CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-db

Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model, vector index design, RAG retrieval architecture, migration, query tuning, glossary, capacity estimation, backup strategy, database anti-pattern remediation work, and ISO 27001, ISO 27002, or ISO 22301-aware database recommendations.

63

Quality

74%

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 ./benchmarks/runs/oma/.agents/skills/oma-db/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 agent definition with a coherent multi-phase workflow, explicit guardrails, and failure handling, but it is an overview that defers nearly all executable detail (templates, examples, checklist, anti-patterns) to resource files that are not present in the bundle. Redundant scheduling meta-sections and abstract framework vocabulary inflate token cost without adding actionable guidance.

Suggestions

Ship the referenced bundle files (resources/execution-protocol.md, checklist.md, examples.md, document-templates.md, anti-patterns.md, vector-db.md, iso-controls.md, error-playbook.md) or remove/inline the dangling references — progressive_disclosure and actionability both suffer because the skill's core instructions point at files that don't exist.

Deduplicate the domain enumeration: the 'Intent signature' and 'When to use' sections restate the frontmatter description; collapse them into one section and drop the 'SSL primitive' column from the Actions table to cut tokens.

Make the VERIFY step executable: replace abstract 'run checks' with concrete validation commands or an inline mini-checklist, since database work involves risky migrations where feedback loops matter.

DimensionReasoningScore

Conciseness

The domain list is repeated three times (frontmatter description, 'Intent signature', 'When to use'), and the Actions table's 'SSL primitive' column (SELECT/READ/COMPARE) and abstract 'Scenes'/'Transitions' framework add ceremony without guidance. Content is directive rather than tutorial — it avoids explaining concepts Claude already knows — so it fits 'mostly efficient but could be tightened' rather than the concept-explaining padding of anchor 2.

3 / 5

Actionability

The only executable code is the two `rg` commands; the workflow steps are high-level directives ('Model entities/aggregates, integrity, transactions...') and all templates, examples, and checklists are deferred to `resources/` files that are absent from the bundle. Concrete guardrails ('enforce at least 3NF by default', 'Default to hybrid retrieval') keep this at 3 rather than 2's 'minimal concrete guidance'.

3 / 5

Workflow Clarity

Clear sequence (Entry → PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE → Default Workflow) with a dedicated failure-and-recovery section, a VERIFY checkpoint, and 'Before submitting, run `resources/checklist.md`'. Not 5 because the validation steps are named abstractly ('Run anti-pattern, integrity, consistency, and backup/recovery checks') rather than given as executable checks, and the referenced checklist file does not exist in the bundle — minor validation gaps matching anchor 4.

4 / 5

Progressive Disclosure

The References section is well-signaled with per-file purposes and one level deep, but no bundle files exist: all 9 `resources/*.md` paths and 6 `../_shared/core/*.md` paths are dangling, and the core instruction 'Follow `resources/execution-protocol.md` step by step' points to a missing file. Navigation is broken in practice despite good on-paper structure, so it cannot score 4.

3 / 5

Total

13

/

20

Passed

Description

92%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, explicit 'what' and 'Use for...' triggers, comprehensive concrete capability coverage, and a distinct database-specialist niche. The only weakness is a keyword list so exhaustive it borders on padded, and a few natural trigger phrasings users might actually say are absent.

DimensionReasoningScore

Specificity

Lists many concrete capabilities — 'schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review' — with comprehensive coverage across SQL, NoSQL, and vector domains. Coverage is comprehensive with no meaningful gaps, matching the top anchor rather than the 'minor gaps' of 4.

5 / 5

Completeness

Explicitly answers both 'what' ('Database specialist for SQL, NoSQL, and vector database modeling...') and 'when' ('Use for database, schema, ERD, table design... ISO 27001, ISO 27002, or ISO 22301-aware database recommendations') with concrete trigger phrases, exactly matching the anchor-5 pattern. The 'when' clause is explicit and specific, so not 4.

5 / 5

Trigger Term Quality

Good natural-phrase coverage: 'database, schema, ERD, table design, document model, vector index design, RAG retrieval architecture, migration, query tuning, glossary, capacity estimation, backup strategy'. A few natural terms users would say are missing (e.g. 'slow query', 'index optimization', 'sharding/replication'), which keeps it below the comprehensive-synonyms anchor at 5 but well above anchor 3.

4 / 5

Distinctiveness Conflict Risk

Clear database-architecture niche with distinct triggers ('ERD', 'vector index design', 'RAG retrieval architecture', 'ISO 22301-aware') that other skills would not claim; conflict risk is minimal. Written in third person ('Database specialist for...'), so no voice penalty applies.

5 / 5

Total

19

/

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
first-fluke/oh-my-agent
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.