axiom-audit-icloud

Use when the user mentions iCloud sync issues, CloudKit errors, ubiquitous container problems, or asks to audit cloud sync.

Quality

79%

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-icloud/SKILL.md

Quality

Content

85%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-sequenced audit skill with concrete grep/verify/fix guidance and explicit validation loops; its main weakness is monolithic structure with no progressive disclosure into separate reference files.

Suggestions

Move the eight detailed Pattern definitions (Issue/Search/Verify/Fix) into a references/ file (e.g. PATTERNS.md) and keep SKILL.md as an overview that links to it one level deep.

Extract the Phase 3 completeness table and Phase 4 compound-severity matrix into a separate references/ document to reduce SKILL.md length.

Confirm the 'Related' links (skills/cloudkit-ref.md, etc.) resolve to real bundle files or reword them as cross-skill pointers rather than in-skill references.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes CloudKit competence rather than re-explaining basics, with most prose conveying non-obvious failure modes that earn their tokens; only minor explanatory passages could be trimmed, fitting the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	It gives exact Grep patterns, per-pattern Read-verification steps, and copy-paste-ready Swift fixes (e.g. `CKSyncEngine.RecordZoneChangeBatch(pendingChanges:recordProvider:)`, `guard FileManager.default.ubiquityIdentityToken != nil`), covering the common cases fully.	5 / 5
Workflow Clarity	Phases 1-5 are explicitly sequenced with validation checkpoints — 'For every grep match, use Read to verify the surrounding context before reporting' — plus a completeness table, compound-severity rules, health scoring, and a false-positive checklist that form clear feedback loops.	5 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and the entire 277-line detailed material — 8 full pattern definitions, completeness and compound tables — lives inline in SKILL.md rather than as an overview pointing to one-level-deep reference files, matching the 'content that should be separate is inline' anchor despite good section headers.	3 / 5
	Total	17 / 20 Passed

Description

73%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 well-targeted trigger description with explicit 'Use when' guidance and strong distinctiveness, but it is trigger-heavy and light on stating concrete capabilities, which holds specificity and completeness just below the top anchor.

Suggestions

Add a brief capability clause before the trigger, e.g. 'Detects iCloud integration mistakes and scores cloud-sync health. Use when...' to make the 'what' as explicit as the 'when'.

Replace the jargon phrase 'ubiquitous container problems' with a natural synonym users would actually say, such as 'iCloud Drive container issues'.

Dimension	Reasoning	Score
Specificity	The description names the iCloud-audit domain and the concrete action 'audit cloud sync', but does not list multiple specific actions (e.g., detect anti-patterns, verify coordination, score health) — matching the anchor that names a domain with only 1-2 concrete actions.	3 / 5
Completeness	It has an explicit, specific 'Use when...' clause with concrete triggers, and the 'what' (audit cloud sync) is present but lightweight — the whole sentence is trigger-focused rather than balancing a clear capability statement, fitting the 'both present but one could be stronger' anchor.	4 / 5
Trigger Term Quality	It covers good natural keywords ('iCloud sync issues', 'CloudKit errors', 'audit cloud sync') but 'ubiquitous container problems' is technical jargon a user would rarely say, leaving a few natural synonyms missing.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (iCloud/CloudKit sync auditing) with distinct, specific triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 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-icloud/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.