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。

71

Quality

86%

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

73%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.

A well-structured, highly actionable workflow with explicit confirmation checkpoints and real bundle files, weakened mainly by verbosity from inlined prompt templates and a redundant quick-use recap. The compliance and style guidance is genuinely valuable domain knowledge rather than padding.

Suggestions

Move the 7-dimension analysis prompt and the script-generation templates into reference files (e.g. references/analysis-prompt.md, references/script-templates.md) and reference them one level deep to reduce inline length.

Trim or remove the '快速使用' section since it restates the 6-step workflow already detailed above, or replace it with a one-line pointer to the relevant steps.

Resolve the SKILL_DIR placeholder proactively (e.g. provide a one-liner that auto-detects the directory) so the bash commands are copy-paste ready without manual substitution.

DimensionReasoningScore

Conciseness

Mostly efficient, but the ~55-line 7-dimension analysis prompt and the full script-generation templates are inlined, and the '快速使用' section largely restates the 6-step workflow, adding length that could be trimmed or moved to references.

3 / 5

Actionability

Commands are concrete with explicit flags (e.g. 'uv run SKILL_DIR/scripts/download_douyin.py --urls ... --output-dir ...'), but the literal SKILL_DIR placeholder must be resolved before copy-paste, a minor gap versus fully executable.

4 / 5

Workflow Clarity

The 6 steps are clearly sequenced with two explicit 用户确认 checkpoints (Steps 4 and 6), download failure-recovery guidance in Step 2, and parallel-execution guidance in Step 3, matching the top anchor for feedback loops.

5 / 5

Progressive Disclosure

Good structure with a 参考资源 table and one-level-deep references (analysis-dimensions.md, proven-formulas.md, script-style-samples.md, two scripts) that all exist, though large prompt blocks remain inlined rather than split into reference files.

4 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: it states a concrete multi-step capability, lists comprehensive natural trigger terms, and explicitly signals when Claude should use it, all in third person. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

The description 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' — giving comprehensive coverage of the workflow rather than vague language.

5 / 5

Completeness

It explicitly answers both 'what' (the full creation workflow) and 'when' via '当用户提到…时使用此技能' with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

It enumerates eight natural user phrases — '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 synonyms and common variations users would actually say.

5 / 5

Distinctiveness Conflict Risk

The Douyin/TikTok e-commerce script niche with specific triggers like '千川素材' and '种草脚本' is clearly distinct with minimal overlap risk against other skills.

5 / 5

Total

20

/

20

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.