BD Music
Learns the user's music taste as a written corpus and uses it to build playlists, recommend tracks, and discover adjacent artists. USE WHEN my music, my music taste, what do I like, build me a playlist, make a playlist, playlist for focus or a drive, recommend music, songs like, what should I listen to, new bands, discover new artists, find bands like the ones I have, expand my taste, add to my music, add this band, my favorite bands, music reference, update my music list. NOT FOR song generation, audio editing (AudioEditor), video audio, audio or studio gear.
The skill promises to learn your music taste from written input and use it to build playlists, recommend tracks, and find adjacent artists. Triggers cover the standard range: recommend music, build a playlist for focus, find bands like… The package contains 6 files with 1065 tokens of documentation. Tests show a B grade with 82 quality and 49 process score. No critical errors, but the process score signals gaps in implementation logic or usage examples.
Runs on 10 platforms including Claude, Cursor, and DeepSeek. Safety at 100, but that doesn't mean recommendations will beat random Spotify browsing. Worth installing if you accept that the skill organizes your own taste rather than discovering new music for you—it's a mirror, not a compass.
Learns the user's music taste as a written corpus and uses it to build playlists, recommend tracks, and discover adjacent artists.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1065 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 566: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.