CtrlK
BlogDocsLog inGet started
Tessl Logo

704-technologies-sql

Use when you need framework-agnostic SQL guidance — schema naming, relational table design, query readability, indexes, transactions, database security, migrations, testing, and monitoring — without choosing Spring Boot, Quarkus, or Micronaut. This should trigger for requests such as Review SQL schema or migrations; Improve SQL query performance and readability; Design relational tables and indexes; Review database transaction, security, or monitoring practices. Part of Plinth Toolkit

64

Quality

80%

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 ./skills/704-technologies-sql/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

A lean, well-structured body with executable build/verify commands, concrete deferral targets, and exemplary progressive disclosure to a single real reference file. The main gap is the workflow's lack of a validate→fix→retry feedback loop for SQL/migration changes, which the rubric caps at 3; there is also mild duplication between the coverage list, the 'When to use' section, and the description.

Suggestions

Add an explicit feedback loop after verification, e.g. 'If `mvn clean verify` or migration validation fails, fix the offending SQL and re-run before promoting changes' — this lifts workflow clarity past the database-operations cap of 3.

Merge 'What is covered in this Skill?' and 'When to use this skill' into one section (the latter already repeats the description's trigger phrases verbatim) to cut duplicated tokens.

Inline one short, copy-paste SQL snippet for the most common case (e.g., bind parameters vs. string concatenation) so the top-level guidance is executable without opening the reference.

DimensionReasoningScore

Conciseness

The ~55-line body is efficient with no explanation of concepts Claude already knows; anchor 4 fits ('minor instances of over-explanation that could be trimmed') because 'What is covered in this Skill?' and 'When to use this skill' largely duplicate each other and the frontmatter description, and 'After editing this repository's XML sources, regenerate skills and verify the build' is repo-maintenance filler for a SQL skill.

4 / 5

Actionability

Concrete, executable commands are present ('Run `./mvnw compile` or `mvn compile`', 'Run `./mvnw clean verify` or `mvn clean verify`') alongside specific file paths and named deferral targets ('@311-frameworks-spring-jdbc', 'references/704-technologies-sql.md'), matching anchor 4. Not anchor 5 because no inline SQL example covers the common cases — everything executable lives in the reference — and workflow verbs like 'inspect current schema' remain high-level.

4 / 5

Workflow Clarity

The four-step sequence is clear and validation is explicitly present (step 4 'Execute appropriate build, migration, SQL validation, and test checks' plus the MANDATORY and VERIFY constraints), but there is no validate→fix→retry feedback loop — nothing says what to do when verification fails. The rubric's scoring note caps workflow_clarity at 3 for database-operation skills missing feedback loops, which overrides the otherwise anchor-4 fit.

3 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview that delegates all detailed guidance and examples to a single one-level-deep reference, 'references/704-technologies-sql.md' (verified to exist, 184 lines, well-organized with its own table of contents), linked both in the Workflow step and a dedicated Reference section — a clear match for anchor 5's 'clear overview with well-signaled one-level-deep references'.

5 / 5

Total

16

/

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.

A strong description with comprehensive capability coverage, explicit trigger phrases, and clear de-scoping from Java framework skills. Its weaknesses are the second-person "Use when you need" phrasing (explicitly penalized by the rubric) and topic-noun rather than action-verb capability framing, plus a missing synonym/extension layer in the triggers.

Suggestions

Rewrite the opening in third person or plain imperative, e.g. 'Provides framework-agnostic SQL guidance for schema naming, table design...' instead of 'Use when you need framework-agnostic SQL guidance', to avoid the second-person penalty.

Lead the capability list with action verbs ('Reviews SQL schema and migrations, designs relational tables and indexes, improves query readability and performance') rather than a bare topic list.

Add natural synonyms and artifacts to the trigger list, such as '.sql files', 'database queries', 'schema design', and 'DDL', so users phrasing the request differently still match.

DimensionReasoningScore

Specificity

The description lists nine concrete capability areas ("schema naming, relational table design, query readability, indexes, transactions, database security, migrations, testing, and monitoring"), which reads as a topic list rather than the action-verb coverage of the 5-anchor ("Extract text and tables from PDF files, fill forms, merge documents") — closer to anchor 4's 'several specific actions, minor gaps'. Per the judging guideline, the second-person phrase "Use when you need framework-agnostic SQL guidance" reduces this score by 1.

3 / 5

Completeness

It explicitly answers both what ("framework-agnostic SQL guidance — schema naming, relational table design, ... monitoring") and when ("This should trigger for requests such as Review SQL schema or migrations; ..."), with concrete trigger phrases — a clear match for anchor 5. Anchor 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Trigger phrases are natural user requests ("Review SQL schema or migrations; Improve SQL query performance and readability; Design relational tables and indexes"), matching anchor 4's 'good keyword coverage; a few natural terms missing'. It falls short of anchor 5 because common synonyms and file extensions are absent (no '.sql', 'database queries', 'query tuning', 'DDL').

4 / 5

Distinctiveness Conflict Risk

The negative scoping "without choosing Spring Boot, Quarkus, or Micronaut" plus the framework deferrals makes the niche mostly distinct (anchor 4). Not anchor 5 because triggers like "Review SQL schema or migrations" still overlap with migration-tool (e.g., Flyway) and database-tuning skills, and "Part of Plinth Toolkit" adds no disambiguation.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
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.