axiom-audit-core-data

Use when the user mentions Core Data review, schema migration, production crashes, or data safety checking.

Quality

80%

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 ./axiom-codex/skills/axiom-audit-core-data/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a strong, highly actionable auditor prompt with clear phased workflows and mandatory verification checkpoints. It is slightly verbose in places and its progressive disclosure is weak because the referenced external references/skills cannot be verified against an actual bundle and detail is kept inline.

Suggestions

Tighten or relocate explanatory rationales Claude already knows (e.g. why viewContext freezes the UI, the 1000-queries math) to raise conciseness toward the score-3 anchor.

Either add real reference bundle files for the cross-auditor and pattern details cited in 'Related', or remove the dangling reference pointers so navigation is verifiable and one level deep.

Consider moving the long Phase 3 completeness table and Phase 4 compound-finding table into a single reference file, keeping SKILL.md as a lean overview with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumption-respecting (explicit "Do not reason from training data" directive, lean grep tables), but several explanatory passages restate known Core Data behavior (e.g. "viewContext is main thread — heavy work on it freezes the UI", "1000 items = 1000 extra database queries") that could be tightened, matching the score-2 anchor.	2 / 3
Actionability	It provides concrete, executable grep patterns, exact Swift fix snippets (e.g. migration options dictionary, objectID cross-thread passing, fetchBatchSize), and copy-paste-ready output templates, hitting the fully-executable anchor.	3 / 3
Workflow Clarity	The five-phase sequence is explicit, each detection step mandates Read verification before reporting (validation checkpoints), and Phase 5 defines a feedback-style health-score gating with explicit severity-bumping rules, satisfying the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The body references external resources only loosely in a 'Related' section ('axiom-data (core-core-diag reference)', other skills) with no verifiable bundle files present in references/scripts/assets, and much detail that could live in reference files is inline; this matches the score-2 anchor of structure present but references not clearly signaled or verified.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 well-constructed with an explicit "Use when" trigger and natural, distinctive terms tied to a clear Core Data niche. Its main weakness is specificity — it states the domain and triggers rather than enumerating the concrete audit actions the skill performs.

Suggestions

Add concrete actions to match the score-3 specificity anchor, e.g. 'Detects Core Data safety violations — missing migration options, thread-confinement violations, N+1 queries, and unsafe store deletion. Use when the user mentions Core Data review, schema migration, production crashes, or data safety checking.'

Dimension	Reasoning	Score
Specificity	The description only names the domain ("Core Data review, schema migration, production crashes, or data safety checking") without enumerating concrete actions the skill performs, matching the score-2 anchor that names a domain and some actions but is not comprehensive.	2 / 3
Completeness	It opens with an explicit "Use when the user mentions ..." trigger clause answering when, and the listed topics convey what the skill addresses, satisfying both the what and when with explicit triggers.	3 / 3
Trigger Term Quality	Natural user-facing terms like "Core Data review", "schema migration", "production crashes", and "data safety checking" are exactly what a user would say, giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	The Core Data / schema-migration / production-crash niche is highly specific and unlikely to fire for unrelated skills, giving a clear distinct niche with distinct triggers.	3 / 3
	Total	11 / 12 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: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-audit-core-data/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.