CtrlK
BlogDocsLog inGet started
Tessl Logo

identify-top-key-values

Analyze RT event tables to identify the most common values for stitching keys. Use when inspecting what ID values are actually flowing into RT 2.0, debugging unexpected stitching behavior, or checking for data quality issues like nulls or empty stitching keys.

67

Quality

81%

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

78%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 tight, actionable single-purpose skill: a concrete config-inspection command and an executable SQL template cover the core workflow well. Weaknesses are minor — some purpose restatement, one confusing sentence, no multi-key query example, and implicit rather than explicit validation checkpoints.

Suggestions

Consolidate the purpose statement: the intro paragraph, 'Use this skill when' list, and 'Process' section restate the same intent — keep one, and rewrite or remove the garbled plazma sentence ('This is what's seen in plazma and may not be different than what the rt system ignores by configuration').

Extend the Core Query Template with a second example showing how to build the query when multiple keyColumns or multiple eventTables are configured, since real RT configs often have more than one of each.

Add an explicit validation checkpoint after fetching the RT configuration (e.g., confirm "status": "ok" and that keyColumns is non-empty before generating the query) and one line on interpreting results (e.g., what proportion of nulls/empty values indicates a data-quality problem).

DimensionReasoningScore

Conciseness

Mostly lean with no explanations of concepts Claude already knows, but the purpose is restated three times (intro paragraph, "Use this skill when", "Process"), and the sentence "This is what's seen in plazma and may not be different than what the rt system ignores by configuration" is garbled and could be tightened or removed.

4 / 5

Actionability

Provides a concrete `tdx api` command with an example response and a copy-paste-ready SQL template, but only covers the single-key-column, single-event-table case — no example of generating a query for multiple key columns or multiple event tables, and no guidance on interpreting results or what thresholds indicate a problem.

4 / 5

Workflow Clarity

The sequence (get RT configuration → generate query from configured keys → run against recent data) maps directly to the provided commands and is fully executable; checkpoints such as verifying "status": "ok" in the config response or handling an empty/failed query result are only implicit.

4 / 5

Progressive Disclosure

A single self-contained file with no bundle directories; sections are well-organized, every piece of content is core to the one task, and the Related Skills pointers are clearly signaled — nothing that belongs in a separate file is inlined.

5 / 5

Total

17

/

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 a specific capability and provides an explicit, multi-scenario 'Use when' clause with natural trigger language. Its only weaknesses are incomplete synonym coverage and slight overlap risk with adjacent stitching-configuration skills.

DimensionReasoningScore

Specificity

Names the domain ("RT event tables", "stitching keys") and several concrete actions ("identify the most common values", "checking for data quality issues like nulls or empty stitching keys"), with minor gaps — the core capability is a single analysis action rather than comprehensive coverage.

4 / 5

Completeness

Explicitly answers both what ("Analyze RT event tables to identify the most common values for stitching keys") and when ("Use when inspecting... debugging unexpected stitching behavior, or checking for data quality issues") with three concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Includes natural phrases a practitioner would say — "debugging unexpected stitching behavior", "nulls or empty stitching keys", "what ID values are actually flowing into RT 2.0" — but misses common synonyms and variations like "top values", "identity graph", or "over-stitching".

4 / 5

Distinctiveness Conflict Risk

"RT 2.0" and "stitching keys" carve a clear niche with minimal conflict risk, but "debugging unexpected stitching behavior" could also plausibly trigger closely related stitching-configuration or over-stitching analysis skills.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
treasure-data/td-skills
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.