CtrlK
BlogDocsLog inGet started
Tessl Logo

data-model-creation

[Deprecated] Optional advanced tool for complex data modeling. For simple MySQL table creation, use relational-database-tool directly; for PostgreSQL / CloudBase PG schema work, use postgresql-development. New environments should use PostgreSQL DDL via queryPgDatabase/managePgDatabase — see postgresql-development skill instead.

57

Quality

67%

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 ./config/.claude/skills/data-model-creation/SKILL.md

The canonical home for this skill is data-model-creation in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

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 strong on actionability and workflow clarity thanks to a concrete Mermaid example, a type-mapping table, explicit validation checkpoints, and specific tool signatures, but it repeats routing guidance across several sections and keeps all content inline rather than splitting reference material into bundle files.

Suggestions

Consolidate the PostgreSQL/deprecation routing so it appears once; the Activation Contract and Quick routing sections overlap heavily and could be merged.

Move the type-mapping table and detailed tool-usage guidance into a references/ file (e.g. TYPE_MAPPING.md) and link to it from the body to improve progressive disclosure.

Add an explicit validate->fix->retry feedback loop around the publish step, since publishing a data model is a hard-to-reverse operation.

DimensionReasoningScore

Conciseness

The body is mostly useful operational content and does not explain concepts Claude already knows, but the PostgreSQL/deprecation routing is repeated across the Overview, Quick routing, Then-also-read, and Best practices sections, and the Activation Contract overlaps heavily with Quick routing — material that could be tightened.

2 / 3

Actionability

It provides a copy-paste-ready Mermaid classDiagram example, a concrete business-to-Mermaid type mapping table, explicit naming conventions, and specific tool signatures such as manageDataModel(action="list"|"get"|"docs") and modifyDataModel with action="create".

3 / 3

Workflow Clarity

The 'How to use this skill' section gives a clear 4-step sequence with explicit validation checkpoints ('Validate names, field types, and relationships before calling modeling tools' and 'Publish only after checking field names, required constraints, and relationship directions') plus a Minimal checklist, exceeding the missing-checkpoint bar of anchor 2.

3 / 3

Progressive Disclosure

The file is well-organized with clearly signaled one-level sibling-skill references and standalone fallback URLs, but at ~180 lines all content is inline with no internal bundle references — the type-mapping table and detailed tool guidance could live in separate reference files.

2 / 3

Total

10

/

12

Passed

Description

57%

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 distinctive and excels at conflict-avoidance routing, but it is weak on its own capabilities, natural trigger terms, and lacks an explicit positive 'Use when' trigger for this skill.

Suggestions

Add an explicit positive trigger clause (e.g., 'Use when you need multi-entity ER modeling or Mermaid classDiagram output') so the skill's own 'when' is clear, not just when to use alternatives.

List the concrete actions this skill performs (e.g., 'design entity relationships, generate Mermaid classDiagram models, publish data models') instead of only describing the domain.

Lead with natural user-facing terms ('data model design', 'ER diagram', 'entity relationships') and relegate internal tool jargon (queryPgDatabase/managePgDatabase) to later in the description.

DimensionReasoningScore

Specificity

It names the domain ('complex data modeling') and references concrete tool names ('queryPgDatabase/managePgDatabase', 'relational-database-tool'), but it never lists the concrete actions this skill itself performs — the only actions stated are routing directives to other skills.

2 / 3

Completeness

The 'what' is stated weakly ('Optional advanced tool for complex data modeling'), but there is no explicit 'Use when...' trigger for this skill — the description only tells you when to use other skills, so per the cap-at-2 guideline it cannot reach 3.

2 / 3

Trigger Term Quality

Some natural keywords appear ('complex data modeling', 'MySQL table creation', 'schema work'), but coverage of common variations is thin and weighed down by internal jargon ('CloudBase PG', 'PostgreSQL DDL', 'queryPgDatabase/managePgDatabase') that users would rarely say.

2 / 3

Distinctiveness Conflict Risk

The description is almost entirely about deprecation and redirecting to named alternatives, giving the skill a clear niche and actively steering away from overlaps, making it unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

12

Passed

Validation

81%

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

Validation13 / 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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

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.