SKILLEMALL.ai
GitHub ↗ RU Sign in

BC Doubao ASR / 豆包语音转写

Transcribe audio files via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0, recorded audio → text) API from ByteDance/Volcengine. Best-in-class Chinese speech recognition. 调用字节跳动火山引擎「豆包录音文件识别模型2.0」转写录音文件，中文识别效果业界领先。Use when the user needs to transcribe recorded audio files, or asks for Doubao/豆包/Volcengine/火山引擎 audio file transcription. Do NOT use for real-time/streaming speech recognition, text-to-speech (TTS), or live captioning. 不适用于实时语音识别、语音合成(TTS)或直播字幕。

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 2 038 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Transcribe audio files via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0, recorded audio → text) API from ByteDance/Volcengine. Best-in-class Chinese speech recognition.…

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationWriting and documentstype 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
83/100
safety, quality, tests
Safety 60%
82
Quality 40%
85
Run on models
none yet
Process rating
C
63/100
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 1

  • high Obfuscation obf-html-comment-instruction SKILL.md:53
    Hidden instruction inside an HTML comment
    <!-- SYSTEM INSTRUCTION FOR AI AGENTS — DO NOT SKIP -->

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 63/100

  • 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. 6 mutating operations with no state check
  • 40Consistency. Frontmatter name (Doubao ASR / 豆包语音转写) differs from the folder (doubao-asr)
  • 85Steps. 44 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 2038 tokens

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
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 449: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 44 items
  • +4Has examples (6 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.