ian-xiaohei-illustrations

生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务；默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。

Quality

92%

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

Quality

Content

85%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.

A well-structured, actionable multi-step workflow with a real validation/feedback loop and clean one-level-deep references. Its lone weakness is mild redundancy between the generation-time forbidden-style list and the QA failure-mode list, which keeps conciseness below full marks.

Suggestions

Consolidate the forbidden-style rules into one place — the '禁止 PPT、商业插画、幼稚可爱…' list in step 3 and the '太像流程图/PPT…画风太可爱' list in step 4 overlap; keep them as generation constraints and have step 4 reference them rather than restating.

Trim the 核心定位 framing where it restates the frontmatter description; the body can assume the purpose is known and lead directly into the workflow.

Since references/prompt-template.md already holds the prompt template, have step 3 reference it rather than re-listing all required prompt elements inline.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-dense with no padding about concepts Claude already knows, but the forbidden-style list in step 3 ('禁止 PPT、商业插画、幼稚可爱…') overlaps the QA failure modes in step 4 ('太像流程图/PPT…画风太可爱、幼稚'), so it could be tightened — matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	Instruction-only but highly actionable: concrete prompt elements (16:9, 纯白背景, 黑色手绘线稿), explicit tool use (内置 image_gen, 每张单独生成), specific counts (4-8 张), and copy-ready save paths (assets/<article-slug>-illustrations/, 01-topic-name.png) — satisfying 'specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	A clear five-step sequence (消化正文 → 配图策略 → 单张生成 → 检查与迭代 → 保存交付) with an explicit validation checkpoint in step 4 referencing qa-checklist.md and a feedback loop (优先重生成或局部编辑), plus a non-destructive save safeguard — matching 'clear sequence with explicit validation steps'.	3 / 3
Progressive Disclosure	The body is an overview pointing to five real, one-line-described reference files (all verified present in ./references/) and assets/examples/, each exactly one level deep with no nested see-also chains — matching 'clear overview with well-signaled one-level-deep references'.	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.

A strong, third-person description that crisply states a distinctive purpose, an explicit use-when clause, and a rich set of natural trigger terms. Its only soft spot is verbosity — the dense trigger enumeration could be trimmed slightly without losing signal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (生成配图, 配图建议/shot list, 去标题/改图) plus specific style parameters (16:9 纯白手绘, 少量红橙蓝批注), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states both what ('生成 Ian 风格的中文正文配图') and when ('用于用户要求为中文文章…生成…等任务'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor; not capped at 2 because the 'Use when' equivalent is present.	3 / 3
Trigger Term Quality	Extensive coverage of natural user terms in quotes ('怪诞''小黑''手绘''正文配图''文章插图''shot list''去标题/改图') alongside concrete context types (文章、帖子、博客、Notion 文档), matching 'good coverage of natural terms users would say'.	3 / 3
Distinctiveness Conflict Risk	A narrow, distinctive niche (Ian 风格小黑中文正文配图) with idiosyncratic triggers unlikely to fire for unrelated skills, matching 'clear niche with distinct triggers'.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: helloianneo/ian-xiaohei-illustrations
Path: ian-xiaohei-illustrations/SKILL.md
Commit: 91b5608

Reviewed: ~1 month 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.