CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-daily/skills/query/SKILL.md

The canonical home for this skill is query in garrytan/gbrain

SKILL.md
Quality
Evals
Security

Quality

Content

70%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.

A highly actionable, well-sequenced workflow with strong error-handling guidance and copy-paste-ready gbrain commands. Its main costs are redundancy — grounding/citation rules repeated across four or five sections — and a monolithic structure that inlines protocol detail a reference file should carry.

Suggestions

Consolidate the citation, no-hallucination, and source-precedence rules (currently repeated in Contract, Anti-Patterns, Quality Rules, Output Format, and Citation in Answers) into a single section.

Move the Token-Budget Awareness implementation detail (cost formulas, fractional-budget compatibility, packing counters) into a reference file, keeping only the decision rule and one example inline.

Give get_timeline and list_pages the same concrete command examples the other tools have, so every listed tool is executable as written.

DimensionReasoningScore

Conciseness

The body is operational rather than tutorial-style, but the citation/no-hallucination rules are restated across Contract, Anti-Patterns, Quality Rules, Output Format, and Citation in Answers, and the Token-Budget section inlines protocol minutiae (ceil(fact.length/4) cost math, fractional-budget compatibility) that could be tightened or moved out.

3 / 5

Actionability

Concrete, executable commands with flags and question-to-command mappings cover the common cases (recall with budget-policy, query with return-unit, four graph-query examples, doctor, filter flags); minor gaps remain since get_timeline and list_pages are never shown as actual commands.

4 / 5

Workflow Clarity

A clear 5-phase sequence with explicit validation ("Check each retrieval result for notices before answering") and genuine error-recovery feedback loops in 'When it fails' (try display names/synonyms, narrow or page before claiming absence), matching the anchor-5 pattern of sequence plus checkpoints plus recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist, so everything lives in a ~230-line SKILL.md; section headers give structure, but protocol-level detail (Token-Budget Awareness, memory-verbs block) is inlined where a reference file would be appropriate, and external doc pointers (docs/protocol/MEMORY_VERBS_v1.md, ../conventions/agent-operator-protocol.md) are buried mid-paragraph rather than clearly signaled.

3 / 5

Total

15

/

20

Passed

Description

63%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 solid description with a clear what and an explicit when-clause, naming three concrete capabilities. Its weakness is that the trigger guidance uses generic phrasing instead of the natural trigger phrases (which sit unused in the triggers frontmatter), weakening both keyword quality and distinctiveness.

Suggestions

Fold the natural trigger phrases from the frontmatter triggers list (e.g. "tell me about", "who is", "what do we know about") into the description's 'Use when...' clause so it contains concrete user-utterable terms.

Narrow the when-clause to brain-specific lookups (e.g. "Use when the user asks a question that the brain's saved notes should answer") to reduce overlap with general Q&A or web-search skills.

Mention the graph/relationship capability (e.g. "who knows who", "connections") in the description to make the what-coverage more comprehensive.

DimensionReasoningScore

Specificity

"3-layer search, synthesis, and citation propagation" lists three concrete actions with a named domain (the brain's knowledge), matching the anchor-4 pattern of several specific actions with minor gaps; it is not comprehensive enough for anchor 5 (no mention of graph traversal or gap-flagging).

4 / 5

Completeness

Both what ("Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation") and when ("Use when the user asks a question...") are present, but the when-clause uses generic phrasing rather than concrete trigger phrases, matching anchor 4 exactly.

4 / 5

Trigger Term Quality

The when-clause offers only generic phrases ("asks a question", "wants a lookup", "needs information") while natural trigger phrases like "tell me about" or "who is" exist only in the separate triggers frontmatter, not the description itself — some relevant keywords but missing common variations.

3 / 5

Distinctiveness Conflict Risk

"the brain's knowledge" carves out a niche, but "Use when the user asks a question" is broad enough to overlap with any general Q&A or web-search skill; anchor 3 (somewhat specific but could still overlap with similar skills) fits better than anchor 4.

3 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

plugin-variants/gbrain-daily/skills/query/SKILL.md

Reviewed

Table of Contents

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.