AD qclaw-speaker
四引擎本地轻量CPU TTS语音播报系统。让 QClaw/OpenClaw 像豆包一样自然开口说话。 引擎：Edge TTS（在线微软神经）→ sherpa-onnx Piper（离线13MB ONNX）→ Windows SAPI（离线原生）。 支持 11 款中文音色、自动语音播报、引擎智能降级、一键安装。 Use when: 用户说"语音播报"/"说话"/"开口"/"读出来"/"念给我听"/"tts", 要求文字转语音, 需要自动语音回复, 无障碍/驾车/做饭场景。
四引擎本地轻量CPU TTS语音播报系统。让 QClaw/OpenClaw 像豆包一样自然开口说话。 引擎：Edge TTS（在线微软神经）→ sherpa-onnx Piper（离线13MB ONNX）→ Windows SAPI（离线原生）。 支持 11 款中文音色、自动语音播报、引擎智能降级、一键安装。…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenscripts/install.py:25High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"name": "vits…nt8",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/install.py:31High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"name": "vits…nt8",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/speak.py:41High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"xiao_ya": {"engine":"sherpa","voice":"vits…nt8", "desc":"小雅 女声 (13MB离线)","size":13},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/speak.py:42High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"chaowen": {"engine":"sherpa","voice":"vits…nt8", "desc":"超稳 男声 (13MB离线)","size":13},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/speak.py:104High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)model_name = voice_info.get("voice", "vits…nt8")quoted
Files scanned: 8. 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 46/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1749 tokens
- 100Running it twice. No mutating operations
- low 12 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
- -296 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 237: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (8 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.