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.

61

Quality

73%

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

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

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 well-structured and actionable with concrete tool calls and an executable example, and the workflow has clear validation checkpoints. The main drag is repeated routing guidance across several sections that inflates length without adding guidance.

Suggestions

Consolidate the MySQL-vs-PostgreSQL routing into a single authoritative section and have other sections cross-reference it instead of restating it.

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

Provide a complete modifyDataModel call example with the full parameter shape (mermaidDiagram, action, publish decision) so the create path is copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient with no padding about basic concepts, but the MySQL-vs-PostgreSQL routing guidance is restated across the Activation Contract, Overview, Quick routing, and Best practices sections and could be consolidated.

3 / 5

Actionability

Provides concrete tool calls (manageDataModel action="list"/"get"/"docs", modifyDataModel with action="create"), an executable Mermaid example, and a compact type-mapping table, with only minor gaps such as a full modifyDataModel call skeleton.

4 / 5

Workflow Clarity

A clear four-step sequence (Clarify → Model → Use tools → Publish) with validation checkpoints ("Validate names, field types, and relationships before calling modeling tools", "Publish only after checking..."), though the publish step lacks an explicit validate→fix→retry feedback loop.

4 / 5

Progressive Disclosure

Single well-organized file (~170 lines) with clear section headers and one-level-deep sibling-skill references via relative paths; no bundle files exist, and the structure is appropriate, though some content (e.g. full Mermaid rules) could optionally live in a reference.

4 / 5

Total

15

/

20

Passed

Description

78%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 clearly carves out a niche and aggressively routes sibling tasks away, giving strong distinctiveness and decent trigger coverage. Its main weakness is that the deprecation/routing framing crowds out a crisp positive statement of when to use this skill.

Suggestions

Lead with one explicit "Use when..." clause naming Mermaid classDiagram / multi-entity relational modeling before the redirect guidance, so the positive trigger is as prominent as the deprecation.

Name the concrete modeling actions this skill performs (draft classDiagram, validate fields/relationships, generate model structure) rather than only describing what to use instead.

Add the natural synonyms users say ("ER diagram", "entity-relationship", "schema design") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions/destinations — "complex data modeling", "MySQL table creation", "PostgreSQL / CloudBase PG schema work" — with explicit tool routing, but does not fully enumerate the modeling actions themselves.

4 / 5

Completeness

States the "what" ("Optional advanced tool for complex data modeling") and provides equivalent explicit trigger guidance via routing boundaries (use X for simple, use Y for PG), though the "when to use THIS skill" portion is weaker than the redirect/deprecation guidance.

4 / 5

Trigger Term Quality

Good natural-keyword coverage ("data modeling", "MySQL table creation", "PostgreSQL / CloudBase PG schema work", queryPgDatabase/managePgDatabase), though a few common user phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit conflict-resolution routing against sibling skills (relational-database-tool, postgresql-development), minimizing risk of triggering for the wrong skill.

5 / 5

Total

17

/

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.