schema-unify

Migrate a brain from gbrain-base (or any pack) to gbrain-base-v2's 14-canonical-type taxonomy via gbrain onboard --check + the unify-types Minion handler. Collapses 94 noisy types to 15 canonical with subtypes, alias rows, and link rows. Triggers when an agent notices pack_upgrade_available, type_proliferation, or asks "what is the canonical taxonomy / how do I clean up my page types".

Quality

90%

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

Quality

Content

83%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.

Highly actionable and well-sequenced migration playbook with strong validation and rollback guidance. The main weakness is structure: with no reference files, a lot of peripheral detail (output formats, duplicate anti-patterns sections, contract) is inlined in a single long document rather than progressively disclosed.

Suggestions

Move the Output Format block and Contract section into a reference file (e.g. references/unify-types-contract.md) and link to it from the body to reduce inline bulk.

Merge the duplicate 'Anti-patterns' and 'Anti-Patterns' sections into one; the repeated manual_only and mapping_rules guidance adds length without new signal.

Add a short 'Quick start' summary at the top (the 3 core commands) before the phase-by-phase detail so the common path is skimmable.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes competence (terse mental model, copy-paste bash, decision tree); a few sections restate the same caveat (e.g. --follow/PGLite and the manual_only warning appear in multiple places), which is mild padding.	4 / 5
Actionability	Copy-paste-ready bash commands with exact flags and JSON params, concrete expected outputs, explicit rollback SQL, and a decision tree mapping situations to commands — fully executable.	5 / 5
Workflow Clarity	Five explicit phases (Discovery→Preview→Apply→Verify→Post-migration) with validation checkpoints at each gate, expected ok/findings, and a rollback section; the destructive/batch operation has verification steps so it clears the workflow cap.	5 / 5
Progressive Disclosure	No bundle files exist; the body inlines a large amount of detail (full output-format samples, celebration summary, contract, two anti-patterns sections) that is monolithic rather than split into referenced files, and external links are only URLs at the end.	3 / 5
	Total	17 / 20 Passed

Description

96%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, specific description that clearly states what the skill does and when it fires, with concrete actions and natural trigger phrases. Only marginal: it is tightly scoped to a single product's internal taxonomy, so distinctiveness is high but not perfectly isolated.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: migrate a brain to a 14-canonical-type taxonomy, collapse 94 types to 15 canonical with subtypes/alias rows/link rows, via specific tools (gbrain onboard --check, unify-types handler).	5 / 5
Completeness	Explicitly answers both 'what' (migrate brain, collapse 94→15 types with subtypes/alias/link rows) and 'when' ('Triggers when an agent notices...') with concrete trigger guidance.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('clean up my page types', 'what is the canonical taxonomy') plus technical finding names (pack_upgrade_available, type_proliferation) with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Highly specific niche (gbrain-base→v2 taxonomy migration) with distinct triggers; minor overlap risk only with other gbrain schema skills, not a 5 because the niche is narrow but not uniquely disambiguated from neighboring gbrain ops.	4 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: skills/schema-unify/SKILL.md
Commit: 055ac6c

Reviewed: about 2 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.