Name: brain-ops
Rating: 60 (1 reviews)
Author: garrytan

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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-coding/skills/brain-ops/SKILL.md

The canonical home for this skill is brain-ops in garrytan/gbrain

Quality

Content

65%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 concrete and well-sequenced with strong command-level actionability, but it lacks an explicit validation feedback loop on the write path and inlines protocol detail that its own references point to — and those referenced files are not actually bundled.

Suggestions

Add an explicit validate→fix→retry checkpoint to the Phase 2 write cycle (e.g., verify put_page auto_links, re-query for duplicates, retry on errors).

Move the full MEMORY_VERBS verb semantics and keyless-brain extraction rules into the referenced docs/protocol/MEMORY_VERBS_v1.md and bundle that file so the inlined block becomes a concise pointer.

Consolidate the gbrain command syntax into a single copy-pasteable reference block so the common read/write cycle is executable end-to-end.

Dimension	Reasoning	Score
Conciseness	Mostly dense and information-rich with every phase earning its tokens, but the lengthy shallow-`ls` anecdote and repeated MANDATORY emphasis could be trimmed.	4 / 5
Actionability	Highly concrete commands throughout (gbrain entity/search/query/think, find ... \| wc -l, remember(fact, provenance, ttl?)) with real syntax, but they are scattered fragments rather than consolidated copy-paste-ready sequences for a full read/write cycle.	4 / 5
Workflow Clarity	Phases are clearly sequenced with numbered steps and some validation signals (anti-dup check, auto_links verification, sources-list count check), but there is no explicit validate→fix→retry feedback loop on the core write path, which the destructive/batch guideline caps at 3.	3 / 5
Progressive Disclosure	Structure is good with clear phase headers and signaled one-level-deep references, but the referenced paths (skills/conventions/*.md, docs/protocol/MEMORY_VERBS_v1.md) are not present as real bundled files, and substantial protocol detail (MEMORY_VERBS semantics, keyless-brain extraction rules) is inlined rather than delegated to those referenced docs.	3 / 5
	Total	14 / 20 Passed

Description

75%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 distinctive with a clear niche, but its "when" guidance is a read directive rather than a natural trigger clause, capping completeness. Keyword coverage is good but lacks synonym variety.

Suggestions

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g., "Use when reading, writing, citing, or looking up people, companies, or deals in the brain").

Include common synonyms/variations a user might say ("brain lookup", "save to brain", "cite a source") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete operations — "brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking" — giving comprehensive coverage of the read/write cycle.	5 / 5
Completeness	The "what" is clear, but the only "when" signal is "Read this before any brain interaction" — a read directive rather than an explicit "Use when..." trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage ("brain", "knowledge base", "lookup", "read/write", "back-linking") but these are domain-specific terms missing common synonyms or variations a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear niche (brain knowledge base operations) with distinct verbs like back-linking and ambient enrichment; minimal risk of triggering for unrelated skills.	5 / 5
	Total	17 / 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: plugin-variants/gbrain-coding/skills/brain-ops/SKILL.md
Commit: 43597b1

Reviewed: 1 day 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.