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

85%

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

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 runbook for a single-command health check: executable commands, explicit exit-code branching, and a safety framing around proposed vs. authorized actions. The only real flaws are organizational — a duplicated 'Output Format' heading, some repetition of the approval rule, and inline content that could be split out.

Dimension	Reasoning	Score
Conciseness	Efficient and operational — exit-code semantics, the actions[] catalog, and the contract are things Claude cannot know, and no generic concepts are explained. Not 5 because the '## Output Format' heading appears twice (once for the JSON example, once for reporting format), the separate-approval point is repeated three times, and version-pinned details ('0.11.1', '0.11.0') sit outside any deprecation/old-patterns section.	4 / 5
Actionability	Fully executable throughout: concrete commands (`gbrain skillpack-check --quiet`, `printf '%s\n' "$REPORT" \| jq -r '.actions[]'`, `which gbrain`, `gbrain --version`), precise exit-code semantics, and a complete copy-paste-ready JSON output example covering the common cases.	5 / 5
Workflow Clarity	Clear sequence with explicit validation checkpoints: the exit code gates all branches (0 healthy / 1 action needed / 2 undetermined), and the exit-2 path has a three-step triage checklist with feedback for recovery. The skill is report-only, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist, and the body is well-sectioned with a clearly signaled one-level '## Related' section pointing to the migrations manual and a troubleshooting guide. Not 5 because the ~117-line body inlines the 20-line JSON example and the action catalog that could live in a reference file, and the duplicate 'Output Format' heading is a navigation gap.	4 / 5
	Total	18 / 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 strong, niche description that clearly states what the command does and when to use it, with natural trigger phrases. Its only deductions are a second-person parenthetical ('your OpenClaw's morning-briefing') and slightly thin action enumeration compared to the top specificity anchor.

Suggestions

Rewrite the parenthetical in third person, e.g. 'so a host agent (OpenClaw morning-briefing or any cron) can see at a glance', to remove the second-person voice penalty.

Briefly enumerate what the report contains (healthy flag, summary, proposed actions, doctor checks, migration counts) to move specificity from '1-2 concrete actions' toward comprehensive coverage.

Fold one or two natural synonyms from the triggers field (e.g. 'is the brain working', 'gbrain health') into the description text itself for fuller trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Run `gbrain skillpack-check` to produce an agent-readable JSON health report', 'Wraps `gbrain doctor` + `gbrain apply-migrations --list`'), which would anchor at 4, but the second-person phrase 'your OpenClaw's morning-briefing' triggers the rubric's third-person-voice penalty of 1. Not 2 because the domain and multiple specific actions are clearly stated, unlike 'Processes PDF files'.	3 / 5
Completeness	Explicitly answers both what ('produce an agent-readable JSON health report', 'Wraps `gbrain doctor` + `gbrain apply-migrations --list`') and when ('Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-phrase coverage: 'is gbrain healthy?', 'morning check', 'jobs not running, brain not updating, autopilot silent'. Not 5 because comprehensive synonyms (e.g. 'is the brain working', 'gbrain health') appear only in the separate triggers field, not in the description itself.	4 / 5
Distinctiveness Conflict Risk	Clear niche with gbrain-specific triggers ('gbrain skillpack-check', 'is gbrain healthy?'); no plausible overlap with other skills, minimal conflict risk.	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/skillpack-check/SKILL.md
Commit: e78f1c3

Reviewed: 5 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.