CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-douyin-script

抖音爆款脚本创作工作流。从竞品视频拆解到脚本生成的完整流程:下载抖音视频→Gemini视频分析→爆款公式提炼→脚本+分镜生成→AI味审校。 当用户提到"抖音脚本"、"爆款拆解"、"竞品分析"、"带货脚本"、"千川素材"、"种草脚本"、"视频拆解"、"抖音视频分析"时使用此技能。

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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 workflow, validation checkpoints, and verified bundle references. Its main weaknesses are verbosity from large inline prompt templates and content that could be split into reference files for better progressive disclosure.

Suggestions

Move the large inline prompt templates (the 7-dimension analysis prompt and the 种草/千川 script-generation templates) into reference files under references/ and link to them from their respective steps to improve conciseness and progressive disclosure.

Consider extracting the 广审合规 check rules (检查4) into a dedicated references/compliance-rules.md, keeping only a concise checklist inline in Step 6.

The inlined AI味 and 口语化 rules currently reference external skills ("视频脚本口语化审校", "ai-taste-proofreading") — either bundle those rule summaries into a local reference file or inline only the minimal actionable checklist to avoid reliance on skills that may not be present.

DimensionReasoningScore

Conciseness

Largely operational and free of concept-explanation fluff, but the large inline prompt templates (7-dimension analysis prompt, two script-generation templates) could be tightened or moved to references to reduce the main file's token load.

2 / 3

Actionability

Provides copy-paste-ready executable commands (e.g. "uv run SKILL_DIR/scripts/download_douyin.py --urls ..." and "uv run SKILL_DIR/scripts/analyze_video.py ...") with documented parameters and complete prompt templates.

3 / 3

Workflow Clarity

A clearly sequenced 6-step workflow with explicit user-confirmation checkpoints (Step 4, Step 6), download-failure error recovery, and a 5-item compliance validation checklist with rewrite feedback.

3 / 3

Progressive Disclosure

Three real reference files and two scripts are well-signaled and one-level-deep with a navigation table, but substantial reusable prompt templates are inlined in the body rather than split into reference files.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete sequenced actions, explicit trigger guidance, and a clearly bounded niche. It satisfies the what/when/when-to-use requirements with no over-claiming or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in sequence: "下载抖音视频→Gemini视频分析→爆款公式提炼→脚本+分镜生成→AI味审校" — five specific operations, not vague language.

3 / 3

Completeness

Explicitly answers what ("抖音爆款脚本创作工作流...完整流程") and when ("当用户提到...时使用此技能"), with an explicit Use-when clause present.

3 / 3

Trigger Term Quality

Provides eight natural terms users would say ("抖音脚本"、"爆款拆解"、"竞品分析"、"带货脚本"、"千川素材"、"种草脚本"、"视频拆解"、"抖音视频分析"), covering common variations.

3 / 3

Distinctiveness Conflict Risk

Clear niche (抖音爆款脚本创作) with distinct triggers unlikely to fire for unrelated skills; no overlap with generic document/code skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alchaincyf/huashu-skills
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.