CtrlK
BlogDocsLog inGet started
Tessl Logo

database-design

设计 BK-CI 数据库表、DDL 脚本、索引、分表或数据归档策略时使用。当用户提到表结构、字段设计、索引优化、SQL 脚本命名、分片、归档迁移时优先使用。

60

Quality

70%

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 ./ai/skills/database-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a well-structured, lean instruction-only guide with a clear 7-step workflow and good routing sections, but it lacks concrete executable detail and the referenced bundle files are missing, weakening both actionability and navigation. As a database/DDL skill it also omits the validation/rollback feedback loops the rubric requires, capping workflow clarity.

Suggestions

Add explicit validation/rollback checkpoints to the workflow (e.g., a 'validate DDL on a staging DB → verify backward compatibility → only then apply' step) to satisfy the database feedback-loop requirement and lift workflow_clarity.

Create the referenced reference/1-script-management.md and reference/2-sharding.md (or remove the references) so the signaled navigation resolves to real files, fixing progressive_disclosure.

Include 1-2 concrete examples inline — a script-naming pattern and a minimal index/DDL snippet — to move actionability from directive-level to executable.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and free of concept-explanation padding, with each line offering actionable guidance; slight redundancy between the description and the 适用场景/不适用场景 sections keeps it just off the pristine 5.

4 / 5

Actionability

Gives concrete directives ('先按查询路径设计索引', 'DDL 变更必须走脚本管理') but stays at directive level with no concrete SQL, naming patterns, or index syntax, and the reference files that would supply specifics are absent; matches the 'some concrete guidance but incomplete' anchor.

3 / 5

Workflow Clarity

A clear 7-step sequence exists, but this DDL/database skill has no validation or rollback checkpoints (validate→fix→retry); per the database feedback-loop rule, workflow_clarity is capped at 3.

3 / 5

Progressive Disclosure

Sections are well-organized and references to reference/1-script-management.md and reference/2-sharding.md are clearly signaled one level deep, but those referenced files do not exist, so the navigable structure is not realized; sits at the 'structure present but gaps' anchor rather than 4.

3 / 5

Total

13

/

20

Passed

Description

83%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 strong: it states concrete capabilities and gives an explicit 'use when' clause with a rich set of natural trigger terms scoped to BK-CI. It sits just below top marks on specificity, trigger coverage, and distinctiveness due to a few missing synonyms/extensions and minor overlap risk with related architecture skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('设计...数据库表、DDL 脚本、索引、分表...数据归档策略'), naming five distinct design activities in the BK-CI domain; stops short of comprehensive coverage (e.g. omits 唯一约束/回滚), so not a 5.

4 / 5

Completeness

Explicitly answers both what ('设计 BK-CI 数据库表、DDL 脚本、索引、分表...归档策略') and when ('当用户提到...时优先使用' with concrete trigger phrases), matching the top anchor precisely.

5 / 5

Trigger Term Quality

Provides six natural trigger terms users would say ('表结构、字段设计、索引优化、SQL 脚本命名、分片、归档迁移') including synonyms 分片/分表; missing file extensions like .sql and a few synonyms (建表), so just below the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to BK-CI database design with specific triggers that rarely overlap unrelated skills; minor overlap risk with sibling architecture/SQL skills keeps it just below the minimal-conflict 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TencentBlueKing/bk-ci
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.