SKILLEMALL.ai
GitHub ↗ RU Sign in

AD MiniMax TTS Plus

MiniMax TTS skill (enhanced). Multi-agent voice support (each agent can select a unique voice written in SOUL.md), native voice message for Telegram (MP3) and Feishu (OGG/Opus). Activate when user explicitly requests text-to-speech. Say "文字模式" or "关闭语音" to stop voice generation. Note: This skill uses the MiniMax secret key for API authentication. The API endpoint is https://api.minimaxi.com (not platform.minimax.io). See setup section for details.

ClawHub Agent Skills author: vshen009 v1.2.3 MIT-0 5 files · 1 script body ≈ 1 239 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationTelegramAI and agentsInfrastructuretype 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
A
90/100
safety, quality, tests
Safety 60%
96
Quality 40%
81
Run on models
none yet
Process rating
D
39/100
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
This is a copy of a skill from another catalog; the rating counts the canonical one: MiniMax TTS Plus (ClawHub)

How to improve

    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
    • low Exfiltration exfil-webhook-url scripts/tts-xiaoye.sh:179
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendVoice" \
      placeholder
    • low Exfiltration net-credential-use scripts/tts-xiaoye.sh:179
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendVoice" \
      vendor-host
    • low Exfiltration exfil-webhook-url scripts/tts-xiaoye.sh:184
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendVoice" \
      placeholder
    • low Exfiltration net-credential-use scripts/tts-xiaoye.sh:184
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendVoice" \
      vendor-host

    Files scanned: 5. 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 39/100

    • 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
    • 30Running it twice. 8 mutating operations with no state check
    • 40Consistency. Frontmatter name (MiniMax TTS Plus) differs from the folder (minimax-tts-plus)
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 10 steps
    • 100Execution cost. Instruction body is 1239 tokens
    • low 16 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
    • +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 451: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 10 items
    • +4Has examples (10 code blocks)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: clean
    This is a disclosed MiniMax text-to-speech skill that can optionally send generated voice messages to Telegram or Feishu, with no evidence of hidden or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026