CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-audit-networking

Use when the user mentions networking review, deprecated APIs, connection issues, or App Store submission prep.

55

Quality

61%

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 ./axiom-codex/skills/axiom-audit-networking/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a strong, highly actionable audit skill with a clear phased workflow and explicit verification checkpoints; its main weakness is progressive disclosure — everything lives in one ~250-line file with no reference files to offload the pattern catalog. Trimming the explanatory 'why it matters' prose would further improve token efficiency.

Suggestions

Move the 10 detection-pattern catalog (Phase 2) into a references/patterns.md file and summarize it in SKILL.md, giving one-level-deep navigation.

Tighten the Phase 3 'Why it matters' and Phase 4 severity columns to brief phrases to reduce explanatory padding.

Add an optional references/ file for the cross-auditor overlap notes so the main body stays a lean overview.

DimensionReasoningScore

Conciseness

The body is information-dense and avoids explaining concepts Claude already knows (no 'what is URLSession' filler), but the 'Issue'/'Why it matters' prose in the Phase 3 and Phase 4 tables is explanatory padding that could be tightened without losing actionable value.

2 / 3

Actionability

Each anti-pattern ships exact grep search strings, severity ratings, contextual Read-verification instructions, and a concrete 'Fix' — for an instruction-only audit skill this is copy-paste-ready, fully actionable guidance.

3 / 3

Workflow Clarity

A clear five-phase sequence with intermediate outputs ('Present this map in the output before proceeding') and explicit validation checkpoints ('use Read to verify the surrounding context before reporting', 'Require evidence... don't speculate') provides strong feedback loops.

3 / 3

Progressive Disclosure

The body is well-sectioned into phases rather than a monolithic wall, but no bundle files exist (references/scripts/assets all absent) and content like the 10 detection patterns or API reference stays inline, so there is no one-level-deep file split to navigate.

2 / 3

Total

10

/

12

Passed

Description

45%

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 trigger-rich and distinct but functionally incomplete: it tells Claude when to use the skill without saying what the skill does. Adding a concrete capability clause (e.g., 'Audits iOS networking code for deprecated APIs and anti-patterns') would fix the missing 'what'.

Suggestions

Lead with a concrete 'what' clause stating the skill's actions, e.g. 'Audits iOS networking code for deprecated APIs, anti-patterns, and App Store rejection risks.'

Keep the existing 'Use when...' clause so both the 'what' and 'when' halves are explicit, matching the score-3 completeness anchor.

Add a verb describing output, e.g. '...and reports severity-ranked findings with fixes,' to lift specificity from vague to concrete.

DimensionReasoningScore

Specificity

The description names only trigger contexts ('networking review, deprecated APIs, connection issues, or App Store submission prep') with no concrete actions or capabilities — it never says what the skill does, matching the vague/abstract anchor rather than the score-2 'names domain and some actions'.

1 / 3

Completeness

It has an explicit 'Use when...' trigger clause but entirely omits the 'what' — what the skill does is never stated, so it is missing one of the two required halves (the score-1 anchor covers 'missing what OR when').

1 / 3

Trigger Term Quality

'networking review', 'deprecated APIs', 'connection issues', and 'App Store submission prep' are natural terms a user would actually say, giving good coverage across the skill's scenarios.

3 / 3

Distinctiveness Conflict Risk

The networking-audit-for-App-Store niche combined with specific triggers (deprecated APIs, App Store submission prep) is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.