CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-integration

Use when work crosses into Apple's system surfaces rather than your own UI or data — Siri and Shortcuts, widgets, Live Activities, in-app purchase, localization, privacy prompts, alarms, timers, calendar, reminders, contacts, SharePlay, VoIP and CallKit, accessory pairing, weather, Spotlight indexing, background tasks, Background Assets, push, or push on networks with no internet.

64

Quality

76%

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 ./.claude-plugin/plugins/axiom/skills/axiom-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

An exemplary router skill: unambiguous decision tree, symptom-to-reference mapping, explicit cross-domain and conflict routing, and an anti-rationalization table full of non-obvious, version-specific gotchas. The main costs are quadruple-stated routing (table, DOT graph, numbered list, examples) and inline version numbers that aren't quarantined in a deprecation section.

DimensionReasoningScore

Conciseness

The body is mostly dense, high-value pointer material with no explanations of concepts Claude already knows, but routing is stated three times over (Quick Reference table, DOT decision tree, numbered decision list, plus Example Invocations), which is real redundancy that could be tightened. It also carries many inline version numbers ("iOS 18+", "iOS 26+", "Xcode 26", "iOS 26.4", "deprecated in the 27 SDKs") that the guidelines penalize when not confined to a deprecated/old-patterns section — the ODR deprecation row is the only one placed in that framing. This lands on anchor 3 ("mostly efficient but... could be tightened"), not 4.

3 / 5

Actionability

As an instruction-only router, every row gives an exact, executable instruction: symptom → exact file path ("My background task never runs" → Read `skills/background-processing-diag.md"), exact agent launches ("Launch `iap-auditor` agent"), and concrete API-level gotchas with the reference to read. Per the scoring notes, absence of code is not penalized when guidance is this actionable; it fully matches anchor 5's copy-paste-ready standard for its genre.

5 / 5

Workflow Clarity

The routing workflow is unambiguous: a decision tree with numbered branches and sub-branches (1–16 with a/b/c variants), plus cross-domain routing and a conflict-resolution section that resolves every overlap ('stay here' vs 'also invoke axiom-X'). No destructive or batch operations exist that would require validation checkpoints, so the simple-skill exception applies and the single action (identify feature → read reference) is fully clear, matching anchor 5.

5 / 5

Progressive Disclosure

References are one level deep, consistently formatted, and surfaced through multiple navigation aids (Quick Reference table, decision tree, examples), matching the good-structure anchor 4. It falls short of 5 because no bundle files exist alongside SKILL.md to verify the ~40 referenced `skills/*.md` paths, and some detail that belongs in those references (e.g., multi-sentence SharePlay GroupSessionMessenger internals in the anti-rationalization table) is inlined in the router itself.

4 / 5

Total

17

/

20

Passed

Description

72%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 trigger-rich, highly distinctive description with excellent natural keywords and an explicit 'Use when' clause plus a boundary against sibling skills. Its one weakness is that it never states what the skill actually does (routing to per-topic references and auditors), listing domains instead of capabilities.

Suggestions

State the 'what' explicitly, e.g. prefix the topic list with 'Routes iOS system-integration work to per-topic reference files and audit agents' so the description answers both what and when.

Trim the topic enumeration slightly and spend the saved tokens on one capability clause, keeping the description concrete without growing it.

DimensionReasoningScore

Specificity

The description enumerates ~20 concrete system-surface topics ("Siri and Shortcuts, widgets, Live Activities, in-app purchase, localization, privacy prompts, alarms, timers, calendar, reminders, contacts, SharePlay, VoIP and CallKit...") but states no actions the skill performs — it is a scope list, not a capability list. It sits between anchor 2 ("names the domain but actions are minimal or generic") and anchor 3; the breadth and concreteness of the named topics lift it above 2, but the total absence of any verb/capability keeps it below 4.

3 / 5

Completeness

The 'when' is explicit and strong ("Use when work crosses into Apple's system surfaces rather than your own UI or data"), but the 'what' — that this skill routes to per-topic reference files and audit agents — is never stated; only the subject-matter domain is implied by the topic list. It falls between anchor 2 ("only 'when' is present without 'what'") and anchor 4 (both present): the unusually explicit and detailed 'when' with an enumerated domain lifts it above 2, but the missing explicit 'what' bars a 4.

3 / 5

Trigger Term Quality

Trigger terms are exactly what a user would naturally say: "Siri", "Shortcuts", "widgets", "Live Activities", "in-app purchase", "alarms", "timers", "calendar", "reminders", "contacts", "SharePlay", "VoIP and CallKit", "weather", "push". This comprehensively covers natural phrasings and framework synonyms, matching the anchor-5 example's coverage (analogous to "PDF files, PDFs, forms, .pdf"); nothing common is missing and there is no jargon-only filler.

5 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche ("Apple's system surfaces") and explicitly draws the boundary against sibling skills ("rather than your own UI or data"), matching anchor 5 ("clear niche with distinct triggers; minimal conflict risk"). Even the most confusable trigger ("push, or push on networks with no internet") is distinguished from generic networking work.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

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.