video-product

一站式短视频制作。支持文章链接、追爆报告、文字主题等多种输入，用 gen.py 直连火山 Seedance / 阿里云百炼 Wan2.7-HappyHorse 端点生成视频素材（声画同出），FFmpeg 组装成片。

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/video-product/SKILL.md

Quality

Content

77%

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

The body is highly actionable with excellent workflow sequencing and validation feedback loops, but it is long and repetitive with significant inline reference-style content. Consolidating the repeated model-fallback and 音色规则 material and offloading the lookup tables into reference files would improve conciseness and progressive disclosure.

Suggestions

Deduplicate the model fallback chain, 音色一致性 rules, and 逐段确认 flow that are restated across A.1/A.2/A.3 — state each once and cross-reference.

Move the model-selection tables, voice-ID table, and error→cause→fix table into a reference file (e.g. references/models.md) linked from a concise 脚本清单/参考 section to improve progressive disclosure.

Trim explanatory justification Claude already knows (e.g. why subagents help) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and substantive but includes notable repetition — the model fallback chain, 音色一致性 rules, and 逐段确认 flow are restated multiple times across A.1/A.2/A.3 — matching 'could be tightened' rather than the 'every token earns its place' score-3 anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready gen.py/assemble.py/compress_preview.py/tts.py invocations with all flags, specific model IDs, and a concrete error→cause→fix table, matching 'Fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	Steps 1–7 are clearly sequenced with explicit validation checkpoints and feedback loops — compress_preview exit-code-driven per-segment confirmation, check.py 'verdict: accepted' loop, and the mandatory artifacts/_deprecated cleanup before assemble — matching the 'Clear sequence with explicit validation steps; feedback loops' anchor.	3 / 3
Progressive Disclosure	All referenced bundle scripts (gen.py, assemble.py, compress_preview.py, check.py, tts.py) exist in scripts/ and are one-level-deep with no nested reference chains, but large inline blocks (model-selection tables, voice-ID table, error table) that could be split into reference files keep it at 'content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 distinctive with natural trigger terms, but it omits an explicit 'when to use' clause, which caps completeness at 2. Adding a 'Use when...' sentence referencing the natural trigger terms would raise completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when 需要从文章链接、追爆报告或文字主题生成短视频' to satisfy the completeness 'when' requirement.

Keep the natural trigger terms (短视频制作, 文章链接, 追爆报告, 文字主题) in the 'Use when' clause so users would naturally say them.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('用 gen.py 直连火山 Seedance / 阿里云百炼 Wan2.7-HappyHorse 端点生成视频素材（声画同出），FFmpeg 组装成片') plus multiple input types, matching the 'Lists multiple specific concrete actions' anchor rather than the score-2 'some actions, but not comprehensive'.	3 / 3
Completeness	Clearly answers 'what does this do' but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 ('Has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Uses natural user-language terms a person would actually say — '短视频制作', '文章链接', '追爆报告', '文字主题' — giving good coverage of common phrasings rather than technical jargon alone.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (end-to-end short-video production via specific named endpoints with named input sources) and references the sibling viral-chaser skill, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 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
skill_md_line_count	SKILL.md is long (524 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/main/skills/video-product/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.