CtrlK
BlogDocsLog inGet started
Tessl Logo

three-body-video-creator

《三体》赛道AI视频创作工具,提供结构化的多智能体协作流程、素材生成与视频合成,涵盖选题深化、视觉设计、音频生成、视频制作全流程

55

Quality

63%

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/three-body-video-creator/three-body-video-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-organized, actionable multi-step pipeline with concrete script invocations, explicit validation checkpoints, and feedback branches, backed by a real one-level-deep bundle. It loses points mainly to mild verbosity (repeated persona descriptions) and a few under-specified generation steps.

Suggestions

De-duplicate the character voice/personality descriptions (步骤3 and 步骤10) by referencing character-profiles.md once instead of restating.

Make image-generation (步骤8) actionable with a concrete command or tool invocation like the audio steps, rather than '生成1080P关键帧序列图'.

Tighten the 触发条件/能力包含 preamble and 可选分支 to remove restatable overlap and keep the pipeline lean.

DimensionReasoningScore

Conciseness

Mostly efficient and well-structured with outputs and concise bullet steps, but the 15-step pipeline repeats dialogue/personality descriptions (步骤3 vs 步骤10) and includes some restatable padding (e.g., repeated trigger conditions) that could be trimmed.

3 / 5

Actionability

Provides concrete executable script calls with explicit parameters (voice_generator.py --input ... --output ..., video_compositor.py flags) and a working Python import example; minor gaps are placeholder placeholders for BGM and vague '生成1080P关键帧' without a concrete command.

4 / 5

Workflow Clarity

A clearly sequenced 15-step, three-phase process with explicit validation checkpoints (步骤12 原著合规检测, 步骤13 技术指标检测, 步骤15 五维评审≥80分合格) and feedback loops (可选分支 rework steps 1-3/4-8/11/13); only minor validation gaps keep it from 5.

4 / 5

Progressive Disclosure

Good structure: SKILL.md is an overview pointing to real one-level-deep references (references/*.md, scripts/*.py, assets/*/), all referenced paths exist and are signaled with 'when to read' notes; the inline dialogue/design detail is appropriately placed, with only minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

58%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 niche (《三体》themed AI video creation) and a reasonably specific capability list, but omits an explicit 'Use when...' trigger clause and lacks natural user-said phrasing, which caps completeness and trigger_term_quality at 3.

Suggestions

Add an explicit 'Use when...' / '当用户需要...' trigger clause naming natural phrasings (e.g., 三体视频、威慑纪元短片、AI科幻视频) to raise completeness to 4-5.

Tighten the capability list into concrete distinct verbs (生成配音、设计分镜、合成视频、检测原著合规) rather than broad phase categories.

Include common synonyms/file cues users would say (三体2、罗辑、AI创作大赛) to broaden trigger_term coverage.

DimensionReasoningScore

Specificity

Names the domain (《三体》AI视频创作) and lists several concrete actions (多智能体协作流程、素材生成、视频合成、选题深化、视觉设计、音频生成), but they are phrased as capability categories rather than sharp distinct verbs like the score-5 anchor.

4 / 5

Completeness

Clearly states 'what' the skill does (structured multi-agent workflow + asset generation + video synthesis across four phases) but provides no explicit 'when/Use when' clause, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Contains relevant terms (《三体》、AI视频、视频创作) but lacks natural user phrasing and synonyms/extensions users would actually say; no equivalent of 'Use when...' natural trigger phrases.

3 / 5

Distinctiveness Conflict Risk

The 《三体》 niche and full-pipeline video-creation framing make it clearly distinguishable from generic video skills, with only minor overlap risk against other fandom/video skills.

4 / 5

Total

14

/

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.

Validation15 / 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.