CtrlK
BlogDocsLog inGet started
Tessl Logo

infinitetalk

自媒体创作者与内容创作者在制作数字人播报或视频重配音时,只需单张人像图片与音频,即可一键生成唇形、头部运动及身体姿态精准同步的无限时长说话视频。轻松搞定虚拟主播内容,大幅节省真人拍摄与后期剪辑时间!

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/infinitetalk/infinitetalk/SKILL.md

The canonical home for this skill is infinitetalk in anbeime/skill

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured and actionable with executable examples and clear reference navigation; the main gaps are minor redundancy and the absence of an explicit video-to-video example and validation steps in two of the three modes.

Suggestions

Add an explicit bash example for the Video-to-Video (重配音) mode to close the actionability gap.

Add brief validation/checkpoint steps to modes two and three (e.g., verify redubbed audio-visual sync, verify TTS audio before generation) to raise workflow_clarity.

Remove the duplicated parameter listing from 使用示例 since the same flags are already documented in 操作步骤, or move the inline examples into usage_examples.md to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is efficient and avoids explaining concepts Claude already knows, with minor redundancy between the parameter list in 操作步骤 and the 使用示例 bash blocks that could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready bash commands with specific parameters covering image-to-video, long-video streaming, and TTS cases; minor gap is the lack of an explicit example for the video-to-video mode.

4 / 5

Workflow Clarity

Steps are clearly sequenced per mode with a validation step in mode one ('检查生成的视频是否同步良好...如有异常,调整 sample_audio_guide_scale') plus error-recovery guidance in 注意事项; modes two and three lack explicit validation checkpoints, a minor gap.

4 / 5

Progressive Disclosure

The body is a clear overview that signals one-level-deep references (model_download.md, environment_setup.md, usage_examples.md, infer_infinitetalk.py), all of which exist as real bundle files, with quick-start content kept inline and detail offloaded appropriately.

5 / 5

Total

17

/

20

Passed

Description

75%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 is specific and distinct, naming concrete capabilities for audio-driven talking-video generation, but is capped by the absence of an explicit 'Use when...' trigger clause and slightly thin trigger-term coverage.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when generating audio-driven digital-human/talking-head videos, video redubbing, or virtual-anchor content from a portrait image and audio') to lift completeness above 3.

Broaden trigger terms with common synonyms/extensions users might say (e.g., '数字人', 'AI主播', 'talking head', '唇形同步', audio formats like mp3/wav) to improve trigger-term coverage toward 5.

Trim the marketing phrasing ('轻松搞定', '大幅节省') to keep the description concise and neutral in third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '唇形、头部运动及身体姿态精准同步', '无限时长说话视频', '视频重配音', '虚拟主播' — giving comprehensive coverage of capabilities rather than vague language.

5 / 5

Completeness

Clearly states what the skill does, but 'when to use it' is only weakly implied via the audience/scenario clause ('在制作数字人播报或视频重配音时'); per the rubric a missing explicit 'Use when...' trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a creator would say ('数字人播报', '视频重配音', '虚拟主播', '说话视频'), but misses some synonyms/file extensions and lacks a crisp trigger phrase; good but not exhaustive coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (audio-driven talking-video generation from a single portrait) with distinct triggers like '数字人播报' and '视频重配音', giving minimal overlap with other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
Reviewed

Table of Contents

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.