CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oma-db

Design schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.

Quality

73%

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-plugin/directory/skills/oma-db/SKILL.md
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 a well-structured, highly specific orchestration document: a clear sequenced workflow with verification checkpoints, concrete tool and resource pointers, and a well-signaled one-level reference system. Its main cost is token efficiency — redundant scheduling/transition sections and guardrails that restate standard database knowledge Claude already has.

Suggestions

Merge the 'Intent signature' and 'When to use' sections and fold the Transitions section into the guardrails to remove duplicated content.

Trim guardrails that restate knowledge Claude already has (e.g. 3NF/ACID definitions, 'measure before optimizing') and keep only the project-specific policy decisions.

Move the 18-item guardrails list or the Deliverables-by-Scope detail into a reference file, keeping a short summary inline.

DimensionReasoningScore

Conciseness

The body is mostly prescriptive rather than educational, but includes unnecessary repetition: the Transitions section restates guardrails 2-4, 'Intent signature' overlaps 'When to use', and several guardrails (3NF/ACID basics, 'measure, explain, then optimize') restate standard DB knowledge Claude already has. Not 4 because the redundancy and known-knowledge restatement is more than minor.

3 / 5

Actionability

Gives mostly concrete, directive guidance: named code-intelligence tools (find_file, search_for_pattern, get_symbols_overview), precise section pointers (resources/anti-patterns.md §5), a concrete expand-contract procedure (additive expand, dual-write + batched backfill, verified read switch, delayed contract), and specific artifact specs. Not 5 because no executable commands or worked examples appear inline — the executable detail is delegated to the referenced resource files.

4 / 5

Workflow Clarity

A clear 10-step canonical workflow with verification steps (run migration/query-plan/retrieval-quality commands, anti-pattern review, checklist sections), explicit exit criteria, and a failure-and-recovery section. Not 5 because the explicit validate -> fix -> re-validate feedback loop for migrations and destructive operations is delegated to checklist.md and error-playbook.md rather than stated inline, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

The body works as an overview with a well-annotated, one-level-deep References section where each file is scoped by purpose and condition ('check the sections relevant to the task before handoff', 'matching prior failure'). Not 5 because the 18-item guardrails list and deliverables detail are dense inline content that could be split out, and no bundle files are present to verify the referenced resources/*.md and ../_shared paths actually resolve.

4 / 5

Total

15

/

20

Passed

Description

66%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 specific and reasonably distinctive with concrete, naturally-phrased capabilities and an explicit boundary to a sibling skill. Its main weakness is the missing 'Use when...' trigger clause, which caps completeness and limits trigger-term coverage of common synonyms like SQL, ERD, and RAG.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about database design, schemas, ERDs, migrations, query tuning, or vector/RAG retrieval.'

Include natural synonyms and formats users actually say — SQL, NoSQL, table design, indexing, RAG — to broaden trigger-term coverage.

Optionally mention capacity planning or backup strategy to close the coverage gap with the body's capabilities.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Design schemas and migrations, tune queries, or plan vector retrieval and database operations') with clear verbs and objects. Not 5 because body capabilities like capacity estimation, backup strategy, and data governance are absent, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (schema design, migrations, query tuning, vector retrieval planning), but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'Application API implementation uses oma-backend' is only weak negative routing. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'schemas', 'migrations', 'tune queries', 'vector retrieval', 'database operations'. Not 5 because common variations like SQL, NoSQL, ERD, indexing, and RAG are missing; not 3 because coverage goes beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear database-design niche and explicitly delegates API implementation to oma-backend, reducing conflict risk. Not 5 because 'database operations' is a broad phrase that could still overlap with closely related backend/infra skills.

4 / 5

Total

15

/

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

Path

.claude-plugin/directory/skills/oma-db/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.