dm-graph-traversal

CDF Data Modeling query-vs-list expert skill. Use for graph-native reads with instances.query, traversal payload design, failure debugging, pagination/dedupe semantics, and regression-proof tests (including Node.js/TypeScript parity checks).

Quality

85%

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

81%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-structured skill body with executable code, clear validation checkpoints, and feedback loops. The main weakness is conciseness — several rationale blocks and a large inlined example could be trimmed or moved to references.

Suggestions

Trim or consolidate the repeated 'Why:' rationale paragraphs (e.g. Search-First, Two-Phase, Edge-With-Properties) into one-line notes; Claude can infer the reasoning from the guardrails.

Move the full Edge-With-Properties query example (lines 176-217) into a reference file and keep only a minimal inline snippet, reducing inline bulk.

Verify code/validate-query-parity.cjs is bundled or note it as out-of-skill, since it is referenced for validation but does not appear in scripts/.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-sectioned, but several 'Why:' rationale blocks and the large inlined query example (lines 174-217) plus the parity-check section re-explain concepts Claude can infer; could be tightened without losing actionability.	3 / 5
Actionability	Provides copy-paste-ready, executable TypeScript query payloads, concrete validator CLI invocations with flags and check modes, and explicit assertion examples — covering the common cases fully.	5 / 5
Workflow Clarity	Multi-step Implementation Workflow (lines 246-257) and Testing Requirements are clearly sequenced, with explicit validation checkpoints (payload-shape tests, parity checks), feedback loops (retries for transient failures), and a Done Criteria checklist — strong checkpoints for fragile/batch operations.	5 / 5
Progressive Disclosure	Good structure with a well-signaled one-level-deep reference (references/query-vs-list.md confirmed present) and an external validator script, though a substantial query example and reference table are inlined rather than split out; minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

88%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, specific description that clearly states both what the skill does and when to use it, with concrete CDF Data Modeling trigger phrases and low conflict risk. The only minor gap is trigger-term synonym coverage.

Suggestions

Add a couple of plain-language synonyms a user might say (e.g. 'graph relationships', 'reverse traversal', 'cursor pagination') alongside the API-specific jargon to broaden natural trigger matching.

Dimension	Reasoning	Score
Specificity	Names the CDF Data Modeling domain and lists multiple concrete actions: 'instances.query', 'traversal payload design', 'failure debugging', 'pagination/dedupe semantics', and 'regression-proof tests (including Node.js/TypeScript parity checks)' — comprehensive coverage of specific actions.	5 / 5
Completeness	Explicitly answers both: 'what' (CDF Data Modeling query-vs-list expert skill doing graph-native reads via instances.query) and 'when' ('Use for graph-native reads with instances.query, traversal payload design, failure debugging, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('graph-native reads', 'instances.query', 'traversal payload', 'failure debugging', 'parity checks') but relies on CDF-specific jargon with few synonyms or variations; good coverage but a few natural phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CDF Data Modeling graph traversal vs list), with distinct triggers tied to instances.query/traversal that are unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: cognitedata/builder-skills
Path: skills/dm-graph-traversal/SKILL.md
Commit: c87160a

Reviewed: 5 days 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.