AB music-identify
Identify songs from audio clips using AudD API and optionally queue them to Spotify. Triggers on /songsearch command, voice messages with song identification intent, or when user asks "what song is this." Also handles recall queries like "what did I shazam" or "what was that song" by reading the music log. Works with any audio file (OGG, MP3, WAV, etc.).
Identify songs from audio clips using AudD API and optionally queue them to Spotify.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-usescripts/identify.sh:27Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)response="$(curl -sS -F "file=@${audio_path}" -F "api_token=${api_key}" -F "return=spotify" https://api.audd.io/ || true)"vendor-hostquoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 27 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1173 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 356: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.