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.

75

Quality

94%

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

92%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-structured diagnostic skill body with explicit sequenced workflows, validation checkpoints, and properly signaled one-level references. The only notable weakness is mild redundancy (the callCloudApi prohibition and the generic AIOps Methodology section) that could be trimmed for token efficiency.

Suggestions

Remove or condense the 'AIOps Methodology' section — its principles (data collection, pattern recognition, baseline comparison) are already demonstrated by the workflow steps and add generic padding.

State the 'never use callCloudApi for metrics' rule once (e.g. in 'Do NOT use for') and reference it from the other locations instead of repeating it in 'Common mistakes' and the methodology.

Consider moving the large report-template block (Steps 7) and the CLS Query Patterns table into a reference file to further slim the inline body, since they are reference material rather than workflow steps.

DimensionReasoningScore

Conciseness

Largely efficient and domain-specific, but the 'AIOps Methodology' section restates generic principles already demonstrated by the workflow, and the 'never use callCloudApi' warning is repeated across 'Do NOT use for', 'Common mistakes', and the methodology; not 5 due to these trimmable redundancies, not 3 because the bulk is purposeful tooling guidance.

4 / 5

Actionability

Provides copy-paste-ready, fully executable guidance — exact tool calls with action and metricName parameters (e.g. queryEnv(action="metrics", metricName="GatewayTraceEnvQPS")), a Preferred Tool Map, CLS queryString patterns, and concrete console URLs; covers the common inspection cases specifically.

5 / 5

Workflow Clarity

The Full Inspection Workflow is a clearly sequenced 7-step process with explicit checkpoints (env-bound check in Step 1, CLS-enabled gate before log diagnosis in Step 3, time-range scoping, playbook jump on pattern match) plus a minimal checklist; the read-only diagnostic nature means the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

SKILL.md acts as an overview with well-signaled, one-level-deep references to the real bundle files references/alarm-interpretation.md and references/fault-playbooks.md (both present), and clearly points to sibling skills via relative paths; content is appropriately split and easy to navigate.

5 / 5

Total

19

/

20

Passed

Description

96%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 with concrete capabilities, explicit 'Use when' guidance, and rich bilingual trigger terms. Its only weak spot is a slight distinctiveness risk against the many sibling CloudBase skills, where 'health checks' and 'log diagnosis' could conceivably overlap.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'health checks, log diagnosis, alarm interpretation (CPU alert normal?, peak QPS), metrics via queryEnv(action=metrics)', and named fault playbooks for '429 / function 404 / ACCESS_TOKEN_INVALID / zero invocations' — giving comprehensive, non-generic coverage; not the 4 anchor since no real coverage gaps remain.

5 / 5

Completeness

Explicitly answers both 'what' (AIOps-style CloudBase inspection doing health checks, log diagnosis, alarm interpretation, metrics, fault playbooks) and 'when' via a clear 'Use when users need...' clause plus 'Triggers on...'; matches the 5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage across two languages — 'health checks', 'troubleshooting', plus '巡检, 诊断, 告警, 峰值 QPS, 限频, 调用量为 0' — including synonyms and the exact phrases users would say; better than the 4 anchor which only has a few missing terms.

5 / 5

Distinctiveness Conflict Risk

Scoped to read-only CloudBase inspection with distinctive named error-code triggers (429, function 404, ACCESS_TOKEN_INVALID), but 'health checks, log diagnosis' is broad enough to risk minor overlap with the several sibling CloudBase skills; not 5 because some overlap with closely related implementation skills remains.

4 / 5

Total

19

/

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.