siliconflow-tts

Generate speech audio via SiliconFlow Text-to-Speech API. Converts text to MP3/WAV/Opus/PCM using fnlp/MOSS-TTSD-v0.5 voices and SILICONFLOW_API_KEY.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-constructed single-script skill: the body is lean reference material with executable commands, a complete CLI/voice/env reference, and a documented self-check, while the implementation lives in the bundled tts.py. It scores at the top of the rubric on every content dimension.

Dimension	Reasoning	Score
Conciseness	The body is dense, actionable reference content — exact sample rates per format, voice IDs, path constraints, and env vars — with no padding explaining concepts Claude already knows. Every section earns its place; it does not fall to level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Multiple complete, copy-paste-ready bash invocations with real text, paths, and flags (e.g. `python3 ./skills/siliconflow-tts/scripts/tts.py --text ... --format wav --output ...`), and the referenced script `scripts/tts.py` exists. Not level 2: these are fully executable, not pseudocode.	3 / 3
Workflow Clarity	This is a single-command skill whose action is unambiguous across several concrete scenarios, and it documents a built-in validation feedback loop (ASR self-check → Jaccard ≥0.5 → PASS/WARN) with numbered steps. Not capped at 2: audio generation is not a destructive/batch op and a validation step is present and described.	3 / 3
Progressive Disclosure	SKILL.md is a clear, well-sectioned overview and the heavy implementation is correctly split one level deep into `scripts/tts.py`, which is referenced by exact path. There is no nested reference chain and navigation via section headers is easy; the bundle structure matches the referenced paths.	3 / 3
	Total	12 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and has a clear, low-conflict niche, but it lacks an explicit "Use when..." trigger clause and leans on branded jargon over natural user terms, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when generating voiceover, narration, or spoken audio from text') so both 'what' and 'when' are answered and completeness can reach 3.

Include natural user-facing trigger terms — 'voiceover', 'narration', 'read text aloud', 'TTS' — alongside the branded API/model names to improve trigger term coverage.

Consider trimming branded implementation detail (fnlp/MOSS-TTSD-v0.5, SILICONFLOW_API_KEY) from the description, since these are config details rather than natural triggers.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — "Generate speech audio" and "Converts text to MP3/WAV/Opus/PCM" — tied to a specific model and API, matching the anchor for listing several specific concrete actions. Not level 2: it goes beyond naming a domain and a couple of actions.	3 / 3
Completeness	It clearly answers "what" (generate/convert speech audio) but contains no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2. Not level 3: the "when" is missing rather than explicit.	2 / 3
Trigger Term Quality	It includes some natural terms ("Text-to-Speech", "speech audio") but is dominated by branded jargon ("fnlp/MOSS-TTSD-v0.5", "SILICONFLOW_API_KEY") and omits common user variations like "voiceover", "narration", or "read aloud". Not level 3: coverage of natural terms a user would say is incomplete.	2 / 3
Distinctiveness Conflict Risk	The branded SiliconFlow TTS niche with a specific model and API key is a clear, narrow scope unlikely to trigger for unrelated skills. Not level 2: it is more than "somewhat specific" — the branding makes overlap with similar skills unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/content-producer/skills/siliconflow-tts/SKILL.md
Commit: bcef823

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.