CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-domain-database

Database specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms (Neon, Supabase, Firestore). Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection. Cloud vendor guide absorbed from moai-platform-database-cloud.

Quality

66%

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 ./.claude/skills/moai-domain-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%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 verbose, prose-heavy overview that describes capabilities rather than instructing: it narrates nonexistent DatabaseManager/DataRouter classes instead of providing executable code, duplicates the description in a Quick Reference section, and inlines everything despite declaring progressive disclosure. The strongest parts are the Rationalizations/Red Flags/Verification checklists and the absorbed cloud vendor snippets.

Suggestions

Replace the narrative 'Create a DatabaseManager/DataRouter/DataSyncManager' and 'use a QueryAnalyzer' passages with either real executable code/scripts or concrete database-native commands (e.g., actual EXPLAIN ANALYZE invocations, mongosh aggregation examples, redis-cli commands).

Honor the declared progressive_disclosure structure by splitting the per-database module guides and Cloud Vendor Guide into references/ files, keeping SKILL.md as a lean overview with clearly signaled links.

Delete the Quick Reference section (it duplicates the frontmatter description) and trim Core Components/Technology Stack feature lists that restate knowledge Claude already has.

DimensionReasoningScore

Conciseness

Several padded sections restate knowledge Claude already has: "Quick Reference" duplicates the frontmatter description, "Core Components" and "Technology Stack" enumerate well-known features, and version listings ("PostgreSQL 14+", "MongoDB 6.0+", "Oracle 19c+") add time-sensitive clutter outside any deprecated/old-patterns section. This matches anchor 2 (several unnecessary or padded sections) rather than 3, since the padding spans multiple large sections rather than isolated instances.

2 / 5

Actionability

The core guidance is prose about imaginary helpers with no executable code: "Create a DatabaseManager instance and configure multiple database connections", "use a QueryAnalyzer to generate optimization suggestions", "create an AggregationOptimizer" — none of these classes or tools exist in the skill. Only the absorbed Cloud Vendor Guide has real snippets (RLS policy, pgvector query, Firestore rules). This sits at anchor 2 (high-level hints, missing specific steps) rather than 3, because the majority of the document instructs through non-executable narrative rather than incomplete-but-real code.

2 / 5

Workflow Clarity

"Quick Start Workflow" and "Advanced Patterns" present a rough sequence (initialize connections, run migrations, route data) but with no validation checkpoints embedded in the flow. The Verification section offers a checklist ("Migration file exists for every schema change", "EXPLAIN ANALYZE run for new queries") but it is detached from any workflow, and database operations lack validate-fix-retry loops, capping this dimension at 3 per the rubric's database-operations rule.

3 / 5

Progressive Disclosure

Section headers provide some structure, but no bundle files exist despite frontmatter declaring "progressive_disclosure: enabled" with token budgets. Content that clearly belongs in separate files (per-database module guides, the 60-line Cloud Vendor Guide) is inlined in a ~265-line body. Not anchor 2 because headers do give navigable structure; not anchor 4 because nothing is actually split out or referenced.

3 / 5

Total

10

/

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.

A strong description: third-person voice, explicit what-and-when structure, and concrete platform/task triggers. Minor improvements would come from adding natural synonyms (SQL, NoSQL, migrations) and clarifying its boundary against the absorbed platform skills.

DimensionReasoningScore

Specificity

The description lists several concrete task actions ("schema design, query optimization, indexing strategies, data modeling, or cloud database selection") across six named platforms. It falls short of anchor 5 because the actions are broad task categories and coverage gaps remain (migrations, ORMs, and aggregation/caching operations appear only in the separate when_to_use field, not the description).

4 / 5

Completeness

It explicitly answers both what ("Database specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms") and when ("Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection") with concrete trigger phrases, matching the anchor-5 pattern.

5 / 5

Trigger Term Quality

Natural user phrases are present ("PostgreSQL", "MongoDB", "Redis", "schema design", "indexing strategies", "Neon, Supabase, Firestore"), giving good keyword coverage. Not anchor 5 because common variations users would say are missing, such as "SQL", "NoSQL", "database migrations", "query tuning", or file/tool extensions.

4 / 5

Distinctiveness Conflict Risk

The database niche is clear with distinct platform and task triggers, so it is mostly distinct. Not anchor 5 because it explicitly overlaps sibling platform skills ("Cloud vendor guide absorbed from moai-platform-database-cloud", plus the body's moai-platform-supabase/neon/firestore companions), creating minor conflict risk with closely related skills.

4 / 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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

modu-ai/moai-adk

Path

.claude/skills/moai-domain-database/SKILL.md

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.