CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-data

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

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./axiom-cursor/skills/axiom-data/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-organized router skill with concrete, specific routing directives and an unambiguous decision tree, but it carries a three-way redundancy (table, decision tree, examples) and, critically, every referenced detail file is missing from the bundle, leaving the routing structure pointing at dead paths.

Suggestions

Ship the referenced `skills/*.md` files with the bundle (or fix the paths) — as delivered, all ~30 Quick Reference and Decision Tree routes resolve to nonexistent files, breaking progressive disclosure entirely.

Merge the Decision Tree into the Quick Reference table (or vice versa) — the same symptom-to-file mappings are repeated across both sections, roughly halving the routing payload.

Add a fallback branch to the Decision Tree for tasks that match multiple categories or none, and a one-line verification step after auditor delegation (e.g., what output confirms the audit ran).

DimensionReasoningScore

Conciseness

The body is dense routing content with no concept-teaching, but the ~33-line Decision Tree substantially duplicates the Quick Reference table (e.g., "SwiftData schema migration, VersionedSchema → skills/swiftdata-migration.md" appears in both). Mostly efficient, but the duplicated routing layers could be consolidated into one.

3 / 5

Actionability

Directives are concrete throughout: exact paths ("Read: `skills/database-migration.md`"), named agents ("Launch: `database-schema-auditor` agent"), and specific per-audit checklists ("unsafe ALTER TABLE, DROP operations, missing idempotency"). Not fully executable since no runnable commands or code are given and none of the referenced files exist in this bundle.

4 / 5

Workflow Clarity

The numbered conditional Decision Tree makes routing unambiguous, and the destructive case has a mandated guardrail ("ANY schema migration? → skills/database-migration.md (ALWAYS — prevents data loss)"). Falls short of level 5 because there is no fallback for tasks matching multiple or zero branches, and the auditor delegation paths end without any verification step.

4 / 5

Progressive Disclosure

References are one level deep and clearly signaled via a symptom-to-reference table, but none of the ~30 referenced `skills/*.md` files (nor references/, scripts/, assets/ directories) exist in this bundle — the index routes to nothing, so the progressive-disclosure architecture is non-functional. Better organized than the level-1 wall of text, but the dead references make navigation impossible in practice.

2 / 5

Total

13

/

20

Passed

Description

70%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 trigger-focused description with explicit "Use when" guidance and a concrete enumeration of covered technologies. Its main weakness is that it never states capabilities — what the skill does with SwiftData, GRDB, etc. — leaving "Covers" as the sole verb.

Suggestions

Replace or augment "Covers X, Y, Z" with one or two concrete capability verbs, e.g., "Diagnoses migration crashes, routes persistence work to per-technology references, and audits schema changes for data-loss risks."

Add a couple of common user phrasings or file extensions ("iCloud", "JSON", "saving data") to round out trigger coverage.

DimensionReasoningScore

Specificity

"Covers SwiftData, Core Data, GRDB, SQLite, Realm, CloudKit sync, file storage, Codable, migrations" enumerates nine concrete technologies, but the only verb is "Covers" — no capabilities (e.g., audit, migrate, diagnose) are stated. It is more concrete than a bare domain claim yet lacks the specific actions of the level-4 anchor.

3 / 5

Completeness

Both parts are explicit: "Use when working with ANY data persistence... in an Apple app" answers when, and "Covers [technology list]" answers what. Not level 5 because the "what" states scope without saying what the skill actually does with those technologies.

4 / 5

Trigger Term Quality

Good natural keyword coverage — "data persistence", "database", "storage", "migration", "serialization", "CloudKit" — plus framework names users would say. Missing a few common variants ("iCloud", "JSON", ".sqlite", "saving data"), so it falls short of comprehensive level-5 coverage but is well above level 3.

4 / 5

Distinctiveness Conflict Risk

The Apple-persistence niche is clear via "SwiftData, Core Data, GRDB, SQLite, Realm". "ANY... storage... serialization" is broad and the body itself delegates keychain/CryptoKit/tvOS to sibling axiom skills, indicating minor but real overlap risk with closely related skills.

4 / 5

Total

15

/

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

CharlesWiltgen/Axiom

Path

axiom-cursor/skills/axiom-data/SKILL.md

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.