SKILLEMALL.ai
GitHub ↗ RU Sign in

BC audio-transcribe

This skill should be used when the user explicitly asks to "transcribe a meeting", "transcribe audio", "transcribe a meeting recording", "convert audio to text", "generate meeting minutes from audio", "do speech-to-text", "transcribe with speaker diarization", "identify speakers in audio", "transcribe Chinese audio", "transcribe English audio", "transcribe Japanese audio", "multi-speaker transcription", "transcribe a podcast", "transcribe podcast episode", "transcribe an interview", "convert podcast to text", "podcast to transcript", or mentions FunASR, Paraformer, SenseVoice, Whisper, MiMo, MiMo-V2.5-ASR, meeting transcription, podcast transcription, or speaker diarization. Supports multi-speaker meeting and podcast transcription in Chinese, English, Japanese, Korean, Cantonese, and 99 languages (via Whisper), plus Xiaomi MiMo-V2.5-ASR (8B, local GPU) for stronger proper-noun and code-switching accuracy. Automatic speaker diarization via CAM++, hotword biasing (FunASR path), LLM cleanup. FunASR works on GPU and CPU; MiMo requires a local CUDA GPU with >=20GB VRAM.

ClawHub Agent Skills author: zxkane v1.7.1 MIT-0 13 files · 2 scripts body ≈ 3 411 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

GeneratorMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
84
Quality 40%
62
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Shorten the description to 1024 characters.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-privilege references/pipeline-details.md:373
    Privilege escalation / world-writable permissions
    sudo chmod 600 /swapfile
  • medium Dangerous commands cmd-privilege references/pipeline-details.md:378
    Privilege escalation / world-writable permissions
    sudo swapoff /swapfile && sudo rm /swapfile
  • medium Dangerous commands cmd-privilege references/pipeline-details.md:398
    Privilege escalation / world-writable permissions
    sudo fallocate -l 4G /swapfile && sudo chmod 600 /swapfile \
  • low Dangerous commands cmd-privilege scripts/patch_clustering.py:102
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    print("  If FunASR was installed with sudo, try: sudo python3 patch_clustering.py --yes")
    code literal

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1082 chars, limit 1024

Process rating: all ten parameters 58/100

  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (audio-transcribe) differs from the folder (zxkane-audio-transcriber-funasr)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 39 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 3411 tokens
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1081: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -36 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 17 example trigger phrases
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
This appears to be a legitimate audio transcription skill, but it runs sensitive speaker-gender inference by default and can send transcript/context data to cloud LLM providers when LLM features are used.
LLM: suspicious (high) · VirusTotal: · 29 May 2026