BC doubao-asr（豆包语音转写）
Transcribe recorded audio files to text via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0) from ByteDance/Volcengine. Best-in-class Chinese speech recognition with speaker diarization. Use this skill whenever the user wants to: convert audio/recording to text, transcribe a meeting recording or voice memo, identify who said what in a recording (说话人分离), transcribe m4a/mp3/wav/ogg/flac files, or mentions 录音转文字/豆包/火山引擎/Volcengine/Doubao ASR. Also use when the user has an audio file and needs a transcript, even if they don't explicitly say 'transcribe'. Do NOT use for real-time/streaming speech recognition, text-to-speech (TTS), live captioning, or audio format conversion.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
read-dotenvSKILL.md:335Reads a .env file (detector / deny-list definition)**Error**: `Missing: VOLCENGINE_ACCESS_KEY_ID...` after running `source .env`
detector -
low Exfiltration
read-dotenvSKILL.md:336Reads a .env file (detector / deny-list definition)**Cause**: `source .env` sets variables in the current shell but does not export them to child processes. The script runs as a subprocess and cannot see unexported variables. / `source .env` 仅在当前 shel
detector -
low Exfiltration
read-dotenvSKILL.md:337Reads a .env file (detector / deny-list definition)**Solution**: Use `set -a && source .env && set +a` to auto-export all variables, or use `export` before each variable in your `.env` file. / 使用 `set -a && source .env && set +a` 自动导出所有变量，或在 `.env` 文件
detector
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: All mapping items must start at the same column at line 50, column 1: } author: vahnxu ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 64/100
- 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. 15 mutating operations with no state check
- 40Consistency. Frontmatter name (doubao-asr（豆包语音转写）) differs from the folder (doubao-asr)
- 70Execution cost. Instruction body is 4081 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 51 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 665: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.