CB audiolla
HTTP/MCP client for a user-deployed audiolla audio-production server. Use ONLY when the user has explicitly named audiolla AND provided AUDIOLLA_URL (or has it set in the environment). Capabilities: stem separation (Demucs / MDX / BS-Roformer), mastering (matchering reference / pedalboard preset chain), MIR analysis (BPM, key, LUFS, spectral features, beat grid, onset detection, melody contour, structural segmentation via librosa), DSP transforms (gain, EQ, compand, reverb, pitch, tempo via SoX), loudness measurement and normalization, generic effects chains (full pedalboard catalog as ordered chain), multiband compression (LR4 crossovers), transient shaping, sidechain ducking, de-essing, mid/side encode-decode, parametric EQ, panning, stereo width, silence detection and trimming, audio repair (declip + dehum), clip detection, harmonic/percussive separation, time-stretch and pitch-shift, BPM/key matching, pitch correction (auto-tune), beat slicing, audio thumbnail extraction, convolution reverb, static PNG spectrogram/waveform and 8-mode animated MP4/WebM video (ffmpeg), Chromaprint acoustic fingerprinting, AudioSet tagging, CLAP audio embeddings + similarity + zero-shot classification, ID3/Vorbis/FLAC metadata read/write, MIDI composition from JSON spec, MIDI inspection, MIDI transformation (transpose/quantize/tempo/channel-filter), MIDI quantize and humanize, drum pattern generation, MIDI rendering via fluidsynth, polyphonic audio-to-MIDI transcription (Spotify basic-pitch ONNX), chords-to-MIDI conversion, AI audio restoration (de-reverb, de-echo, AI de-noise via UVR/audio-separator), DSP noise reduction, neural speech/vocal enhancement (DeepFilterNet DF3), voice activity detection (silero-vad), speaker diarization (pyannote 3.1), DJ prep (BPM + key + Camelot + LUFS in one call), loop-point detection, curated server-side workflow presets (master-for-spotify, podcast-cleanup, vocal-cleanup) and ad-hoc op pipelines that chain multiple operations server-side. v1.0.0
HTTP/MCP client for a user-deployed audiolla audio-production server.
As a process B 72/100 · Nearly there — weak spots: execution cost, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useSKILL.md:171Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AUDIOLLA_TOKEN" $AUDIOLLA_URL/v1/engines
-
medium Exfiltration
net-credential-useSKILL.md:174Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AUDIOLLA_TOKEN" $AUDIOLLA_URL/v1/ps
-
medium Exfiltration
net-credential-useSKILL.md:177Credential used in a network call (verify the destination is the intended service)curl -X DELETE -H "Authorization: Bearer $AUDIOLLA_TOKEN" $AUDIOLLA_URL/v1/ps/htdemucs
-
medium Exfiltration
net-credential-useSKILL.md:180Credential used in a network call (verify the destination is the intended service)curl -X POST -H "Authorization: Bearer $AUDIOLLA_TOKEN" $AUDIOLLA_URL/v1/unload
-
medium Exfiltration
net-credential-useSKILL.md:189Credential used in a network call (verify the destination is the intended service)curl -X PUT -H "Authorization: Bearer $AUDIOLLA_TOKEN" \
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2822 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: HTTP/MCP client for a user-deployed audiolla audio-production serv… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 15738 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 2822 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 72/100
- 30Running it twice. 15 mutating operations with no state check
- 40Execution cost. Instruction body is 15738 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Steps. 94 steps, 9 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- 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
- +3Description length 2822: 120–800 characters recommended
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 42 headings
- +3Step-by-step instructions: 94 items
- +3Output format is stated explicitly
- +4Has examples (34 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 42.