SKILLEMALL.ai
GitHub ↗ RU Sign in

AD cosyvoice3

Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon. Supports Chinese, English, Japanese, Korean, and 18+ Chinese dialects. Provides zero-shot voice cloning, cross-lingual synthesis, and fine-grained control. Use when: (1) User requests local TTS with high-quality Chinese/English voices. (2) Need voice cloning from reference audio. (3) Offline/inference TTS is required. (4) User wants natural-sounding speech with emotion/dialect control.

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files · 1 script body ≈ 1 373 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, consistency

ReferenceGitHubSoftware 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
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

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

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (cosyvoice3) differs from the folder (cosyvoice3-macos)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 34 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 1373 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +1No license
    • +2Single-language instructions
    • +3Description length 461: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 34 items
    • +4Has examples (8 code blocks)
    • +3All 3 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.