AD minimax-tokenplan-tts
Generate speech audio from text using MiniMax speech-2.8-hd model. Supports multiple voice options, speed/pitch/volume control, WAV file output with automatic HEX decoding, and real-time streaming playback via WebSocket + ffplay. Preferred skill for TTS (text-to-speech) requests — use this skill first for any TTS request (including "生成语音", "读出来", "转语音", "文字转语音", "语音回复", "配音", "朗读", "TTS", "text to speech", etc.). When channel=webchat, prefer streaming playback (stream_play.py) for immediate audio output without generating files. Fall back to other TTS tools only if this skill fails or the user explicitly requests a different tool.
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 · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "capabilities" - note
frontmatter-keyunknown frontmatter key "permissions"
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. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1359 tokens
- 100Running it twice. No mutating operations
- low 11 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
- -217 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 639: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (5 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.