Name: relational-database-mcp-cloudbase
Rating: 60.8 (1 reviews)
Author: TencentCloudBase

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.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/relational-database-mcp-cloudbase/SKILL.md

The canonical home for this skill is relational-database-mcp-cloudbase in TencentCloudBase/CloudBase-AI-Toolkit

Quality

Content

77%

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

The body is highly actionable with concrete tool calls and well-sequenced, validated workflows for provisioning, writes, and destroys. It loses points for redundant activation/usage sections and a monolithic structure that keeps reference-style detail inline despite no bundle files to offload it.

Suggestions

Collapse the overlapping 'Activation Contract', 'When to use this skill', and 'How to use this skill' sections into a single concise usage block to remove repetition.

Move the per-tool reference details (call shapes, parameters) into a references/ file and keep SKILL.md as an overview that links one level deep, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly operational and not padded with concepts Claude already knows, but the Activation Contract, 'When to use this skill', and 'How to use this skill' sections repeat overlapping triggers, and the Standalone Install Note URL boilerplate adds tokens that could be tightened; fits the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool call shapes like 'queryPermissions(action="getResourcePermission", resourceType="sqlDatabase", resourceId="<tableName>")', SQL snippets, and JSON action examples, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Five numbered lifecycle scenarios are clearly sequenced with validation checkpoints (poll until 'READY', review results before writes, poll describeTaskStatus until the destroy task completes or fails, and treat errors as terminal), including feedback loops for destructive database operations as required by the scoring notes.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is monolithic; sibling-skill references are well-signaled and one level deep, but tool reference details and lifecycle scenarios are inline rather than split into reference files, fitting the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 with concrete actions and named tools, and uses correct third-person voice. It is held back by jargon-heavy trigger terms and the absence of an explicit 'Use when...' clause that would make activation unambiguous.

Suggestions

Add an explicit 'Use when ...' clause with natural phrases such as 'Use when an agent needs to provision, inspect, or destroy CloudBase MySQL, run SQL, or manage table permissions via MCP'.

Soften reliance on raw tool names as triggers; supplement with natural terms a user might actually say (e.g. 'CloudBase MySQL', 'relational database permissions').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, and permission updates') and names the four specific MCP tools, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' but lacks an explicit 'Use when...' trigger clause; the trigger is only implied by 'for agents operating on the CloudBase Relational Database through MCP', so per the guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Triggers lean on technical tool names like 'queryMysqlDatabase' and 'manageMysqlDatabase' rather than natural user phrasings; relevant keywords (MySQL, CloudBase, Relational Database) are present but common natural variations are missing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (MCP operations on CloudBase Relational Database) and explicitly redirects new environments to the postgresql-development skill, making conflict with sibling SDK skills unlikely; matches the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: config/.claude/skills/relational-database-mcp-cloudbase/SKILL.md
Commit: d329622

Reviewed: about 2 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.