CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-db

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

52

Quality

58%

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 ./.agents/skills/oma-db/SKILL.md

The canonical home for this skill is oma-db in first-fluke/oh-my-agent

SKILL.md
Quality
Evals
Security

Quality

Content

50%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-organized, domain-expert skill whose core value lies in its 17 concrete guardrails, but it is wrapped in redundant meta-framework scaffolding, its verification steps name checks without saying how to run them, and its heavy reliance on 11+ resource files that are missing from the bundle leaves both actionability and navigation incomplete.

Suggestions

Ship the referenced resource files (or remove the references): 11 `resources/*.md` and 4 `../_shared/core/*.md` paths are cited but absent, breaking every detailed lookup.

Make the VERIFY step executable — give the actual anti-pattern/integrity check commands or inline the checklist content instead of pointing to a missing resources/checklist.md.

Trim the process scaffolding (Scenes, SSL-primitive action table, Resource scope table) and the repeated vector-DB guidance down to a single section to cut token cost without losing substance.

DimensionReasoningScore

Conciseness

The 17 guardrails are dense and mostly earn their tokens, but the surrounding scaffolding ("Scheduling"/"Intent signature", the PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE "Scenes", and the invented "SSL primitive" action table) is process ceremony that adds no database knowledge, and key guidance is repeated across sections (vector-DB rules appear in Control-Flow, Transitions, guardrails 12–15, and Optimize). Not the 2 anchor's 'several unnecessary explanations' of known concepts, but clearly could be tightened.

3 / 5

Actionability

There is some genuinely concrete guidance — the canonical `rg` discovery commands are executable, and guardrails 16–17 (expand-contract steps, measure-explain-re-measure) are specific — but most sections give abstract direction ("Model entities/aggregates, integrity, transactions...") with no worked example, SQL snippet, or template, and the files that would carry the detail (resources/query-tuning.md, resources/migration-playbook.md, etc.) are not present in the bundle.

3 / 5

Workflow Clarity

The Entry → Scenes → Transitions → Failure/Recovery → Exit sequence is coherent, and a VERIFY step exists ("Run anti-pattern, integrity, consistency, and backup/recovery checks"), but the checkpoints are implicit and non-executable — no commands or procedures are given, and the self-check file (resources/checklist.md) is absent. Since this skill governs migrations on live tables, vague validation for destructive/batch operations holds it at the 3 anchor rather than 4.

3 / 5

Progressive Disclosure

The References section is well-labeled with one purpose per file and one-level-deep paths, but none of the 11 referenced `resources/*.md` or `../_shared/core/*.md` files exist in the bundle, so navigation is broken, and content that belongs in those files (guardrail details, deliverable templates) is inlined in a ~185-line SKILL.md. This sits between 'minimal structure/inlined content' (2) and 'good structure with minor gaps' (4).

3 / 5

Total

12

/

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 domain-specific, action-oriented description with good trigger keywords and a useful boundary handoff to oma-backend. Its main weakness is the absence of any explicit 'Use when...' trigger clause, which caps completeness and limits its discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions schemas, ERDs, migrations, query tuning, RAG/vector search, or database capacity and backup planning."

Replace the generic "plan vector retrieval and database operations" with concrete verbs/objects such as "plan vector indexes, chunking, and hybrid retrieval for RAG".

Include the natural synonyms users actually say (ERD, RAG, indexing, NoSQL) to round out trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Design schemas and migrations, tune queries, or plan vector retrieval" — each tied to the database domain. It falls short of the 5 anchor because "plan... database operations" is generic padding and coverage of the skill's actual scope (ERD, indexing, capacity, backup) is partial.

4 / 5

Completeness

The 'what' is clear (design schemas/migrations, tune queries, plan vector retrieval), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the second sentence "Application API implementation uses oma-backend" is a redirect boundary, not a trigger. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural keywords users would say are present: "schemas", "migrations", "tune queries", "vector retrieval", "database". A few common natural terms are missing (ERD, RAG, indexing, backup, NoSQL), which keeps it at the 'good coverage, a few natural terms missing' anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

The DB-design niche is distinct and the explicit handoff to oma-backend for "Application API implementation" reduces conflict risk with that sibling skill. Minor overlap risk remains with infrastructure/QA-type skills because "database operations" is broad, so it does not reach the 5 anchor's minimal-conflict bar.

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
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.