skillpack-check

Run `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations --list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron) can see at a glance whether the skillpack needs attention. Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off (jobs not running, brain not updating, autopilot silent).

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

76%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 highly actionable, well-structured body with concrete commands and exit-code semantics, weakened only by a batch action loop that skips per-step validation and a duplicated section heading.

Suggestions

Add per-command validation to the actions[] loop (e.g. check each command's exit status and stop/escalate on failure) so the batch workflow can score above the cap of 3.

Remove the duplicate '## Output Format' heading (lines 85 and 119) by merging the prose about not writing files into a single section.

Consider moving the full JSON example into a reference file and keeping only the key fields inline, to tighten the overview further.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence (no explaining what JSON or cron is), but the duplicated '## Output Format' heading and slight restatement of the summary-first rule are trimmable redundancy.	4 / 5
Actionability	Provides a copy-paste bash loop, concrete action entries with meanings, explicit exit-code semantics, and a numbered troubleshooting sequence for exit 2 — fully executable across the common cases.	5 / 5
Workflow Clarity	The run -> branch-on-exit-code -> execute actions[] sequence is clear and includes partial-status handling, but the batch `for cmd in actions; eval` loop lacks per-command validation, and the rubric caps batch operations without verification at 3.	3 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references (skills/migrations/v0.11.0.md, docs/guides/minions-fix.md) and no bundle nesting; the duplicate Output Format heading is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

87%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 strong, third-person description that pairs a concrete statement of behavior with an explicit 'Use when' clause and natural trigger phrases. It is specific to the gbrain product and unlikely to collide with other skills.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('produce an agent-readable JSON health report', 'Wraps `gbrain doctor` + `gbrain apply-migrations --list`') with specific commands and output, but coverage is narrow for a single-purpose wrapper.	4 / 5
Completeness	Explicitly answers both what (produce JSON health report wrapping doctor + migrations) and when (a clear 'Use when...' clause with concrete trigger scenarios), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('is gbrain healthy?', morning cron check, 'jobs not running, brain not updating') with good synonym coverage, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (gbrain install health) with distinct, product-specific triggers, making conflict with other skills unlikely.	5 / 5
	Total	18 / 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/skillpack-check/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.