brain-ops

Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/brain-ops/SKILL.md

Quality

Content

67%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 content is highly actionable with concrete gbrain commands and well-sequenced multi-phase workflows backed by real verification checkpoints. Its weak spots are conciseness (a padded opener and a long anecdote) and progressive disclosure (some inline protocol detail that could be split into the referenced files).

Suggestions

Trim the poetic opener and condense the corpus-scope anecdote into a one-line rule plus the fix command to recover token budget.

Move the MEMORY_VERBS contract detail and the shallow-ls warning into the referenced `docs/protocol/MEMORY_VERBS_v1.md` / conventions files and link to them from the body.

Add an explicit validate→fix→retry loop for page writes (e.g., check `auto_links.errors`, fix, re-write) to push workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly information-dense, but the poetic opener ('The brain is not an archive. It is a live context membrane...') and the multi-paragraph corpus-scoping anecdote ('Real example: a shallow ls...') are unnecessary explanation that could be tightened, matching 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Concrete, copy-paste-ready commands appear throughout (`gbrain entity "<name>"`, `gbrain think`, `find <dir> -name '*.md' \| wc -l`, `[source-id:slug]` citations, `remember(fact, provenance, ttl?)` signatures), but there is no single complete end-to-end worked example, leaving minor gaps below the fully-executable anchor 5.	4 / 5
Workflow Clarity	Phases 1–4 lay out clearly numbered, sequenced steps with several checkpoints (backlink check, timeline check, auto_links verification, 'verify against gbrain sources list'), so the destructive-skill validation cap does not force 3; minor validation gaps (no explicit validate→fix→retry loop on writes) keep it just below 5.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers and one-level-deep references clearly signaled via blockquotes (`skills/conventions/brain-first.md`, `quality.md`, `docs/protocol/MEMORY_VERBS_v1.md`), though some inline content (the MEMORY_VERBS protocol block, the corpus-scope warning) could live in separate reference files and no bundle files ship alongside the skill.	4 / 5
	Total	15 / 20 Passed

Description

67%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 is specific and distinct, naming several concrete brain operations with an explicit activation cue. Its main weakness is trigger-term naturalness — the phrasing leans on internal jargon rather than terms a user would naturally say.

Suggestions

Reword the 'when' clause into concrete user-facing triggers (e.g., 'Use when the user mentions a person, company, or deal, or asks to look up or update brain knowledge').

Soften internal jargon ('ambient enrichment', 'read-enrich-write loop') into natural synonyms a user might actually say.

Consider adding a short 'Use when...' sentence with common variations (lookup, citation, recall) to lift completeness toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Brain knowledge base operations') and lists several concrete operations — 'brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking' — though the items are operation labels rather than fully concrete actions, so it stops short of comprehensive coverage at 5.	4 / 5
Completeness	Clearly states what it does and offers an explicit when clause ('Read this before any brain interaction'), but the when is generic rather than concrete trigger phrases, so it is above the no-trigger cap of 3 yet below the concrete-trigger anchor 5.	4 / 5
Trigger Term Quality	Relevant keywords appear ('brain', 'lookup', 'citation', 'read/write') but several terms are internal jargon ('ambient enrichment', 'back-linking', 'read-enrich-write loop') and natural user phrasings or synonyms are thin, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'Brain knowledge base operations' carves a clear proprietary niche with distinct triggers and low conflict risk, with only minor overlap potential against generic knowledge-base skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	15 / 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/brain-ops/SKILL.md
Commit: 7b7921d

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.