maintain

Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

71%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.

Highly actionable body dense with executable gbrain commands and a clear two-path workflow with validation. Weaker on conciseness (inline version/time-sensitive detail) and progressive disclosure (monolithic single-file structure with no bundle references).

Suggestions

Move the dense dream-cycle configuration reference (config keys, defaults, mode dials) into a references/ file and keep only the invocation patterns inline.

Consolidate version-specific notes (v0.23, v0.36.4.0, v0.11.1+, v1.1 deferrals) into a single 'Version notes / deprecated' section so time-sensitive detail does not interrupt the main workflow.

Add explicit per-dimension validation checkpoints to the manual path (e.g. re-run 'gbrain health' after each dimension) to match the autonomous path's rigor.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance for a custom tool, but the dense dream-cycle section and inline version notes (v0.23, v0.36.4.0, v0.11.1+, 'Auto-commit deferred to v1.1') could be tightened; time-sensitive version detail is mixed into the main flow.	3 / 5
Actionability	Pervasive copy-paste-ready commands (e.g. 'gbrain doctor --remediate --yes --target-score 90 --max-usd 5', 'gbrain extract links --dir ~/brain') with flags and expected outputs cover the common cases fully.	5 / 5
Workflow Clarity	Clear autonomous-vs-manual sequencing with validation signals (autopilot exit codes, 'Check gbrain health before and after', cost-cap bail conditions); minor gaps in explicit per-dimension checkpoints in the manual walk.	4 / 5
Progressive Disclosure	Well-sectioned but monolithic: dream-cycle, heartbeat, and benchmark detail that could live in separate reference files are inlined, and the referenced paths (skills/_brain-filing-rules.md, docs/guides/minions-fix.md) point outside a bundle that contains no reference files.	3 / 5
	Total	15 / 20 Passed

Description

88%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 concise, third-person description that names a comprehensive set of concrete maintenance actions and pairs them with an explicit 'Use when' trigger clause. Trigger-term synonym coverage is the weakest aspect but still strong.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Clearly answers both what ('Brain health checks: ...') and when ('Use when asked to check brain health, run maintenance, or audit quality') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases 'brain health', 'run maintenance', 'audit quality' match what users would say, but synonym/extension coverage is limited relative to the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The 'brain health checks' niche is fairly distinct with specific triggers, with only minor overlap risk against generic maintenance/audit skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: about 2 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.