aiox-data-engineer

Activate Dara (data-engineer) for Database Architect & Operations Engineer. Use for database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modeling, operations, and monitoring

Quality

56%

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 ./.claude/skills/AIOX/agents/data-engineer/SKILL.md

Quality

Content

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is an action-rich persona definition but is delivered as a monolithic, heavily duplicated inline YAML that inflates token cost. Workflow scaffolding is present but undermined by stale command references and a lack of progressive disclosure.

Suggestions

Move the large YAML agent definition into a separate bundled reference file and keep SKILL.md as a lean overview with one-level-deep, clearly signaled links.

Deduplicate the command list — keep it in one canonical location and reference it elsewhere instead of repeating the table, YAML block, and Quick Commands verbatim.

Update the 'Typical Workflow' to use current command names (*security-audit, *analyze-performance) instead of the deprecated *rls-audit and *explain.

Dimension	Reasoning	Score
Conciseness	The body embeds a ~400-line inline YAML agent-definition block and repeats the command list three times (Star Commands table, commands YAML, Quick Commands), plus persona/emoji/zodiac padding Claude does not need. It is not 2 because the verbosity is pervasive and structural, not a few tighten-able spots.	1 / 3
Actionability	Concrete, copy-paste commands are listed (e.g., '*apply-migration {path}', '~/.local/bin/coderabbit --prompt-only -t uncommitted'), but the actual task workflows live in external dependency files (db-apply-migration.md, security-audit.md) that are only named, not shown. It is not 3 because key execution detail is deferred and not inline, and not 1 because many specific commands and one full workflow are executable.	2 / 3
Workflow Clarity	A migration sequence with validation checkpoints exists (snapshot baseline → dry-run → apply → smoke-test) and the CodeRabbit workflow has explicit gates, but the 'Typical Workflow' references deprecated command names ('rls-audit', 'explain') absent from the current command table. It is not 3 because that inconsistency undermines clarity, and not 1 because real validation steps are present for destructive operations.	2 / 3
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist, and the entire agent-definition YAML is inlined as a monolithic block rather than split into navigable, well-signaled references. It is not 2 because content that clearly should be separate is inline with no real file-level navigation.	1 / 3
	Total	6 / 12 Passed

Description

85%

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, specific description with explicit what/when guidance and a distinct database niche. Its main weakness is trigger phrasing built around persona activation rather than the natural task language users would actually utter.

Suggestions

Add natural task-based triggers users would say (e.g., 'when the user asks to design a database schema, write a migration, or optimize a slow query').

Fix the run-on 'monitoring Trigger' so the Use-for clause and Trigger clause are cleanly separated by a period.

Replace awkward phrasing like 'asks to data-engineer' with natural verbs such as 'asks to design or manage a database'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modeling, operations, and monitoring' — rather than vague language. It is not a 2 because the action list is comprehensive and domain-specific, not partial.	3 / 3
Completeness	Explicitly answers what ('Use for database design, schema architecture...') and when ('Trigger when user asks to data-engineer, or says...'). It is not 2 because both the what and the when are present and explicit, despite a missing-space typo ('monitoring Trigger').	3 / 3
Trigger Term Quality	Triggers are persona-invocation phrases ('activate data-engineer', 'switch to data-engineer', '@data-engineer', 'asks to data-engineer') rather than natural task terms a user would say like 'design my schema' or 'optimize this query'. It is not 3 because common natural variations are missing, and not 1 because several relevant keywords do appear.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear database/Supabase niche with distinct persona-activation triggers, making it unlikely to fire for non-database skills. It is not 2 because the scope is narrowly database-lifecycle specific rather than broadly overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .claude/skills/AIOX/agents/data-engineer/SKILL.md
Commit: 0b32b68

Reviewed: about 14 hours 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.