BB apple-music-dj
Ultimate personalization engine for Apple Music. Analyzes listening history, Apple Music Replay stats, library data, and taste patterns to create intelligent playlists directly in the user's Apple Music library via the MusicKit API. Supports deep cuts discovery, mood/activity playlists, trend scouting, constellation discovery ("surprise me"), playlist refresh/evolution, automated weekly curation via cron, taste DNA cards, compatibility scoring, listening insights, catalog gap analysis, album deep dives, artist rabbit holes, daily song drops, concert prep, and personalized new release radar. Use this skill whenever the user mentions Apple Music, playlists, music recommendations, listening habits, music taste, "what should I listen to", discovering new music, mood playlists, workout playlists, deep cuts, hidden gems, trending music, "surprise me", refreshing a playlist, or anything related to curating their music experience. Also trigger on: "DJ", "mix", "playlist for", "music for", "songs like", "similar to", "what's hot", "new releases for me", "taste DNA", "taste card", "compatibility", "how compatible", "year in review", "listening stats", "what have I missed", "album deep dive", "rabbit hole", "concert prep", "seeing [artist] live", "daily song", "what should I listen to right now", or OpenClaw in the context of music.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- Shorten the description to 1024 characters.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1344 chars, limit 1024 - warning
description-long-hermesdescription is 1344 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "icon"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4919 tokens
- 100Steps. 32 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1343: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -227 emoji in the instructions: noise for the model
- -33 of 17 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 22 example trigger phrases
- +4Structure: 32 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.