setup

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

Quality

72%

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

77%

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 with a clearly sequenced, well-validated multi-phase workflow, but it is long and monolithic with redundant explanations and inline detail that belongs in referenced files. Tightening redundancy and splitting sub-content into referenced docs would improve conciseness and progressive disclosure.

Suggestions

De-duplicate the Transaction pooler/IPv6 guidance: state it once in 'How GBrain connects' and cross-reference from Phase A, Phase B, Phase H, and Anti-Patterns.

Move detailed sub-content (Phase A.5 topology selection, the self-upgrade marker protocol, the brain-first lookup tables) into referenced docs and keep SKILL.md a leaner overview with well-signaled links.

Trim the 'Why Supabase' section to decision-relevant essentials, removing the marketing-style bullet points.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable GBrain-specific guidance rather than basic concept explanation, but at ~580 lines it is verbose: the Transaction pooler/IPv6 point is repeated across 'How GBrain connects', Phase A, Phase B, Phase H, and Anti-Patterns, and the 'Why Supabase' section reads as marketing. Not a 3 because not every token earns its place; not a 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	Provides fully executable bash throughout (e.g. 'gbrain init --non-interactive --url "postgresql://…"', 'nohup gbrain import <dir> --no-embed --workers 4', the environment discovery script) with specific flags and copy-paste-ready commands. Not a 2 because the code is real and complete, not pseudocode.	3 / 3
Workflow Clarity	Sequenced phases A–J with explicit validation checkpoints ('Verify: gbrain doctor --json', 'Prove search works', 'Verify sync works', Phase I runbook) and clear feedback loops (Error Recovery symptom→fix table, doctor-first protocol). Not a 2 because validation and retry loops are present for the database/import operations.	3 / 3
Progressive Disclosure	Referenced docs (docs/architecture/topologies.md, docs/GBRAIN_SKILLPACK.md, docs/GBRAIN_VERIFY.md, etc.) are one-level-deep and well-signaled, but SKILL.md is a monolithic ~580-line runbook with substantial detail inlined (topology selection, self-upgrade marker protocol, lookup tables) that could be split out; no bundle files are present. Not a 3 because the file is not a lean overview pointing to detailed materials.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and occupies a clear, distinct niche, but it omits an explicit 'Use when…' trigger clause and only partially covers natural trigger phrasings within the description text itself. Adding explicit when-guidance and broader trigger variations would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when…' clause to the description, e.g. 'Use when the user asks to set up, initialize, or configure GBrain, or mentions provisioning a Supabase/PGLite knowledge brain.'

Broaden natural trigger terms inside the description (e.g. 'initialize brain', 'configure gbrain', 'knowledge base setup') instead of relying solely on the separate triggers field.

Keep the third-person/imperative voice but ensure the description alone communicates both what and when without depending on the triggers field.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Set up GBrain', 'auto-provision Supabase or PGLite', 'AGENTS.md injection', 'first import'), matching the anchor for multiple specific concrete actions. It is not a 2 because the actions are comprehensive and domain-specific rather than partial.	3 / 3
Completeness	Clearly states what the skill does, but the description itself lacks an explicit 'Use when…' trigger clause (the when guidance lives only in the separate triggers field), so per the guideline completeness is capped at 2. Not a 1 because the what is clearly and specifically stated.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('Set up GBrain', 'Supabase', 'PGLite') but offers no 'Use when…' expansion or common variations, matching 'some relevant keywords but missing common variations'. Not a 3 because coverage of natural phrasings is thin.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (GBrain setup with Supabase/PGLite provisioning) with distinct triggers, making it unlikely to fire for unrelated skills. Not a 2 because the scope is sharply scoped rather than broadly overlapping.	3 / 3
	Total	10 / 12 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 (580 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: 3fafb69

Reviewed: about 19 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.