CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-watchos

Use when building ANY watchOS app — app structure, independent apps, Watch Connectivity, Smart Stack widgets, complications, controls, RelevanceKit, background tasks, ClockKit migration.

Quality

80%

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-watchos/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured router SKILL.md that maps watchOS topics to concrete sub-skill files with genuinely useful conflict-resolution rules, especially the device-tunnel vs WCSession disambiguation. Its weaknesses are the fully duplicated decision tree, build-tooling metadata inlined in the body, and references to skills/ files that are not present in this skill's bundle.

Suggestions

Drop the 'dot' decision tree (or the Quick Reference table) — they encode the same routing twice and the dot format must be mentally rendered to be useful.

Move the AXIOM_AUDITOR_INLINE build-tooling block out of the distributed SKILL.md (or into a build artifact) so the shipped body contains only routing content.

Ship or verify the referenced 'skills/*.md' files inside this skill's bundle (conventionally under references/), so every route from the table resolves to a real file.

DimensionReasoningScore

Conciseness

A lean router: no concept over-explanation, no padding, assumes Claude's competence. The 'dot' decision tree fully duplicates the Quick Reference table's routing, and the AXIOM_AUDITOR_INLINE block is build-tooling metadata, so not every token earns its place — anchor 4 rather than 5.

4 / 5

Actionability

Concrete file-level routing for every topic ('See skills/watch-connectivity.md') and a specific diagnostic instruction ('Run the app without the debugger attached — if it behaves correctly, the fault is the tunnel'). Absence of code is not penalized for an instruction-only router, but the dot-graph format and unverifiable paths leave minor gaps versus fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

Routing decisions are unambiguous, and the watch-device-diag vs watch-connectivity section includes an explicit validation checkpoint with feedback ('isReachable == false is not a transport failure'; run-without-debugger test). Most other routes lack such checkpoints, matching anchor 4 ('most checkpoints present; minor validation gaps') rather than 5.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep via the Quick Reference table and decision tree — good structure matching anchor 4. However, the body points to 'skills/*.md' paths while no bundle files exist in the reviewed skill directory (no references/, scripts/, or assets/), so the referenced material is not present alongside the SKILL.md and uses a nonstandard location.

4 / 5

Total

16

/

20

Passed

Description

78%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 strong, watch-specific router description with an explicit trigger clause and concrete domain terms. Its main weakness is that the 'what' is conveyed as a topic list rather than explicit actions, and a few natural synonyms (Apple Watch, WatchKit) are missing.

Suggestions

State what the skill does with an action verb before the trigger clause, e.g. 'Guides watchOS app development: app structure, independent apps, Watch Connectivity... Use when building any watchOS app...'.

Add the natural synonyms users say — 'Apple Watch', 'WatchKit', 'watch app' — to improve trigger recall.

Include the design/UX and device-diagnostic scope the body covers (watchOS HIG, glanceable UX, Xcode/Watch connectivity) since users searching on those symptoms will not match the current description.

DimensionReasoningScore

Specificity

Enumerates many concrete capability areas — 'Watch Connectivity, Smart Stack widgets, complications, controls, RelevanceKit, background tasks, ClockKit migration' — which matches the 'several specific actions; minor gaps' anchor. It is topic enumeration rather than explicit action verbs, and body-covered areas like watchOS HIG/glanceable UX and device diagnostics are absent, so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

The 'when' is explicit and strong ('Use when building ANY watchOS app' plus the trigger topic list), but the 'what' is only implied through the em-dash topic enumeration rather than stated actions, fitting anchor 4 ('when' explicit, 'what' could be more explicit) rather than anchor 5's clearly explicit both.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'watchOS app', 'complications', 'Smart Stack', 'Watch Connectivity', 'background tasks', 'ClockKit migration'. Common variations users would actually say — 'Apple Watch', 'WatchKit', 'watch app' — are missing, matching anchor 4 rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Watch-specific niche terms (Smart Stack, ClockKit, RelevanceKit, Watch Connectivity) create a clear trigger niche with minimal overlap risk against adjacent iOS/SwiftUI/health skills, matching anchor 5.

5 / 5

Total

17

/

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

Path

axiom-codex/skills/axiom-watchos/SKILL.md

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.