html-video

使用 html-video 引擎从 content-graph 和模板生成视频。支持 23+ 模板、多种画面比例、变量注入、逐帧渲染、全项目导出。TTS/BGM 由 openclaw MiniMax 扩展提供，不使用 html-video 内置音频。

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/content-producer/skills/html-video/SKILL.md

Quality

Content

92%

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, concise, and workflow-clear with strong validation and fallback loops, scoring at the top of those dimensions; it loses a point on progressive disclosure because one bundle script is unlinked and the template catalog is monolithically inline.

Suggestions

Reference scripts/content_graph.py explicitly from the Content-Graph generation step (e.g. 'run python scripts/content_graph.py') so the bundle file is clearly signaled and discoverable.

Move the multi-table template catalog into a references/TEMPLATES.md file and link to it from a short selection summary, keeping the SKILL.md as a lean overview.

Add a brief explicit validation step after project-set-var (e.g. run 'hv.sh project-show <id>' to confirm injected variables) to make the inject→render checkpoint explicit.

Dimension	Reasoning	Score
Conciseness	Information-dense tables and code blocks with no conceptual padding Claude already knows; the guardrail '禁止…' rules earn their place as operational protection, fitting the lean-and-efficient anchor.	3 / 3
Actionability	Provides copy-paste-ready hv.sh commands, a concrete content-graph.json example, and explicit env-var rows — fully executable guidance rather than abstract direction.	3 / 3
Workflow Clarity	A 5-step sequence with explicit validation (ffprobe duration check) and feedback loops (asset priority '成功即停', siliconflow fail→degrade rule) matches the anchor requiring clear sequencing with checkpoints and error recovery.	3 / 3
Progressive Disclosure	Sections are well-organized and hv.sh is a real one-level reference, but the content_graph.py bundle file is never referenced from the body and the large inline template catalog could live in a separate file, fitting the 'content that should be separate is inline / references not clearly signaled' anchor.	2 / 3
	Total	11 / 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 clearly delineates a distinct niche, but it omits an explicit 'Use when…' trigger clause and relies on technical jargon over natural user phrasing, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when…' clause in Chinese (e.g. '当用户需要生成视频、做短视频或制作带模板的视频时使用') to satisfy the completeness trigger requirement and raise the score.

Replace or supplement internal jargon (html-video 引擎, content-graph, openclaw MiniMax) with natural user terms ('生成视频', '做视频', '短视频模板', '视频制作') to improve trigger-term quality.

Trim the TTS/BGM provider detail from the description; it is implementation trivia that dilutes the trigger without aiding discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '生成视频', '支持 23+ 模板', '多种画面比例', '变量注入', '逐帧渲染', '全项目导出' — matching the anchor that enumerates several specific capabilities rather than naming a domain alone.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when…' or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural keywords ('生成视频', '模板') but leans on internal jargon ('html-video 引擎', 'content-graph', 'openclaw MiniMax', 'TTS/BGM') and omits common variations a user would say, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (html-video template-driven video generation) with distinct triggers, making it unlikely to fire for unrelated skills.	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: 1 missing	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: crews/content-producer/skills/html-video/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.