CtrlK
BlogDocsLog inGet started
Tessl Logo

relational-database-mcp-cloudbase

[Deprecated] This is the required documentation for agents operating on the CloudBase Relational Database through MCP. It defines the canonical SQL management flow with `queryMysqlDatabase`, `manageMysqlDatabase`, `queryPermissions`, and `managePermissions`, including MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, and permission updates. New environments should use PostgreSQL — see postgresql-development skill instead.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin/cloudbase/skills/relational-database-mcp-cloudbase/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is actionable and well-sequenced with validation checkpoints for destructive flows, but structural redundancy across the activation/usage/principle sections inflates token cost and keeps it from being lean.

Suggestions

Collapse the overlapping Activation Contract, When to use this skill, and Key principle sections into a single concise 'When and how to use' block to remove restated MCP-vs-SDK and tool-selection guidance.

State the getConnectionInfo exception once in the queryMysqlDatabase tool section and reference it rather than repeating the warning in multiple places.

Add a brief validate→fix→retry loop note for the schema-initialization scenario to push workflow clarity toward a 5.

DimensionReasoningScore

Conciseness

No basic-concept over-explanation, but the MCP-vs-SDK guidance and tool-selection rules are restated across the Activation Contract, When to use, How to use, and Key principle sections, and the getConnectionInfo caveat is repeated, so the body could be tightened.

3 / 5

Actionability

Provides concrete call shapes (e.g., queryPermissions(action='getResourcePermission', resourceType='sqlDatabase', resourceId='<tableName>')), a runnable JSON runQuery example, and a SQL _openid snippet covering common cases, though some signatures are abbreviated rather than full payloads.

4 / 5

Workflow Clarity

Five numbered lifecycle scenarios include explicit validation checkpoints (poll until READY, explicit confirm=true for destructive ops, post-write read-only verification), but full validate→fix→retry recovery loops are mostly absent so it stops short of 5.

4 / 5

Progressive Disclosure

Well-organized sections with clear headers and one-level-deep, clearly signaled sibling-skill references (../relational-database-web-cloudbase/SKILL.md, ../http-api-cloudbase/SKILL.md); no bundle files exist to split into, so the single ~205-line file is mostly appropriately placed with minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

62%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 and well-scoped to a distinct niche, but it lacks an explicit 'Use when…' trigger clause and leans on technical jargon over natural user phrasing, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers (e.g., 'Use when an agent must provision, query, or destroy CloudBase MySQL via MCP').

Soften jargon by pairing tool names with plain phrases users would say, such as 'manage CloudBase MySQL' or 'inspect SQL data'.

Lead with the capability summary before the deprecation framing so the concrete actions are the first thing parsed.

DimensionReasoningScore

Specificity

Lists six concrete actions (MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, permission updates) plus four named MCP tools, but the 'required documentation for agents operating on' meta-framing keeps it just below a clean comprehensive 5.

4 / 5

Completeness

The 'what' is clear (canonical SQL management flow with enumerated capabilities), but there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Relevant keywords exist (CloudBase Relational Database, MySQL, SQL, MCP) but they lean technical and include tool names rather than natural user phrasing; common synonyms and casual trigger phrasing are missing.

3 / 5

Distinctiveness Conflict Risk

A clear niche (CloudBase Relational Database via MCP with specific tool names) plus an explicit redirect to the postgresql-development skill yields minimal conflict risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

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.