axiom-audit-codable

Use when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.

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-codable/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.

The skill body is highly actionable and well-sequenced with concrete grep/fix patterns and explicit verification steps, assuming Claude's competence throughout. Its main weakness is progressive disclosure: it is a large monolithic file whose detection recipes and reference tables would benefit from being split into separate bundle files.

Suggestions

Extract the eight Phase 2 anti-pattern detection recipes into a separate references file (e.g. references/anti-patterns.md) and summarize them in SKILL.md, reducing the top-level token load.

Move the Phase 3 completeness-reasoning table and the Phase 5 health-score template into reference files, keeping SKILL.md as an overview that points one level deep.

Tighten the verbose inline "Explicit procedure" prose in the Phase 3 table cells and consolidate the repeated "Do NOT" admonitions to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense, procedural, and assumes Swift/Codable competence without explaining basic concepts, but several Phase 3 table cells embed lengthy "Explicit procedure" prose and repeated "Do NOT" admonitions that could be trimmed, keeping it just below fully lean.	4 / 5
Actionability	Exact grep patterns, copy-paste-ready ❌/✅ Swift fix examples, and concrete verification instructions ("Read surrounding 5 lines", "check 3 lines after") provide fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clear five-phase sequence with numbered steps, explicit verification checkpoints ("use Read to verify before reporting", "Present this map before proceeding"), severity cross-reference tables, and an output checklist give explicit validation and feedback structure; the audit is read-only so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist and all content (8 detection recipes, the completeness table, the health-score template) is inlined into a 274-line SKILL.md; the file is well-headed but monolithic with no split into reference files, and the simple-skill exception does not apply given its size.	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.

The description has a strong, explicit trigger clause with natural, distinctive keywords and a clear niche, but it describes when to invoke rather than stating a concrete capability, leaving the "what" implied. Tightening it to lead with the action (e.g. "Detects Codable safety violations...") before the "Use when" clause would raise completeness and specificity.

Suggestions

Lead with a concrete capability statement (e.g. "Detects Codable safety violations including silent data loss and serialization drift.") before the "Use when" clause so the "what" is explicit, not just the "when".

Add a few more natural trigger variants such as "Encodable/Decodable", "JSON parsing", or "coding keys" to broaden keyword coverage.

Keep the trigger list as-is for distinctiveness; the niche is already clear.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Codable review", "JSON encoding/decoding issues", "data serialization audit") but frames everything as trigger conditions rather than concrete capability actions, so it sits at the 'names domain and 1-2 actions but not comprehensive' level.	3 / 5
Completeness	It has an explicit, strong "Use when..." clause but only implies the "what" through the trigger terms rather than stating a capability (e.g. detecting Codable safety violations), so it has both halves with the "what" less explicitly stated.	4 / 5
Trigger Term Quality	Natural developer phrases like "Codable review", "JSON encoding/decoding issues", and "data serialization audit" give good keyword coverage with synonyms, missing only a few variants (e.g. Encodable/Decodable, parsing).	4 / 5
Distinctiveness Conflict Risk	"Codable review" plus "data serialization audit" carves a clear, narrow niche with distinct triggers and minimal overlap with general Swift or other auditor 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-codable/SKILL.md
Commit: 4ae86a3

Reviewed: 4 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.