CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-media

Use when working with camera, photos, audio, haptics, ShazamKit, on-device music analysis, face grouping and video highlights, screen recording, casting to non-AirPlay routes, SharePlay playback, the user's Apple Music library, lock-screen metadata, or CarPlay app design, templates, and navigation. Covers AVCaptureSession, AVFoundation, Core Haptics, MediaPlayer, MusicKit, NowPlaying, ScreenCaptureKit, DockKit.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 whose Anti-Rationalization table and cross-domain rules carry unusually high information density and whose progressive disclosure is exemplary. The main cost is token redundancy: the routing map is stated four times in different formats, and the subagent-routing section promises more than it delivers.

Suggestions

Consolidate the routing map: the Quick Reference table, dot decision tree, and numbered decision list repeat the same feature-to-file mapping; keep the table plus one tree and drop or merge the rest.

Remove or flesh out the 'Cursor Subagent Routing' section: name the available subagents and how to launch them, or fold the camera-auditor delegation into the decision list where it is already described.

Trim Example Invocations to only the ambiguous cases (multi-reference routing like iPhone Duo, or boundary cases like Apple Music library vs. playback), since most rows restate Quick Reference entries verbatim.

DimensionReasoningScore

Conciseness

There is no known-concept padding and rows carry dense, hard-won specifics (MusicKit request starvation, ScreenCaptureKit iOS-only filter constraints), but the same routing map is repeated four times — Quick Reference table, dot decision tree, numbered decision list, and Example Invocations — which could be consolidated into one or two representations.

3 / 5

Actionability

Routing directives are concrete and executable ("Read: skills/camera-capture.md" with pattern and section numbers, "Launch camera-auditor agent") and include precise API-level guidance (SHManagedSession, AVDelegatingPlaybackCoordinator hostClockTime), but the "Cursor Subagent Routing" section is vague and near-empty, naming no subagents or launch mechanics beyond camera-auditor.

4 / 5

Workflow Clarity

The decision tree and numbered list give a clear, unambiguous feature-to-reference sequence with explicit "stay here vs. invoke axiom-X" boundary rules for cross-domain cases. Not 5 because the subagent-delegation path is underspecified and validation checkpoints are N/A rather than addressed; not 3 because the sequence is coherent and complete for every listed feature.

4 / 5

Progressive Disclosure

The body is a pure index/router: details are pushed into one-level-deep, clearly signaled `skills/*.md` references (with pattern/section pointers like "Pattern 8, deferred start"), cross-skill routes are explicitly named, and nothing that belongs in a reference file is inlined — an exemplar of clear overview navigation.

5 / 5

Total

16

/

20

Passed

Description

83%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 router-style description: explicit and specific "Use when" triggers paired with an explicit framework-coverage statement, giving it excellent completeness and low vagueness. Its only weaknesses are minor missing natural synonyms (Chromecast, DLNA, identify songs) and topic-framing rather than action-framing of capabilities.

DimensionReasoningScore

Specificity

The description enumerates many concrete capability areas ("on-device music analysis", "face grouping and video highlights", "screen recording", "casting to non-AirPlay routes", "SharePlay playback") plus a framework coverage list, but capabilities are framed as topics to "work with" rather than concrete actions performed, so it falls just below the comprehensive-actions anchor.

4 / 5

Completeness

Both questions are explicitly answered: an explicit "Use when working with..." clause lists concrete trigger topics, and the "Covers AVCaptureSession, AVFoundation, Core Haptics, MediaPlayer, MusicKit, NowPlaying, ScreenCaptureKit, DockKit" sentence states the what. Not score 4 territory because the when-clause is highly specific rather than generic.

5 / 5

Trigger Term Quality

Good coverage of natural user terms (camera, photos, audio, haptics, screen recording, casting, CarPlay, lock-screen), but common synonyms users would actually say are missing: "Chromecast"/"DLNA", "identify songs"/"Shazam" for ShazamKit, and generic "video".

4 / 5

Distinctiveness Conflict Risk

A clear Apple-media niche with highly distinctive trigger frameworks (ShazamKit, DockKit, ScreenCaptureKit, CarPlay); minor overlap risk remains because broad terms like "photos" and "audio" could collide with vision or speech/transcription skills whose boundary is only clarified in the body, not the description.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

CharlesWiltgen/Axiom

Path

axiom-cursor/skills/axiom-media/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.