axiom-audit-iap

Use when the user mentions in-app purchase review, IAP audit, StoreKit issues, purchase bugs, transaction problems, or subscription management.

Quality

75%

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-iap/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 skill is highly actionable with concrete grep patterns, executable Swift fixes, and a well-sequenced five-phase workflow including verification checkpoints. Its weaknesses are prose padding in the impact/compound tables and a monolithic structure with no bundle references that could offload the 13-pattern catalog.

Suggestions

Tighten the Issue/impact prose in Patterns 13 and the Phase 3/4 tables to one line each; the rubric already rewards brevity, and the user-visible bug narratives can be shortened without losing the signal.

Extract the 13 detection patterns (Phase 2) into a references/PATTERNS.md file and keep SKILL.md as an overview that links to it, achieving one-level-deep progressive disclosure.

Move the Phase 3 completeness checklist and Phase 4 compound table into a references/COMPLETENESS.md so the main body stays a lean workflow overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely actionable, but several cells in the Phase 3/4 tables and Pattern 13's Issue prose over-explain consequences (e.g. "Marketing dollars spent on App Store promotion buy nothing — the user taps 'Buy'... and nothing happens") that could be trimmed without losing signal.	2 / 3
Actionability	It provides exact Grep/Glob patterns, executable Swift fixes (e.g. `await transaction.finish()`, `if case .verified(let transaction) = result`, and the full `paymentQueue(_:shouldAddStorePayment:)` extension), and a copy-paste-ready output template.	3 / 3
Workflow Clarity	Phases 1–5 are explicitly sequenced with validation checkpoints — "use Read to verify the surrounding context before reporting", "Require evidence from the Phase 1 map — don't speculate", and the Phase 5 health scoring gate — giving clear feedback loops for a batch audit operation.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the document is a ~300-line monolith; the 13 detection patterns and the Phase 3 completeness table are inline content that could be split into one-level-deep reference files, though section organization is clear.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 has strong, natural trigger terms and a clearly distinguishable IAP/StoreKit niche, but it leads with the trigger clause and never explicitly states what the skill does. Adding a concrete capability statement before the "Use when" clause would lift completeness and specificity.

Suggestions

Add a leading capability clause before the trigger, e.g. "Audits iOS in-app purchase code for StoreKit anti-patterns, missing transaction handling, and App Store rejection risks. Use when..."

Call out one or two concrete actions (e.g. "detects missing Transaction.finish() and verification gaps") so the "what" is explicit rather than implied by "review"/"audit".

Dimension	Reasoning	Score
Specificity	The description names the domain ("in-app purchase review, IAP audit, StoreKit issues") which implies reviewing/auditing actions, but it lists no concrete capabilities such as detecting missing finish() calls or verifying StoreKit patterns, so it stops short of comprehensive concrete actions.	2 / 3
Completeness	The "when" is explicit ("Use when the user mentions..."), but the "what does this do" is only implied through the nouns "review"/"audit" folded into the trigger list rather than stated as a distinct capability, so it does not clearly answer both halves.	2 / 3
Trigger Term Quality	It covers a strong set of natural trigger phrases a user would actually say — "in-app purchase review, IAP audit, StoreKit issues, purchase bugs, transaction problems, or subscription management" — with good variation.	3 / 3
Distinctiveness Conflict Risk	The IAP/StoreKit/subscription niche is specific with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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-iap/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.