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

80%

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 ./.claude-plugin/plugins/axiom/skills/axiom-data/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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-built router skill: highly actionable routing to specific files and audit agents, a clear decision tree, and a genuinely useful anti-rationalization table. The main costs are token redundancy from stating the same routing three ways and references that point outside the skill's own bundle.

Suggestions

Consolidate the three parallel routing mechanisms: keep the Quick Reference table for symptom lookup and the Decision Tree for technology choice, but trim the Example Invocations to only cases not already covered, cutting ~40-70 lines of duplication.

If Example Invocations are kept for trigger matching, move them to a single reference file and summarize with a few representative examples inline.

State the migration validation gate once (in the Decision Tree or Critical Pattern section) instead of repeating it in the Quick Reference, Critical Pattern, and Example Invocations sections.

DimensionReasoningScore

Conciseness

The body is dense routing signal with zero concept explanations, but the same routing facts are repeated across three parallel sections — e.g. `skills/grdb-performance.md` appears in the Quick Reference table, Decision Tree step 3a, and Example Invocations, while `skills/database-migration.md` appears five-plus times, and the ~70-line Example Invocations section largely duplicates the table. Mostly efficient, but a whole section of duplicated routing could be consolidated, fitting anchor 3 rather than 4.

3 / 5

Actionability

Every entry gives a fully executable instruction: exact files to read ("Read: `skills/swiftdata.md`"), agents to launch, or copy-ready commands ("`/axiom:audit core-data`"). The Example Invocations map ~25 concrete user requests to exact actions, and per the scoring notes the absence of code in an instruction-only router skill is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

The numbered Decision Tree (with 3a/4a/23a sub-branches) gives a clear, unambiguous routing sequence, and the one destructive-capable path is gated by an explicit checkpoint ("ALWAYS read `skills/database-migration.md` when adding/modifying database columns") with the failure modes it prevents, plus audit agents serving as validation. Below anchor 5 because there is no inline error-recovery feedback loop and the routing sequence is duplicated across three sections rather than stated once.

4 / 5

Progressive Disclosure

The SKILL.md is a clean index: a symptom-to-file table with clearly signaled one-level-deep references and all detail delegated to separate files. It misses anchor 5 because the referenced `skills/*.md` files are not part of this bundle (no references/ directory; paths resolve against an external suite layout), and cross-suite indirection like "See axiom-security (skills/keychain.md)" adds navigation layers outside the skill itself.

4 / 5

Total

16

/

20

Passed

Description

77%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 with excellent trigger-term coverage and an explicit, well-scoped "Use when" clause. Its main weakness is the absence of stated actions — it says what domains it covers but not what it does within them (routing to reference guides and running audits).

Suggestions

Add one or two concrete actions to the description, e.g. "Routes to reference guides for schema design, migrations, sync, and safe storage, and runs automated code audits" — this would lift both specificity and completeness.

Consider naming the audit capability ("run safety audits for SwiftData/Core Data/GRDB code") since it is a major feature of the skill but invisible in the description.

DimensionReasoningScore

Specificity

The description comprehensively enumerates concrete technologies ("SwiftData, Core Data, GRDB, SQLite, Realm, CloudKit sync, file storage, Codable, migrations") but states no explicit actions — only generic verbs like "working with" and "Covers". It sits between anchor 2 (minimal/generic actions) and anchor 3 (1-2 concrete actions): domain naming far exceeds minimal, yet no capability verb is present, so it cannot reach 4.

3 / 5

Completeness

Both parts are present: "Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization in an Apple app" is an explicit and specific trigger, and "Covers SwiftData, Core Data, GRDB..." states scope. It falls short of anchor 5 because the "what" is a coverage list of nouns rather than concrete stated actions or capabilities.

4 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered: "data persistence", "database", "storage", "CloudKit", "migration", "serialization" plus nine specific technology names (SwiftData, Core Data, GRDB, SQLite, Realm, Codable). Within the skill's declared scope no meaningful synonyms are missing, matching the comprehensive anchor rather than the "a few natural terms missing" anchor.

5 / 5

Distinctiveness Conflict Risk

"in an Apple app" plus the data-persistence technology list carves a clear router niche with distinct triggers. Minor overlap risk remains: the broad "ANY ... storage, or serialization" umbrella can catch Keychain/CryptoKit/iCloud questions that the body itself routes to sibling skills (axiom-security, axiom-swift), keeping it below the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.