clean progressive disclosure to real reference files. Its main weakness is mild verbosity — the generic 'AIOps Methodology' section explains concepts Claude already knows and could be trimmed.

Suggestions

Trim or remove the 'AIOps Methodology' section — steps like 'Data Collection', 'Pattern Recognition', and 'Root Cause Hypothesis' are generic principles Claude already knows and add tokens without new capability.

Consider moving the large Step 7 report markdown template into a reference file (e.g. references/report-template.md) and keeping only a short pointer inline, to further reduce SKILL.md weight.

The Severity Levels table is useful for report formatting but could be condensed into a single line mapping (Critical=❌, Warning=⚠️, Info=ℹ️, Healthy=✅) to save tokens.

DimensionReasoningScore

Conciseness

Mostly efficient concrete tool-call guidance, but the 'AIOps Methodology' section restates generic principles (Data Collection, Pattern Recognition, Root Cause Hypothesis) Claude already knows, and the body (~285 lines) could be tightened in places.

3 / 5

Actionability

Fully executable guidance throughout — exact MCP calls with action parameters (e.g., `queryEnv(action="metrics", metricName="GatewayTraceEnvQPS")`), ready-to-use CLS query strings, and concrete console URLs covering the common inspection cases.

5 / 5

Workflow Clarity

The Full Inspection Workflow is a clear 7-step sequence with explicit validation checkpoints (env check in Step 1, CLS-enablement check in Step 3 before log diagnosis) plus a minimal checklist and common-mistakes feedback guidance for error recovery.

5 / 5

Progressive Disclosure

Clear overview structure with well-signaled one-level-deep references to real bundle files (`references/alarm-interpretation.md`, `references/fault-playbooks.md`) and sibling skills in a dedicated 'Then also read' section; detail is appropriately split out.

5 / 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.

A strong, third-person description that concisely states concrete capabilities and pairs them with explicit 'Use when...' and 'Triggers on...' guidance covering natural English and Chinese phrases. It is specific, complete, and clearly distinguishable from sibling skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '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' — with comprehensive coverage of the inspection domain and specific fault codes.

5 / 5

Completeness

Explicitly answers both 'what' ('AIOps-style CloudBase inspection skill (v3)... health checks, log diagnosis, alarm interpretation... fault playbooks') and 'when' ('Use when users need... Triggers on...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms in both English ('health checks', 'log diagnosis', 'alarm interpretation', 'troubleshooting', 'peak QPS') and Chinese ('巡检', '诊断', '告警', '限频', '调用量为 0'), matching phrases users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear CloudBase-inspection niche anchored by specific fault codes (429 / function 404 / ACCESS_TOKEN_INVALID / zero invocations) and a specific metrics tool, giving it distinct triggers with minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
Reviewed

Table of Contents

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.