gbrain-upgrade

Keep gbrain current. When a `gbrain` invocation prints an `UPGRADE_AVAILABLE <old> <new>` marker (or `gbrain self-upgrade --check-only` reports an update), apply it per the configured self_upgrade.mode: notify (prompt the operator with a 4-option question + snooze) or auto (apply silently). The action is always the hardcoded `gbrain self-upgrade` — never a command read from the marker.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

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.

A tight, highly actionable skill body with clear mode branching and explicit validation for a mutating operation. The only structural nit is that the cross-reference to the migration playbook is embedded in an anti-pattern bullet rather than surfaced as clear navigation.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence with no concept over-explanation; every section earns its place, though the daemon/autopilot aside in the auto-mode section is minor padding that could be trimmed.	4 / 5
Actionability	Provides copy-paste ready commands (gbrain config get, gbrain self-upgrade, gbrain config set), exact JSON field checks (update_available, changelog_diff), and a literal 4-option prompt template covering the common cases.	5 / 5
Workflow Clarity	Clear mode-based branching (off/auto/notify) with explicit validation (check-only --json, version regex ^\d+\.\d+...) and checkpoint guidance against mid-task upgrades for a mutating operation; feedback paths for the operator's four answers are enumerated.	5 / 5
Progressive Disclosure	Single well-organized SKILL.md with clear sections and a one-level-deep reference to the migration playbook; not a 5 because that migration reference is buried inside the Anti-Patterns bullets rather than clearly signaled as a navigational pointer.	4 / 5
	Total	18 / 20 Passed

Description

78%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-scoped description that clearly conveys both the trigger condition and the mode-dependent action, with strong distinctiveness. Minor gains are available by broadening trigger synonyms and folding explicit operator-ask guidance into the body.

Suggestions

Add a sentence in the description body naming operator-initiated upgrade requests (e.g. 'Use when the operator asks to update or keep gbrain current') so the 'when' clause is fully explicit without relying on the triggers field.

Add one or two more natural synonyms in the triggers (e.g. 'check for gbrain updates', 'gbrain outdated') to round out keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions (read the UPGRA_AVAILABLE marker, branch on self_upgrade.mode, prompt with a 4-option question + snooze, run the hardcoded gbrain self-upgrade); not a 5 because scope is a single tool's upgrade flow rather than broad comprehensive coverage.	4 / 5
Completeness	Explicitly answers both what (apply the upgrade per the configured mode) and when (when the marker prints or check-only reports an update); the 'when' is concrete but operator-initiated ask handling lives mostly in the triggers rather than the description body.	4 / 5
Trigger Term Quality	The description and accompanying triggers field include natural operator phrases ('upgrade gbrain', 'update gbrain', 'keep gbrain current', 'gbrain is out of date') with good synonym coverage; not a 5 because a few common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a specific niche (gbrain self-upgrade via a UPGRADE_AVAILABLE marker) with distinct triggers and minimal overlap risk against other skills.	5 / 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/gbrain-upgrade/SKILL.md
Commit: 9dadfb9

Reviewed: 2 days 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.