SKILLEMALL.ai

AB music-seperator-demucs

Separate vocals and instrument stems from audio files with Demucs CLI. Use when the user asks for vocal extraction, accompaniment generation, stem splitting, batch separation, output format conversion (wav/flac/mp3), or Demucs performance/memory tuning on CPU/GPU. Also trigger when the user mentions demucs or demucas.

ClawHub Agent Skills author: chinesemisaka v1.0.1 MIT-0 3 files body ≈ 593 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 74/100 · Nearly there — weak spots: progress reporting

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
82
Run on models
none yet
Process rating
B
74/100
Nearly there
Progress reporting w 2
0
Failures and branches w 10
55
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

    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: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 74/100

    • 0Progress reporting. Says nothing while it works
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, 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
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 31 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 593 tokens
    • 100Running it twice. No mutating operations
    • 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +4Structure: 1 headings, hard to scan
    • +1No license
    • +2Single-language instructions
    • +3Description length 319: enough signal without eating the budget
    • +3Step-by-step instructions: 31 items
    • +3Output format is stated explicitly
    • +4Has examples (0 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: clean
    The skill set is coherent and mostly self-limiting, but users should notice that some workflows can run powerful local, GitHub, Convex, and moderation commands when explicitly invoked.
    LLM: benign (medium) · VirusTotal: · 29 May 2026