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

81%

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

77%

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

The content is highly actionable with a well-sequenced, validated workflow and copy-paste commands. It is held back by mild output-section repetition, inline version-specific notes, and a monolithic structure that inlines reference-grade detail rather than splitting it out.

Suggestions

Move the full Output Format JSON shapes and the Failure modes table into a reference file, keeping the body as a lean overview that links to them.

Deduplicate the 'Outputs' section against the Contract's Outputs bullet so the pack-file/audit-row/backfill facts appear once.

Relocate version-sensitive notes ('v0.40.6.0', 'v0.40.6') into a dedicated 'Version notes' or deprecated section rather than inline in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no concept tutorials), but the 'Outputs' section repeats the Contract's outputs, and inline time-sensitive version notes ('v0.40.6.0', 'v0.40.6') are not isolated in a deprecated section, so it is mostly efficient rather than fully tight.	2 / 3
Actionability	Every phase gives copy-paste-ready CLI commands plus real JSON/JSONL examples and exact error codes with remediation commands, matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	A clear 7-phase sequence (Brain→Assess→Propose→Apply→Sync→Verify→Commit) includes explicit validation checkpoints (lint --with-db, dry-run before --apply, coverage ≥95% verify), avoiding the score-2 cap for missing validation on batch operations.	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep (conventions/docs links with clear labels), but the body is a long monolithic ~250-line document that inlines heavy detail (full Output Format JSON, Failure modes) that could live in separate reference files, fitting the score-2 anchor.	2 / 3
	Total	10 / 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.

The description is specific, complete, and distinct, with an explicit trigger clause and third-person voice. Its only weakness is trigger-term naturalness — the language is somewhat technical and missing plain user phrasings.

Suggestions

Soften trigger phrasing toward terms a user would naturally say (e.g., 'add a type for my notes', 'find pages without a type') alongside the technical ones.

Consider dropping or glossing internal jargon like 'page.type', 'corpus scans', and 'typed entities' in favor of plainer equivalents.

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' — matching the score-3 anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Explicitly states what it does (the four actions) and when via the explicit 'Triggers when an agent notices...' clause, satisfying the score-3 anchor for both what and when.	3 / 3
Trigger Term Quality	Relevant trigger concepts appear ('untyped pages', 'custom domains needing typed entities', 'wants to see what types the pack declares') but the phrasing leans technical ('schema pack', 'corpus scans', 'typed entities', 'page.type') and misses more natural user variations, fitting the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	It carves a clear schema-authoring niche ('custom domains needing typed entities (researcher, contract, deposition)') distinct from adjacent filing/routing skills, matching the score-3 clear-niche anchor.	3 / 3
	Total	11 / 12 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: 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/schema-author/SKILL.md
Commit: 3fafb69

Reviewed: about 19 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.