CtrlK
BlogDocsLog inGet started
Tessl Logo

sl

ktx's semantic layer - a structured catalog of sources (tables/views), measures, joins, and segments expressed as YAML. Covers the schema and how to query it via `sl_query`. Use when the task involves querying pre-defined metrics (ARR, churn, retention, LTV, MAU) or reading SL source YAML to understand the catalog. Capture is handled by the `sl_capture` skill (memory-agent only).

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-organized, highly actionable reference with complete executable YAML and sl_query examples. Its main weaknesses are mild verbosity in a few explanatory passages and the absence of an explicit validation/feedback loop for query building.

Suggestions

Tighten the explanatory prose in the SQL-source section and the capture-mode note to remove content that restates or justifies rather than instructs.

Add an explicit validation/feedback step for sl_query usage (e.g., on a path-not-found error, verify with sl_discover/discover_data and retry before falling back to raw SQL).

Consider moving the verbose schema reference (Part 1) into a bundled reference file so SKILL.md leads with a concise overview and query workflow.

DimensionReasoningScore

Conciseness

Mostly dense and reference-oriented with executable examples and no basic-concept padding, but several explanatory prose passages (the SQL-source 'one-shot answer' caveat and the duplicated capture-mode note) could be tightened, so it does not fully meet the 'every token earns its place' anchor.

2 / 3

Actionability

Provides complete, executable YAML examples for all three source flavors, a full sl_query input-shape JSON, and worked query examples with concrete rules (on-format, safe_divide), all copy-paste ready.

3 / 3

Workflow Clarity

The two-part structure and decision guidance ('When to prefer sl_query') are clear and a failure mode with remediation is noted, but there is no explicit validate→fix→retry feedback loop for query construction, leaving checkpoints implicit.

2 / 3

Progressive Disclosure

With no bundle files present, the self-contained SKILL.md is well organized into clear Part 1/Part 2 sections with signaled subsections, and sibling-skill cross-references are one-level-deep navigational pointers rather than nested bundle hops.

3 / 3

Total

10

/

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.

A strong, third-person description that states concrete capabilities, gives an explicit 'Use when' trigger with natural metric keywords, and disambiguates from the sibling capture skill. It is specific, complete, and distinctive.

DimensionReasoningScore

Specificity

Names several concrete actions — cataloging sources (tables/views), measures, joins, and segments as YAML, querying via sl_query, and reading SL source YAML — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what (structured catalog of sources/measures/joins/segments in YAML, queryable via sl_query) and when ('Use when the task involves querying pre-defined metrics... or reading SL source YAML').

3 / 3

Trigger Term Quality

Includes natural user-facing metric terms (ARR, churn, retention, LTV, MAU) plus 'pre-defined metrics' and 'reading SL source YAML', giving good coverage of phrasing a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (ktx's semantic layer) with distinct metric-query triggers and explicitly disambiguates capture as a separate sl_capture skill, minimizing conflict.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Kaelio/ktx
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.