AC suno
The Suno craft skill — generate full songs, brand music, and audio (vocals, lyrics, stems) with the right tier, honest rights, and structure control. Use when someone wants to make music with Suno/AI, create a brand sound/theme/jingle/podcast intro, control song structure (meta-tags), build a consistent sonic identity (Personas, Voices), split stems, distribute AI music to Spotify/YouTube, or asks whether they own their Suno songs. Uses the TRACK framework. Reads ai-music-and-sound (the router) + brand-profile + the content skill the music serves first. The agent writes briefs/lyrics and can drive the API where connected; the HUMAN's ears judge every track; WoopSocial publishes the content it scores. Rights: paid plan from the first note, commercial rights not ownership, no indemnification while litigation runs, AI-disclosure at distribution; never clone a real artist's voice. Distinct from ai-music-and-sound, ai-voiceover/elevenlabs (spoken TTS), capcut, and podcast-and-audiograms.
The Suno craft skill — generate full songs, brand music, and audio (vocals, lyrics, stems) with the right tier, honest rights, and structure control.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1849 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low No test case covers injection arriving through data
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 997: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.