CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-card

Content caster (铸). Transforms content into PNG visuals. Seven molds: -l (default) long reading card, -i infograph, -m multi-card reading cards (1080x1440), -v editorial sketchnote (problem→failure→pivot→insight→naming, magazine + archive layout), -c comic (manga-style B&W), -w whiteboard (marker-style board layout), -b big-fonts attachment card (1080x1440, weathered 碑刻 style for 小红书). Output to ~/Downloads/. Use when user says '铸', 'cast', '做成图', '做成卡片', '做成信息图', '做成海报', '视觉笔记', 'sketchnote', '杂志', 'editorial', '漫画', 'comic', 'manga', '白板', 'whiteboard', '大字', '附件图', 'big fonts', '小红书卡片'. Replaces ljg-cards and ljg-infograph.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

87%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 a lean, well-structured dispatcher with concrete commands and excellent one-level-deep progressive disclosure into the mode files and templates. Its main weakness is workflow clarity: the end-to-end flow lacks an explicit validation/verification checkpoint before delivery, particularly for the multi-card batch mode.

Suggestions

Add an explicit verification checkpoint before 交付, e.g. '渲染后确认 PNG 尺寸/张数符合模具要求,再报告路径', so the flow has a validate→fix→retry feedback loop.

For the '-m' multi-card (batch) path, state how to verify all cards were generated and cut correctly before reporting delivery.

Number the core steps (获取内容 → 命名 → 选模具/Read mode → 渲染 → 截图 → 验证 → 交付) so the sequence and its checkpoint are explicit rather than implied by section order.

DimensionReasoningScore

Conciseness

Lean and efficient — '内容进去,PNG 出来。模具决定形状。' plus compact tables and terse rules; it does not explain concepts Claude already knows and every section earns its place, matching the score-3 'lean and efficient' anchor rather than the score-2 'mostly efficient but could be tightened'.

3 / 3

Actionability

Provides concrete, executable guidance: a copy-paste capture command ('node assets/capture.js <html> <png> <width> <height> [fullpage]'), an error-recovery command, a concrete footer HTML snippet, and an execution table mapping each mode to exact mode-file and template paths; matches the score-3 'fully executable code/commands; specific examples' anchor.

3 / 3

Workflow Clarity

A sequence is present via ordered sections (获取内容→文件命名→截图→Footer→交付) and the execution table, with one reactive error-recovery loop for capture, but there is no explicit validation/verification checkpoint before delivery (e.g., confirm the rendered PNG is correct) and the multi-card '-m' batch path has no verification; this fits the score-2 'steps listed but validation gaps; checkpoints missing or implicit' rather than the score-3 'explicit validation steps'.

2 / 3

Progressive Disclosure

Clear overview that points to one-level-deep references with explicit navigation ('先 Read references/taste.md' and a table mapping each parameter to its references/mode-*.md and assets/*_template.html); all referenced bundle files exist on disk, matching the score-3 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

11

/

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.

The description is specific, trigger-rich, and complete, clearly stating both what the skill does and exactly when to invoke it via a comprehensive bilingual set of trigger terms. It is a strong, low-conflict description with no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions via seven named molds each described concretely ('-l long reading card', '-c comic (manga-style B&W)', '-b big-fonts attachment card (1080x1440, weathered 碑刻 style for 小红书)'), matching the 'Lists multiple specific concrete actions' anchor rather than the score-2 'names domain and some actions'.

3 / 3

Completeness

Explicitly answers both what ('Transforms content into PNG visuals. Seven molds: ...') and when ('Use when user says ...'), with an explicit 'Use when' trigger clause matching the score-3 anchor; the score-2 anchor requires 'when' to be missing or only implied, which is not the case here.

3 / 3

Trigger Term Quality

Provides good coverage of natural terms users would actually say across both languages ('铸', 'cast', '做成图', '做成卡片', '做成信息图', '做成海报', '视觉笔记', 'sketchnote', '漫画', 'comic', '白板', 'whiteboard', '大字', '附件图', '小红书卡片'), matching the score-3 anchor; not merely 'Works with PDF files'-level partial coverage.

3 / 3

Distinctiveness Conflict Risk

Clear niche (content→PNG visual cards) with distinct, specific triggers unlikely to fire for unrelated skills, and it clarifies lineage with 'Replaces ljg-cards and ljg-infograph'; matches the score-3 'clear niche with distinct triggers' anchor rather than the score-2 'could still overlap'.

3 / 3

Total

12

/

12

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
lijigang/ljg-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.