video-recreation

自媒体创作者与影片与视频编辑在需要视频二创或反推参考视频时，一键完成从AI视觉分析、图文音素材生成到最终合成的全流程，自动产出包含配音与字幕的高质量二创视频，让创作效率翻倍！

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/video-recreation/video-recreation/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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 a well-sequenced pipeline and clearly signaled, real reference files, but it is padded with redundant configuration explanations and lacks explicit validation checkpoints in the batch workflow. Consolidating the duplicated Suno guidance and adding per-stage verification would meaningfully raise quality.

Suggestions

Consolidate the Suno API-key configuration into a single location and reference it from the other two spots to remove redundancy and improve conciseness.

Add explicit validation/verification checkpoints after each batch stage (e.g. verify frame count, confirm generated images exist, validate SRT timing) before proceeding to lift workflow clarity above 3.

Move the long 使用示例 command blocks and the 智能体角色分工 section into a reference file, keeping the main body as an overview, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly concrete and useful, but noticeably redundant — the Suno API-key configuration is explained three times (前置准备, 步骤5, 示例1), 使用示例 duplicates the 操作步骤 commands, and 注意事项 repeats earlier error-handling content.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands with explicit flags, real script paths, and concrete JSON config examples covering the common cases across all pipeline stages.	5 / 5
Workflow Clarity	The 3-phase/9-step sequence is clear and includes a 断点续传 feedback loop, but this batch pipeline lacks explicit per-step validation/verification checkpoints, capping workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	A 资源索引 section clearly signals one-level-deep references to verified real files in scripts/ and references/, but substantial inline content (full example blocks, the 8-role section) that could live in references keeps it just short of ideal.	4 / 5
	Total	15 / 20 Passed

Description

67%Weight 40%Scale 1-5

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 conveys a clear, distinct niche and covers the full pipeline with concrete actions and an embedded 'when' clause, but mixes in marketing fluff and lacks trigger-term breadth. Tightening the wording and adding explicit 'Use when...' phrasing with synonyms would lift it.

Suggestions

Replace the marketing tail "让创作效率翻倍！" and "一键完成...全流程" with concrete, scoped actions to raise specificity.

Add an explicit 'Use when...' clause with synonyms and variations (e.g. 二创视频、反推视频、视频重制、参考视频复刻) to improve trigger coverage and completeness.

State the trigger guidance in third-person imperative form rather than a scenario clause to match the rubric's preferred voice.

Dimension	Reasoning	Score
Specificity	Lists several concrete pipeline actions — "AI视觉分析", "图文音素材生成", "最终合成", "配音与字幕" — giving broad coverage, but "一键完成全流程" and "让创作效率翻倍" are vague marketing padding that keep it just below comprehensive.	4 / 5
Completeness	Clearly states what the skill does (analysis, material generation, synthesis, voiceover/subtitles) and provides an equivalent 'when' clause ("当需要视频二创或反推参考视频时"), though the trigger guidance could be more explicit and grouped.	4 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ("视频二创", "反推参考视频") but offers few synonyms or variations and no file extensions, leaving common forms missing.	3 / 5
Distinctiveness Conflict Risk	The '视频二创/反推参考视频' niche is specific with distinct triggers and low overlap with other skills, with only minor overlap risk against generic video-editing skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/video-recreation/video-recreation/SKILL.md
Commit: d9e888d

Reviewed: 2 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.