gbrain-advisor

Proactive "make the most of gbrain" coaching. Runs `gbrain advisor` on a cadence and pings the user with the top high-leverage actions for their brain: version drift, pending migrations, stalled jobs, low embed coverage, setup smells, and uninstalled brain skills. Read-only; always asks before fixing.

Quality

91%

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

100%

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

A well-crafted, lean, actionable skill body: concrete commands, a sequenced workflow with validation, and clear sectioning. It appropriately defers detail to a convention file rather than inlining it.

Dimension	Reasoning	Score
Conciseness	Lean and purposeful — a tight Contract, scoped commands, and an output template with no padding or re-explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Gives fully executable commands (`gbrain advisor --json`, `gbrain advisor --apply <dispatch_id>`), the JSON payload shape, per-finding fields, and copy-paste-ready output examples.	3 / 3
Workflow Clarity	The "What to do with the findings" section is a clearly sequenced 1–5 workflow with an explicit validation checkpoint (exit code severity gate) and a hard confirm-before-fix rule for the destructive case.	3 / 3
Progressive Disclosure	Well-organized into clearly signaled sections (Contract, When/How to run, Findings, Cron recipe, Output Format, Anti-Patterns); the only external reference (brain-first.md convention) is one level deep and clearly flagged.	3 / 3
	Total	12 / 12 Passed

Description

82%

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, distinctive description with concrete actions and natural trigger language. It is held back only by an implicit rather than explicit "Use when..." usage trigger.

Suggestions

Add an explicit "Use when..." clause naming the user situations that should invoke this skill (e.g. "Use when the user asks how to get more out of their brain, wants a brain checkup, or is unsure their brain is set up right").

Surface the cadence explicitly as a trigger cue so Claude knows it may fire proactively, not just on demand.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions/signal types — "version drift, pending migrations, stalled jobs, low embed coverage, setup smells, and uninstalled brain skills" plus "Runs `gbrain advisor` on a cadence and pings the user with the top high-leverage actions".	3 / 3
Completeness	Clearly states what it does (runs advisor, pings top actions, read-only) but the "when" is only implied ("Proactive", "on a cadence") with no explicit "Use when..." clause, which caps completeness per the guideline.	2 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — "make the most of gbrain", "set up right", "weekly brain checkup" — matching the trigger field's plain-language terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche ("gbrain advisor") with gbrain-specific triggers unlikely to overlap with other skills.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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

Reviewed: about 20 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.