SKILLEMALL.ai
RU Sign in

BC talkies

Self-hosted OpenAI-compatible speech service. /v1/audio/transcriptions fronts 14 open ASR models (Whisper, Parakeet, Nemotron-3.5-ASR, Canary, Sherpa-ONNX, Vosk, plus wav2vec2 and ZIPA phoneme recognizers that emit IPA); /v1/audio/transcriptions/stream accepts live PCM over WebSocket. /v1/audio/speech fronts 3 TTS engines / 4 backends — Kokoro-82M (41 baked voices, PyTorch + ONNX runtimes), the CUDA-only Qwen3-TTS family (voice cloning, preset speakers, voice design), and the CUDA-only Chatterbox Turbo (English, 19 inline emotion tags, transcript-free cloning). Stereo diarization, URL fetching, six ASR/file-staging MCP tools, bearer auth.

ClawHub Agent Skills author: Ciprian Mandache v1.3.18 MIT-0 4 files · 1 script body ≈ 11 986 tokens Open the sourceclawhub.ai↗ analyzed 12 h ago

Self-hosted OpenAI-compatible speech service.

As a process C 53/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, execution cost

IntegrationDockerMedia and videoAI and agentstype 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
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
C
53/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
Running it twice w 4
30
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.

Exfiltration 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 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".

For the author

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

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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

✓ No critical or high findings

Medium and low: 1
  • medium Exfiltration net-credential-use SKILL.md:617
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $TALKIES_AUTH_TOKEN" $TALKIES_URL/v1/models

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 11986 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 53/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 35 mutating operations with no state check
  • 40Execution cost. Instruction body is 11986 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 76 steps, 1 vague phrases
  • 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 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (8 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)
  • -2localhost URLs: will not work for another user
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 646: enough signal without eating the budget
  • +4Structure: 39 headings
  • +3Step-by-step instructions: 76 items
  • +3Output format is stated explicitly
  • +4Has examples (26 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This skill does send speech and text to a configured Talkies server, but that behavior is clearly disclosed, purpose-aligned, and accompanied by practical safety guidance.
LLM: benign (high) · VirusTotal: · 27 Aug 2026