Name: card-news-generator-v2
Rating: 54.400000000000006 (1 reviews)
Author: bear2u

card-news-generator-v2

Create 600x600 Instagram-style card news series automatically with optional background images. User provides topic, colors, and optional images - Claude generates content and creates multiple cards with proper text wrapping.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/card-news-generator-v2/SKILL.md

The canonical home for this skill is card-news-generator-v2 in bear2u/my-skills

Quality

Content

65%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 highly actionable with complete executable commands covering all generation modes, but it is somewhat padded with redundant examples and lacks an explicit verification step for its batch card-generation workflow. Splitting reference material (colors, technical specs) into bundled files and adding an output-verification checkpoint would improve it.

Suggestions

Add an explicit verification step after auto-generation (e.g., confirm the expected `_<NN>.png` files exist and report count) to satisfy the batch-operation feedback-loop requirement.

Move the recommended-color table, canvas/technical specifications, and full parameter reference into bundled reference files (e.g., references/COLORS.md, references/SPEC.md) and link them from SKILL.md.

Trim redundancy — the 'Example Workflows' section repeats the example conversations and command patterns already shown in 'Core Workflow', so consolidate to one canonical example per mode.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but includes redundant sections (example conversations duplicated by 'Example Workflows', good/bad content examples, recommended-color tables, and soft padding like 'Total time: ~30 seconds') that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands with complete flags and heredoc content for both solid-color and background-image modes, plus single-card variants and a runnable RGB→hex snippet.	5 / 5
Workflow Clarity	The four-step AUTO workflow is clearly sequenced, but this batch operation (generating 5–7 cards at once) lacks an explicit verification checkpoint confirming outputs were created; error handling is reactive, capping workflow clarity at 3.	3 / 5
Progressive Disclosure	Section structure is present, but the ~300-line single file inlines content that could live in references (recommended colors, technical/canvas specs, parameter reference) and there are no external file references to offload detail.	3 / 5
	Total	14 / 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 concretely states what the skill does and occupies a distinct niche, but it omits an explicit 'when to use' trigger clause and relies on domain keywords without the natural user phrases. Adding a 'Use when...' sentence with common request phrasings would raise completeness and trigger quality.

Suggestions

Append an explicit trigger clause such as 'Use when the user asks for card news, Instagram-style card series, or visual card content (e.g., 카드 뉴스 만들어줘).'

Add natural-language synonyms and the Korean request phrasings already present in the body so the description surfaces the terms users actually say.

Optionally mention the single-card generation mode to broaden coverage of the skill's concrete capabilities.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Create 600x600 Instagram-style card news series', 'generates content and creates multiple cards with proper text wrapping', 'optional background images' — with only minor coverage gaps (e.g., single-card mode is not mentioned).	4 / 5
Completeness	Clearly answers 'what' (generate content and create multi-card series with text wrapping and image support) but lacks any explicit 'Use when...' trigger clause, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Contains relevant domain keywords like 'Instagram-style card news series' and 'background images', but misses the natural user phrasing (e.g., Korean '카드 뉴스 만들어줘') and common synonyms that appear only in the body.	3 / 5
Distinctiveness Conflict Risk	The '600x600 Instagram-style card news series' niche is fairly distinct with minimal overlap risk against other skills, though it could be sharper with explicit triggers.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: bear2u/my-skills
Path: .claude/skills/card-news-generator-v2/SKILL.md
Commit: 8ed5784

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.