id-graph-ids-to-canonical-id

Query ID graph to find individual IDs appearing in multiple canonical ID groups. Use when debugging over-stitching by checking whether a single ID has been stitched to more than one canonical ID.

Quality

83%

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

Quality

Content

85%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 lean, well-structured, single-purpose skill: the executable query is complete with the substitution point clearly explained, and the small-skill exceptions for workflow clarity and progressive disclosure are fully met. Minor improvements are available in trimming one padded sentence and briefly covering how to run the query and read its output.

Suggestions

Trim the redundant sentence "This is where you can plug in the parent segment the user gives in the request" — the db-name format already makes the substitution point clear.

Add one or two lines on how to execute the query (which tool/warehouse connects to the Parent Segment real time database) and what the output rows mean for diagnosing over-stitching severity.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — a schema list, one db-naming fact, and one query — but "This is where you can plug in the parent segment the user gives in the request" is padded over-explanation that could be trimmed. It is above anchor 3 because the rest is tight with no teaching of known concepts.	4 / 5
Actionability	The core query is complete, executable SQL with the `<parent_segment_id>` placeholder explained via the db-naming format, a scan-avoidance time filter, and inline comments. It falls short of anchor 5 only because there is no guidance on how to actually run the query or how to interpret the result columns.	4 / 5
Workflow Clarity	This is a simple, single-purpose skill and the single action is unambiguous: take the parent segment ID from the user, form the cdp_audience_<id> database name, and run the provided query. The query is read-only, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear sections (Requirements, Database, ids_updated table, Schema, Core Query), which satisfies the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

82%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: it clearly and explicitly states both what the skill does and when to use it, with concrete niche-specific trigger language. The only weakness is limited coverage of the action space — a single capability is named where a couple of adjacent query variants could be mentioned.

Suggestions

Expand the 'what' clause to name 1-2 adjacent concrete actions (e.g., 'count IDs affected per canonical group' or 'look up all canonical IDs for a specific individual ID') to lift specificity.

Add a synonym or variation of the core trigger terms (e.g., 'duplicate stitching' or 'ID merged into multiple audiences') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	"Query ID graph to find individual IDs appearing in multiple canonical ID groups" names the domain and one concrete action, but offers no broader coverage of related capabilities (e.g., per-segment counts or looking up a specific ID), matching the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor.	3 / 5
Completeness	The description explicitly answers both what ("Query ID graph to find individual IDs appearing in multiple canonical ID groups") and when with a concrete trigger phrase ("Use when debugging over-stitching by checking whether a single ID has been stitched to more than one canonical ID").	5 / 5
Trigger Term Quality	Natural niche terms are present — "ID graph", "over-stitching", "stitched to more than one canonical ID" — which users debugging this system would plausibly say. It stops short of anchor 5 because no synonyms or variations of these terms are covered.	4 / 5
Distinctiveness Conflict Risk	The vocabulary (ID graph, canonical ID, over-stitching, RT 2.0 ID stitching) carves out a clear niche with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: treasure-data/td-skills
Path: realtime-skills/id-graph-ids-to-canonical-id/SKILL.md
Commit: 1a0845f

Reviewed: 4 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.