video-recreation

完整的视频二创工具，支持视频反推、素材生成(图片/音效/背景音乐/配音/字幕)、视频合成、文件下载的全流程，集成Coze Bot API进行视觉分析，使用Edge-TTS进行语音合成

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

85%

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

The content is highly actionable with a well-sequenced, validated workflow and a clean resource index pointing to real bundle files. Its main weakness is verbosity from repeated API-key configuration across multiple sections.

Suggestions

Consolidate the Suno API-key configuration into one place and reference it from elsewhere to remove triplicated content.

Move the full multi-mode bash examples (示例2/示例3/示例4) into a reference file, keeping only one representative example inline.

Trim the 智能体角色分工 list since the operational steps already imply these roles.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but repeats the Suno API-key configuration across three sections (前置准备, step 5, 使用示例) and re-lists the same mode variations, fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash commands with explicit parameters, output paths, and complete JSON config examples for every stage, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear three-phase sequence with numbered steps plus an error-handling/断点续传 section that forms an explicit feedback loop (check error_log.json → identify failed step → re-execute, reusing existing assets), matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	A 资源索引 points to real one-level-deep bundle files (scripts/* and references/*, all verified to exist) with concise per-link descriptions, while the SKILL.md body stays an operational overview, matching 'clear overview with well-signaled one-level-deep references'.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 lists concrete capabilities with named tools, but it lacks an explicit 'when to use' trigger clause and leans on capability enumeration rather than natural trigger terms. Adding a 'Use when...' clause with common user phrasings would lift completeness and trigger quality.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks for 视频二创、反推视频、视频重制 or wants to create a new video based on a reference video.'

Include common natural phrasings users would actually say (e.g. '重制视频', '根据参考视频创作') instead of only capability nouns.

Trim the parenthetical tool-name detail to keep the description concise while preserving the distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '视频反推、素材生成(图片/音效/背景音乐/配音/字幕)、视频合成、文件下载' — and names specific tools (Coze Bot API, Edge-TTS), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' (full video-recreation workflow with reverse analysis, material generation, synthesis, download) but provides no 'Use when...' clause or explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains some natural user terms like '视频二创' and '视频反推', but is capability-list heavy and omits common phrasings such as '重制视频' or '根据参考视频创作' that the body itself lists, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The video-recreation niche is fairly specific, but the lack of explicit triggers means it could still overlap with general video-editing skills, matching 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	9 / 12 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: f595e96

Reviewed: about 12 hours 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.