axiom-data

Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization. Covers SwiftData, Core Data, GRDB, SQLite, Realm, CloudKit sync, file storage, Codable, migrations.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/plugins/axiom/skills/axiom-data/SKILL.md

Quality

Content

71%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.

This is a well-structured router skill that excels at progressive disclosure and provides concrete routing directives, but it is meaningfully redundant across its Quick Reference, Decision Tree, and Example Invocations sections. Consolidating the repeated routing info would materially improve token efficiency.

Suggestions

Consolidate the Quick Reference table, Decision Tree, and Example Invocations into a single routing section; the three-way repetition of the same 'symptom → reference' mappings is the main source of verbosity.

Clean up the Decision Tree numbering (e.g., the 3a/3b/3c and 23a sub-items) into a flatter, consistently numbered sequence for clearer navigation.

Trim the Anti-Rationalization table to the highest-value rows (e.g., migrations, tvOS, Keychain) since several entries restate guidance already conveyed by the routing sections.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it repeats the same routing information three times (Quick Reference table, Decision Tree, and Example Invocations), which is noticeable padding that could be tightened.	3 / 5
Actionability	Directives are concrete and executable ('Read skills/swiftdata.md', 'Launch core-data-auditor agent'), and for an instruction-only router the absence of code is appropriate, though there are minor gaps in executable detail.	4 / 5
Workflow Clarity	The numbered Decision Tree provides a clear routing sequence and includes an explicit migration safety gate ('ALWAYS read skills/database-migration.md'), but the messy sub-numbering (3a/3b/3c, 23a) slightly reduces clarity.	4 / 5
Progressive Disclosure	The SKILL.md is a clean overview that points to well-signaled, one-level-deep references organized in a Quick Reference table, with no bundle files present to evaluate against.	5 / 5
	Total	16 / 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.

The description is strong, explicitly pairing a concrete 'what' with a clear 'Use when...' trigger and covering a broad but coherent data-persistence domain. It could be sharpened by replacing generic verbs ('working with', 'Covers') with concrete actions and tightening distinctiveness against adjacent security skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete technologies (SwiftData, Core Data, GRDB, SQLite, Realm, CloudKit sync, Codable, migrations), but the verbs are generic ('working with', 'Covers') rather than concrete actions like 'extract' or 'merge', leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Covers SwiftData, Core Data, GRDB, SQLite, Realm, CloudKit sync, file storage, Codable, migrations') and 'when' ('Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with synonyms across 'data persistence', 'database', 'storage', 'CloudKit', 'migration', and 'serialization' plus specific product names, though a few natural phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear data-persistence niche with distinct triggers, but its breadth over many storage/persistence technologies creates minor overlap risk with closely related security and storage skills.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CharlesWiltgen/Axiom
Path: .claude-plugin/plugins/axiom/skills/axiom-data/SKILL.md
Commit: 4ae86a3

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.