brain-taxonomist

Filing gate for ALL brain writes. Consulted before creating any new brain page to determine the correct path. Reads the ACTIVE schema pack via `gbrain schema show --json` — no hardcoded directory table. Also runs periodic taxonomy drift detection via `gbrain schema review-orphans`.

Quality

73%

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 ./skills/brain-taxonomist/SKILL.md

Quality

Content

63%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 clear, actionable gating skill with a strong decision protocol and validation feedback loops. It is weakest on progressive disclosure (no reference files despite splittable content) and on conciseness, since the no-hardcoded-table principle is restated across several sections.

Suggestions

Split the enumerated book categories and gbrain-recommended pack contents into a references/ file (e.g., references/recommended-pack.md) and link to it, removing the duplication from the body.

Consolidate the repeated 'no hardcoded directory table' rationale into one section (Hard Rules or Anti-Patterns) and reference it from the others to cut redundant tokens.

Add a per-item validation checkpoint to the bulk-import branch of 'When to Consult' to strengthen the batch-operation feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-sectioned, but it re-explains the no-hardcoded-table principle repeatedly across 'Critical', 'Contract', 'Anti-Patterns', and 'Hard Rules', and restates the gbrain-recommended pack contents and book categories that arguably belong in the referenced pack rather than the skill body.	3 / 5
Actionability	Provides concrete executable commands ('gbrain schema show --json \| jq ...', 'gbrain schema review-orphans --json', 'gbrain doctor --json'), a worked Step 1-5 protocol, and a copy-paste output format; minor gaps are that the book category list is enumerated inline rather than derived, and slug construction is described but not scripted.	4 / 5
Workflow Clarity	A clear five-step decision protocol with an explicit Step 5 validation checklist and feedback loop (no matching type → signal to EIIRP Phase 3 rather than closest-fit), plus drift-detection checkpoints; the destructive/batch validation cap is avoided because filing paths are validated before writing, though batch imports lack a per-item validation checkpoint.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, but it is a single-file monolith with no bundle references despite content that could be split (book taxonomy, the directory-type enumeration, EIIRP integration details); no references/ scripts/ or assets/ bundles exist, so cross-file navigation is not exercised.	3 / 5
	Total	14 / 20 Passed

Description

82%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 specific, well-triggered description with strong natural keyword coverage and a clear niche. Its main weakness is that the 'when to use' guidance relies on the triggers array and body rather than an explicit 'Use when...' clause inside the description field itself.

Suggestions

Add an explicit 'Use when...' clause to the description field itself (e.g., 'Use when creating or refiling brain pages, or running a taxonomy drift check.') so the when-guidance is self-contained.

Tighten the 'what' to list the core actions more compactly (determine filing path, detect taxonomy drift) to reduce reliance on the tool-name sentence for specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (brain writes/filing) and concrete actions ('determine the correct path', 'Consulted before creating any new brain page', 'runs periodic taxonomy drift detection via gbrain schema review-orphans'), with minor gaps in coverage breadth.	4 / 5
Completeness	It clearly answers 'what' (filing gate, reads ACTIVE schema pack, runs drift detection) and 'when' via the MANDATORY consult list in the body, but the description field itself has no inline 'Use when...' clause — the when-guidance lives in triggers/body rather than the description text, so it is not fully explicit at the description level.	4 / 5
Trigger Term Quality	The triggers array includes comprehensive natural phrasings users would say ('where does this brain page go', 'file this in the brain', 'refile brain page', 'create brain page', 'which directory does this page go') plus synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche (brain-page taxonomy/filing gate) with distinct triggers tied to 'brain page' and 'directory', giving minimal conflict risk; minor overlap risk with sibling brain skills like ingest/book-mirror that also touch filing.	4 / 5
	Total	17 / 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/brain-taxonomist/SKILL.md
Commit: 7b7921d

Reviewed: ~12 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.