query

Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.

Quality

75%

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 ./skills/query/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 body is a well-structured, actionable overview with concrete gbrain commands, a clear phased workflow, and good sectioning. Its main weakness is redundancy — citation, source-precedence, and no-hallucination rules are each restated across multiple sections, which inflates the token budget without adding information.

Suggestions

Consolidate citation guidance into a single section; remove its restatement from Contract, Output Format, and Quality Rules to cut redundancy (the lowest-scoring conciseness dimension).

Merge the "Source precedence" lines duplicated in the Contract and the dedicated section into one canonical location, cross-referenced from the other.

Add one worked end-to-end example for the core search/synthesis flow (e.g., a sample question → search → read chunks → synthesized cited answer) to lift actionability from mostly-executable to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence on domain specifics, but the same guidance recurs across sections — citations restated in Contract, Output Format, Quality Rules, and Citation in Answers; source precedence in both Contract and its own section; "no hallucination" twice — so it lands at "could be tightened" rather than the minor-trim 4.	3 / 5
Actionability	Concrete executable commands appear throughout (`gbrain graph-query companies/acme --type works_at --direction in`, `gbrain doctor --json`, named link types), with fully worked graph examples; the core search/synthesis phases stay guidance-level without a worked example, leaving a minor gap that keeps it below 5.	4 / 5
Workflow Clarity	A clearly sequenced 5-phase flow (Decompose → Execute → Read → Synthesize → Flag gaps) with implicit checkpoints (read chunks before full pages, flag gaps, doctor diagnostics); as a read-only skill it is exempt from the destructive-cap, but it lacks an explicit validate→fix→retry loop so it does not reach 5.	4 / 5
Progressive Disclosure	Well-organized into clear headed sections with one clearly-signaled external reference (`docs/protocol/MEMORY_VERBS_v1.md`) and no nested lookups; core operational guidance is appropriately inline, with only minor overlap between Graph Traversal/Search Quality reference-style material and the overview, fitting "good structure; minor organization gaps."	4 / 5
	Total	15 / 20 Passed

Description

83%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 strong description that clearly states what the skill does and gives an explicit, natural-language "Use when..." trigger clause with concrete phrases. It is mostly specific and distinct; the only mild weakness is that a few trigger phrasings are generic enough to invite minor overlap with adjacent lookup skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "3-layer search, synthesis, and citation propagation" — but the actions lean on domain jargon and coverage is not fully comprehensive, fitting the "several specific actions; minor gaps" anchor rather than the exhaustive 5.	4 / 5
Completeness	Explicitly answers both halves: the "what" ("Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation") and the "when" ("Use when the user asks a question, wants a lookup, or needs information from the brain") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — "asks a question", "wants a lookup", "needs information from the brain" — giving good keyword coverage, though it stops short of the comprehensive synonyms/extensions needed for a 5.	4 / 5
Distinctiveness Conflict Risk	The "brain's knowledge" framing carves a clear niche with distinct triggers, but generic phrases like "asks a question" keep a minor overlap risk with other Q&A/lookup skills, so it sits at "mostly distinct" rather than minimal-conflict 5.	4 / 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: skills/query/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.