schema-author

Evolve your brain's schema pack. Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the pack declares.

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

88%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 highly actionable and workflow-driven with strong validation feedback loops, scoring at the top of actionability and workflow clarity. Conciseness and progressive disclosure sit just below perfect due to some redundant inline JSON/contract detail.

Suggestions

Consolidate the Outputs and Contract sections, which overlap heavily, to remove redundant statements about audit rows and backfill effects.

Move the extended JSON output-format examples (per-mutation, per-batch, stats, sync dry-run) into a reference file linked from a brief inline summary, reducing body length while preserving the executable commands.

Consider bundling the conventions into a references/ directory so progressive disclosure is backed by actual local files rather than only external links.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable commands and little basic-concept padding, but the Output Format JSON examples and the Contract/Outputs sections partially duplicate information and could be trimmed.	4 / 5
Actionability	Provides fully executable CLI commands, concrete JSONL mutation batches, and copy-paste-ready JSON output examples covering the common cases.	5 / 5
Workflow Clarity	A clear 7-phase sequence with explicit validation checkpoints — 'lint --with-db' before sync, dry-run before 'sync --apply', coverage ≥95% verification — plus failure-mode recovery loops for batch/destructive operations.	5 / 5
Progressive Disclosure	Clearly signals one-level-deep references (conventions/brain-first.md, schema-evolution.md, docs tutorial links), but inlines sizable JSON output and contract detail that could live in separate files; no bundle files are present to offload content.	4 / 5
	Total	18 / 20 Passed

Description

92%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 strong across all dimensions, clearly stating concrete capabilities and explicit trigger conditions with concrete domain examples. Minor abstractness in a couple of trigger phrases keeps trigger term quality just below perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ('Evolve your brain's schema pack. Add page types...') and when ('Triggers when an agent notices untyped pages... or wants to see what types the pack declares') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger terms like 'untyped pages' and concrete domains ('researcher, contract, deposition'), though some phrasing ('custom domains needing typed entities') is more abstract than what a user would naturally say.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche ('Evolve your brain's schema pack', 'backfill page.type') that is distinct from adjacent filing/querying skills, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

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

Reviewed: 39 minutes 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.