SKILLEMALL.ai
GitHub ↗ RU Sign in

BD asr-sentence-recognition

腾讯云语音识别 ASR Skill，适用于语音转文字、音频转写、字幕生成、会议转录、语音消息识别、 本地文件或 URL 音频识别。包含三种模式：一句话识别（<=60s 短音频）、录音识别极速版 （<=2h/100MB 中长音频快速同步返回）、录音识别（<=5h 长音频异步识别）。支持普通话、 英语、粤语、日语、韩语、德语等语种，以及中英粤混说和多种中文方言。

ClawHub Agent Skills author: Stardusten v0.1.4 MIT-0 18 files body ≈ 1 030 tokens Open the sourceclawhub.ai↗ analyzed 28 h ago

腾讯云语音识别 ASR Skill，适用于语音转文字、音频转写、字幕生成、会议转录、语音消息识别、 本地文件或 URL 音频识别。包含三种模式：一句话识别（<=60s 短音频）、录音识别极速版 （<=2h/100MB 中长音频快速同步返回）、录音识别（<=5h 长音频异步识别）。支持普通话、…

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSoftware developmenttype 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%
85
Quality 40%
79
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-shell-rc references/env_config.md:37
    Writes to a shell startup file
    echo 'export TENCENTCLOUD_SECRET_ID="你的SecretId"' >> ~/.zshrc
  • medium Dangerous commands cmd-shell-rc references/env_config.md:38
    Writes to a shell startup file
    echo 'export TENCENTCLOUD_SECRET_KEY="你的SecretKey"' >> ~/.zshrc
  • medium Dangerous commands cmd-shell-rc references/env_config.md:39
    Writes to a shell startup file
    echo 'export TENCENTCLOUD_APPID="你的AppId"' >> ~/.zshrc

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 41/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (asr-sentence-recognition) differs from the folder (tencentcloud-asr)
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 100Steps. 54 steps
  • 100Execution cost. Instruction body is 1030 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 180: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 54 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (10 of 10)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
The skill mostly implements a coherent Tencent Cloud ASR client, but registry metadata omits required credentials and the runtime scripts perform system-level installs and access host paths (e.g., QQBot downloads), so the package asks for more access than the metadata indicates.
LLM: suspicious (medium) · 11 Mar 2026