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

82%

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete executable commands and validation checkpoints throughout, but it is held back by verbosity in the Dream-cycle internals, time-sensitive version notes not isolated in a deprecated section, and external doc references that are not clearly signaled as part of a bundle. Tightening those areas would lift the middle dimensions.

Suggestions

Move the Dream-cycle internal mechanics (subagent fan-out, slug-collection rationale, trust-boundary details) into a separate reference file and keep SKILL.md to the invocation patterns and quality bar.

Isolate time-sensitive version notes (v0.23, v0.11.0, v0.11.1+) into an explicit 'Version / migration notes' or 'Deprecated' section so they don't pad the main flow.

Add an explicit validate→fix→retry feedback loop for the Dream 8-phase pipeline and relocate the stray timeline-parsing paragraph (line 190) under Timeline extraction where it belongs.

Dimension	Reasoning	Score
Conciseness	Concrete commands keep most sections efficient, but the Dream cycle section over-explains internal orchestration mechanics (subagent fan-out, slug-collection rationale) and inline time-sensitive version notes (v0.23, v0.11.1+) are not isolated in a deprecated section. It is mostly efficient but could be tightened, so not a 3 and clearly above the verbose 1 anchor.	2 / 3
Actionability	The body is full of copy-paste-ready executable `gbrain` commands with real flags, JSON examples, and specific thresholds (e.g. "--target-score 90 --max-usd 5"), matching the fully-executable top anchor.	3 / 3
Workflow Clarity	Phases and the manual path are sequenced with validation checkpoints (RLS check, `gbrain doctor --json`), but the Dream cycle's 8-phase pipeline has no explicit validate→fix→retry feedback loop and a stray timeline-parsing paragraph (line 190) is misplaced mid-section. It is above the unclear 1 anchor but lacks the explicit feedback loops of a 3.	2 / 3
Progressive Disclosure	Sections are well-organized, but content that could live elsewhere (full Dream-cycle internals) is inline and external references (`docs/guides/minions-fix.md`, `skills/migrations/v0.11.0.md`, `skills/_brain-filing-rules.md`) are referenced without a bundle directory existing or being clearly signaled. This is better than a monolithic 1 but not the clean one-level-deep structure of a 3.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, trigger-rich, complete, and clearly differentiated — it names concrete capabilities and gives an explicit 'Use when' clause in third person. It is a strong, concise description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks" — rather than vague language, matching the top anchor.	3 / 3
Completeness	It states what the skill does ("Brain health checks: ...") and provides an explicit when clause ("Use when asked to check brain health, run maintenance, or audit quality"), satisfying both required parts.	3 / 3
Trigger Term Quality	Natural trigger phrases like "check brain health", "run maintenance", and "audit quality" (plus a rich frontmatter triggers list) give good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The brain-health maintenance niche with distinct triggers is unlikely to collide with other skills, fitting the clear-niche top anchor.	3 / 3
	Total	12 / 12 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: 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.