setup

Set up GBrain with auto-provision Supabase or PGLite, AGENTS.md injection, first import

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/setup/SKILL.md

Quality

Content

81%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.

The body is highly actionable and clearly sequenced with strong validation checkpoints and error recovery, scoring top marks on actionability and workflow clarity. Its main weakness is conciseness — the skill is long with some padded prose and inlined reference material — and progressive disclosure would benefit from splitting heavy reference sections into separate files.

Suggestions

Trim motivational and explanatory prose (e.g. 'This is the magical moment', 'Stopping here is like installing a phone and never adding contacts') and consolidate repeated GitHub URL pointers to tighten conciseness.

Move the large Topology 2/3 wiring recipes and the full self-upgrade marker block into reference files, keeping SKILL.md as an overview with one-level-deep pointers.

The Phase A.5 topology decision tree is essential but long; summarize the three shapes inline and link to topologies.md for the per-shape recipes to reduce vertical density.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it is long (~620 lines) with padded prose, repeated GitHub URL pointers, and motivational lines ('This is the magical moment') that could be trimmed.	3 / 5
Actionability	Fully executable guidance throughout — copy-paste commands like 'gbrain init --non-interactive --url ...', 'gbrain doctor --json', discovery/import bash blocks, and concrete JSON config objects cover the common cases.	5 / 5
Workflow Clarity	Phases A–J are explicitly sequenced with validation checkpoints ('Verify: gbrain doctor --json', 'Sync ran is not the same as sync worked'), an error-recovery table, and anti-patterns including feedback loops for the destructive/batch import and migration steps.	5 / 5
Progressive Disclosure	No local bundle files exist, but external references are one level deep and well-signaled ('Read https://github.com/.../topologies.md for the full picture'), and content is organized into clear phases; slightly below 5 because substantial reference-style material (full topology recipes, self-upgrade blocks) is inlined rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

58%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.

The description concretely states what the skill does but omits any 'Use when...' trigger guidance, which caps completeness and leaves the when implicit. Keywords are relevant but lack natural synonyms, so trigger term quality is mid-range.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when the user asks to set up, install, or initialize GBrain (e.g. "set up gbrain", "initialize brain", "gbrain setup").'

Broaden natural-language trigger terms with synonyms users actually say ("install brain", "connect GBrain", "brain setup") to lift trigger term quality.

Mention the verification/health-check outcome ("verified via gbrain doctor") to round out capability coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (GBrain) plus three concrete actions — 'auto-provision Supabase or PGLite', 'AGENTS.md injection', 'first import' — with only minor coverage gaps (no mention of live sync, autopilot, or verification).	4 / 5
Completeness	There is a clear 'what' (set up GBrain with the listed sub-actions) but no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Set up GBrain', 'Supabase', 'PGLite', 'first import') but misses common natural variations a user might say (e.g. 'install', 'brain', 'connect') and the bare product name alone is narrow.	3 / 5
Distinctiveness Conflict Risk	The GBrain-specific scope ('AGENTS.md injection', 'auto-provision Supabase or PGLite') carves a clear niche with minimal overlap risk against other skills; only slightly below a fully distinct 5 because the bare phrase 'Set up' is generic.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (635 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: garrytan/gbrain
Path: skills/setup/SKILL.md
Commit: 055ac6c

Reviewed: 37 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.