CtrlK
BlogDocsLog inGet started
Tessl Logo

poetry-music-visual

内容创作者与影片与视频编辑在制作古诗词MV或文化可视化内容时,使用本技能深度解析诗词意境,一键生成AI绘画配图场景描述与Suno专属纯音乐配乐蓝图,轻松完成视听双重艺术转化,让古典诗词焕发新生。

66

Quality

79%

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/poetry-music-visual/poetry-music-visual/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable, well-structured skill body: the Suno format spec and worked blueprints make the outputs copy-paste ready, and bundle files are properly split and clearly indexed. The main weaknesses are duplicated follow-up guidance between the '用户引导' and '使用流程建议' sections and three near-complete inline examples that inflate token cost.

Suggestions

Merge the '用户引导' list into the '使用流程建议' section — both enumerate the same follow-up options (生成配图 / 调整风格 / 修改情绪), so one canonical list removes the duplication.

Keep one full worked example (e.g., 静夜思) in the body and move the second full blueprint (山居秋暝) plus the generic structure walkthrough into a separate examples file referenced from '资源索引' to cut body length.

Add an explicit output checkpoint before presenting results — e.g., '呈现前对照 assets/output-templates.md 检查配图描述与配乐蓝图格式' — to convert the implicit format expectation into a validation step.

DimensionReasoningScore

Conciseness

The body is mostly efficient — the Suno tag taxonomy and format spec are things Claude does not reliably know, so they earn their tokens — but it includes unnecessary repetition: the '用户引导' list and the '使用流程建议' section both enumerate the same follow-up options (生成实际配图 / 调整配图风格 / 修改配乐情绪), and three complete Suno blueprints (one generic walkthrough plus two full poem examples) are inlined where one plus a pointer would do. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') rather than 4, where over-explanation would be only minor.

3 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact style-tag categories with a concrete comma-separated example, the full set of Suno structure tags, copy-paste-ready director commands in parentheses, and two complete worked blueprints (静夜思, 山居秋暝) covering the common melancholic and tranquil cases — matching anchor 5's 'copy-paste ready… specific examples cover the common cases'. It is not below 5 because no step is left abstract.

5 / 5

Workflow Clarity

The four-step sequence (解析 → 配图设计 → 配乐蓝图 → 整合与优化) is clearly ordered, includes a consistency-check step ('风格一致性检查', '节奏匹配', '情绪递进'), and closes with an explicit user-feedback iteration loop ('如需迭代,基于用户反馈优化'). This matches anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5 because there is no explicit checkpoint for verifying the generated image description or blueprint is well-formed before presenting it.

4 / 5

Progressive Disclosure

The body is a clear overview-plus-procedure, and the '资源索引' section signals all three bundle files with one-line purposes ([references/poetry-imagery.md], [references/music-style-guide.md], [assets/output-templates.md]), all of which exist and are one level deep — good structure per anchor 4. It falls short of 5 because two full worked examples plus a complete generic Suno walkthrough are inlined in the body where an examples file would keep the main file lean, a minor placement gap.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description that explicitly states both what the skill does and when to use it, with a distinct niche and natural trigger keywords. Its main weakness is marketing-style padding ('一键生成', '轻松完成', '让古典诗词焕发新生') that inflates length without adding capability information, plus a few missing synonym trigger terms.

Suggestions

Trim the marketing phrases ('一键生成', '轻松完成视听双重艺术转化', '让古典诗词焕发新生') and lead with the concrete actions instead, e.g. '解析古诗词的意象与情感,生成AI绘画配图场景描述与Suno纯音乐配乐蓝图。用于制作古诗词MV、诗词配图或文化可视化内容时。'

Add a couple of common synonym trigger terms (e.g., 插图、BGM、生图提示词/prompt) so users phrasing the request differently still hit the skill.

DimensionReasoningScore

Specificity

The description lists several concrete actions — '深度解析诗词意境' (deeply analyze poetic mood), '生成AI绘画配图场景描述' (generate AI image scene descriptions), and 'Suno专属纯音乐配乐蓝图' (Suno music blueprint) — but anchor 5 is not reached because of marketing padding like '一键生成' (one-click), '轻松完成' (effortlessly complete), and '让古典诗词焕发新生' (breathe new life into poetry), which the guidelines explicitly penalize as fluff and over-claims.

4 / 5

Completeness

Both 'what' and 'when' are answered clearly and explicitly with concrete trigger phrases: the 'when' is '在制作古诗词MV或文化可视化内容时' (when producing classical-poetry MVs or cultural visualization content), and the 'what' enumerates the analysis, image-description, and music-blueprint capabilities. It is not a 4 because the 'when' clause is already explicit and specific rather than something that could be made clearer.

5 / 5

Trigger Term Quality

It includes natural terms users would actually say — '古诗词MV', '配图', '配乐', 'Suno', '文化可视化', '影片与视频编辑' — giving good keyword coverage, but falls short of anchor 5's comprehensive synonym coverage (e.g., missing variations like 插图, BGM/背景音乐, 生图/prompt, 诗词歌曲).

4 / 5

Distinctiveness Conflict Risk

The 古诗词MV / Suno 配乐 / 文化可视化 niche is well differentiated from most skills, matching anchor 4 ('mostly distinct; minor overlap risk'), but there is residual overlap risk with generic AI-image-prompt generation skills ('AI绘画配图场景描述') and general music-generation skills, so anchor 5's 'minimal conflict risk' is not fully met.

4 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.