oma-db

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/oma-db/SKILL.md

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.

A well-structured, instruction-dense skill body with strong validation checkpoints and appropriately externalized detail guides. Its main costs are redundant parallel workflow sections, repeated resource listings, and unverifiable (absent) bundle files referenced throughout.

Suggestions

Collapse the three overlapping workflow framings (Scenes, Structural Flow, Default Workflow) into one canonical sequence to remove redundancy.

List the resources/ files once (References only) and reference that list from Dependencies and Tools instead of repeating it.

Add one inline concrete example (e.g. a minimal schema-doc snippet or sample expand-contract migration) to ground the abstract ACT/REASON scene descriptions.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative with no concept-explaining fluff, but it carries clear redundancy: the PREPARE–ACQUIRE–...–FINALIZE "Scenes", the Entry/Transitions flow, and the Explore/Design/Optimize "Default Workflow" restate the same process three times, and the resource list is repeated in Dependencies, Tools, and References. Not 4 because several sections could be cut or merged without losing information.	3 / 5
Actionability	Provides executable commands (the rg file/grep invocations), a concrete "run the project's migration, query-plan, or retrieval-quality commands" step, and highly specific instructions (expand-contract with dual-write + backfill + soak window; measure→explain→optimize→re-measure). Not 5 because several scene/action descriptions remain abstract ("Model entities/aggregates", "Produce schema docs") with no inline example or template snippet.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with a VERIFY scene, a pre-handoff self-check (resources/checklist.md), a failure-and-recovery section, and explicit validation loops for destructive operations (verified read switch, re-measure), so the destructive-operation cap does not apply. Not 5 because three overlapping workflow framings (Scenes, Structural Flow, Default Workflow) leave the canonical path slightly ambiguous.	4 / 5
Progressive Disclosure	The References section is well-signaled with one-line purpose labels (e.g. "Self-check (run before handoff): resources/checklist.md") and references are one level deep, with detailed guides split into separate files. Not 5 because no bundle files were present to verify the referenced resources/*.md and ../_shared files actually exist, and the resource list is duplicated across Dependencies, Tools and instruments, and References.	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.

A concise, mostly concrete description with a clear database niche and a helpful routing boundary to oma-backend. Its main weakness is the absence of explicit "Use when..." trigger guidance and of common synonyms (SQL, ERD, NoSQL, RAG) that would improve both completeness and trigger matching.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions databases, schemas, ERDs, SQL/NoSQL modeling, migrations, query tuning, or vector/RAG retrieval."

Broaden natural trigger terms to include SQL, ERD, table design, NoSQL, indexing, and RAG, which the body already treats as intent signatures.

Optionally mention one or two more capabilities from the body (e.g. capacity estimation or backup/recovery planning) to close the coverage gap.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Design schemas and migrations, tune queries, or plan vector retrieval and database operations" — but coverage is incomplete: the body reveals additional core duties (capacity estimation, backup strategy, glossary/standards, anti-pattern review) absent from the description.	4 / 5
Completeness	The "what" is clear (design schemas/migrations, tune queries, plan vector retrieval and DB operations) but there is no "Use when..." clause or equivalent trigger guidance; the oma-backend routing sentence is a boundary hint, not usage triggers. Per the rubric, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say — "schemas", "migrations", "tune queries", "vector retrieval", "database" — but misses common variations like SQL, ERD, NoSQL, table design, or RAG that the body itself lists as intent signatures.	4 / 5
Distinctiveness Conflict Risk	The database/data-modeling niche is distinct and the explicit boundary "Application API implementation uses oma-backend" reduces mis-routing; it is not 5 because it can still overlap with backend/infra skills for general database-adjacent requests.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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: skills/oma-db/SKILL.md
Commit: ce19702

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.