SKILLEMALL.ai

AF light-game-bgm

Compose light, melodic, loopable background music in the spirit of classic cozy game town, village, and overworld themes (the calm 2D RPG / retro online-game vibe) and render it to a real playable audio file using sampled instruments. Use this whenever the user wants to create original music, a game soundtrack, BGM, a chiptune or town/overworld theme, a calm instrumental loop, or asks you to "make a song", "write some music", or produce a seamless looping audio track — even if they don't say the word "skill". Also use it when an existing track sounds too synthetic or stiff (the "stock General-MIDI" sound) and the user wants more realistic instruments, expressive strings, concert-hall space, or a clean loop. Covers the full pipeline: waveform synthesis OR (preferred) MIDI + soundfont rendering, expressive performance, convolution reverb, and seamless looping.

ClawHub Agent Skills author: Yuzhong WU v1.0.0 MIT-0 6 files body ≈ 1 772 tokens Open the sourceclawhub.ai analyzed 2 d ago

Compose light, melodic, loopable background music in the spirit of classic cozy game town, village, and overworld themes (the calm 2D RPG / retro online-game…

As a process F 46/100 · Will not run — References files that are not bundled: references/soundfonts.md, scripts/midi_helpers.py, scripts/hall_reverb_loop.py

GeneratorSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: references/soundfonts.md, scripts/midi_helpers.py, scripts/hall_reverb_loop.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 0. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/soundfonts.md
  • warning missing-ref reference to a missing file: scripts/midi_helpers.py
  • warning missing-ref reference to a missing file: scripts/hall_reverb_loop.py
  • warning missing-ref reference to a missing file: scripts/verify_loop.py

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: references/soundfonts.md, scripts/midi_helpers.py, scripts/hall_reverb_loop.py
  • 0Tools and files. 4 referenced file(s) missing: references/soundfonts.md, scripts/midi_helpers.py, scripts/hall_reverb_loop.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1772 tokens
  • 100Running it twice. No mutating operations

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 870: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 13 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This is a disclosed music-making skill that installs normal audio tools and creates local MIDI/WAV/MP3 files, with no evidence of hidden data access or unsafe behavior.
LLM: benign (high) · VirusTotal: · 21 Jun 2026