CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-tools

Use when asking how to use Axiom or what skills exist, capturing console with xclog, symbolicating .ips/MetricKit/.crash crashes with xcsym, driving/validating simulator UI & accessibility with xcui, or analyzing xctrace/CPU profiles with xcprof.

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured router skill with actionable routing logic, clear workflow sequencing, and clean progressive disclosure. Its main weakness is verbosity in the enforcement/Red Flags prose, which lectures Claude beyond what the routing guidance needs.

Suggestions

Collapse the EXTREMELY-IMPORTANT block and the Red Flags table into a single concise 'Always check for a matching Axiom skill before responding to iOS/Swift tasks; when in doubt, check first' rule — the repetitive 'not negotiable / not optional / cannot rationalize' phrasing is padding Claude does not need.

Trim the Red Flags table entries that merely restate the Rule (e.g. 'I remember how to do this from last time', 'I'll gather info first, then check skills') to the few that add non-obvious domain-specific signal.

Move the Device Hub version notes (Xcode 26 vs 27, 'iOS 26 at WWDC 2025') into the referenced device-control-ref.md or a clearly marked version section so time-sensitive detail does not inflate the router overview.

DimensionReasoningScore

Conciseness

The routing table, priority list and detection criteria are efficient, but the EXTREMELY-IMPORTANT block ('This is not negotiable. This is not optional. You cannot rationalize your way out of this.') and the redundant Red Flags table pad the body with motivational repetition Claude does not need — 'mostly efficient but could be tightened' rather than fully lean.

2 / 3

Actionability

It gives concrete, copy-paste-ready guidance: a trigger-to-file routing table, copy-paste commands ('/skill axiom-concurrency', '/axiom:fix-build'), explicit detection rules (.xcodeproj/.xcworkspace), and worked multi-domain examples — specific rather than vague despite being an instruction-only router.

3 / 3

Workflow Clarity

The routing workflow is clearly sequenced — detect via iOS project criteria, apply the numbered skill priority, invoke router(s), follow the specialized skill — with the priority list and multi-domain rules acting as decision checklists; no destructive/batch step is present that would require a validate-fix-retry loop.

3 / 3

Progressive Disclosure

The body is a clean overview that routes to one-level-deep, well-signaled references (skills/*-ref.md) via a navigation table, splitting detail appropriately; the referenced files are suite-sibling skills rather than local bundle files, which is the intended router pattern, so structure matches the score-3 anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, specific router description that pairs concrete per-tool actions with an explicit 'Use when...' trigger and natural keyword coverage. It clearly answers both what the suite does and when to invoke it.

DimensionReasoningScore

Specificity

It lists four concrete actions each bound to a named tool — 'capturing console with xclog, symbolicating .ips/MetricKit/.crash crashes with xcsym, driving/validating simulator UI & accessibility with xcui, or analyzing xctrace/CPU profiles with xcprof' — matching the 'lists multiple specific concrete actions' anchor rather than the single-domain score 2.

3 / 3

Completeness

An explicit 'Use when asking how to use Axiom...' clause provides the trigger, while the action list answers what it does, so both what and when are explicit — not capped at 2 since the 'Use when...' clause is present.

3 / 3

Trigger Term Quality

It mixes natural user phrasings ('asking how to use Axiom or what skills exist', 'capturing console', 'simulator UI', 'accessibility', 'CPU profiles') with the tool names and file formats, giving good coverage of terms users would actually say, comparable to the score-3 PDF anchor.

3 / 3

Distinctiveness Conflict Risk

It names a specific Axiom tool suite (xclog/xcsym/xcui/xcprof) with distinct triggers tied to Axiom usage, making overlap with unrelated skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 7 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

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.