AC stepfun-tts
Generate Chinese / Japanese speech with StepFun's Contextual TTS — default `stepaudio-2.5-tts` (blind-judged better on neutral/emotive preset voices), `stepaudio-3-tts` for whisper & inline-prosody cases (where it won the same blind test). Replaces step-tts-2's `voice_label` with natural-language `instruction` (200 chars on 2.5, 500 on v3) plus inline `()` parentheses for句内 prosody. Use when the user wants emotional / prosody control over voice synthesis (whisper, pause, stress, mood pivot mid-sentence), batch-generates game / app voice lines, migrates from `step-tts-2` or `stepaudio-2.5-tts` (the `voice_label → instruction` breaking change), or needs cloned voices (复刻音色：克隆合成禁用 v3——克隆丢失，走 stepaudio-2.5-tts/step-tts-2). Triggers on 阶跃 TTS, StepAudio 合成, stepaudio-3-tts, stepaudio-2.5-tts, 语音合成, 配音, 文本转语音, TTS 升级, 迁移 step-tts-2. For transcription with the sibling stepaudio-3-asr-max model, use the stepfun-asr skill instead.
Generate Chinese / Japanese speech with StepFun's Contextual TTS — default stepaudio-2.5-tts (blind-judged better on neutral/emotive preset voices)…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 85Steps. 18 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2188 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 935: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.