sn-md-to-html-report

将 Markdown 报告、研究笔记、行业分析、战略备忘录、技术白皮书、复盘、周报等长文档，重组并创作为有编辑判断、网页美感和证据秩序的自包含 HTML 专题页。用户要求“转成 HTML”“网页化报告”“美化报告”“做成专题页”“便于分享”“提升可读性/设计感”“把报告做成网页”时使用。必须先写 plan.md 再写 HTML，保留原文事实断言和结论强度，不套模板，不做机械 Markdown 转换。

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured design skill with a concrete staged workflow, explicit validation gates, and clean one-level-deep progressive disclosure into four real reference files. Its main weakness is verbosity in the abstract design-philosophy sections, which could be condensed without losing the skill's unique editorial value.

Suggestions

Condense the 设计判断原则 and 设计知识的使用方式 sections into tighter imperative rules; the abstract prose (e.g. '优雅不等于少，也不等于多') restates design judgment Claude largely already applies.

Move the most philosophical design principles into a reference file (e.g. references/01) and keep SKILL.md focused on the actionable workflow, contract, and rules, reducing token load at the top level.

Convert remaining principle statements from descriptive ('文字系统承载页面性格') to prescriptive checklist form ('字体配对须非通用组合；建立字阶并设定字重/字宽/间距') to tighten and increase actionability.

Dimension	Reasoning	Score
Conciseness	The procedural sections (工作流, plan.md 必须包含, HTML 要求) are efficient, but the 设计判断原则 and 设计知识的使用方式 sections are abstract design philosophy (e.g. "让文字排印本身成为设计中可被记住的一部分", "优雅不等于少，也不等于多") that elaborates on judgment rather than adding only what Claude does not know, so it could be tightened.	2 / 3
Actionability	As an instruction-only skill it gives concrete, specific guidance: a staged 8-step workflow, a compact token system with named fields (Color = 4-6 hex, Type = display/body/utility/mono, ASCII wireframe, Signature), and an enumerated set of required plan.md sections — actionable and template-ready.	3 / 3
Workflow Clarity	Eight clearly sequenced steps with explicit gates — "没有完整 plan 不动 HTML", "checklist 是开工前的契约，不是事后补救" — and a fix-loop review ("按检查角度逐项检查；未通过就修正"), matching the anchor for clear sequence with validation steps and feedback loops.	3 / 3
Progressive Disclosure	The body points to four real one-level-deep reference files (references/01–04), each clearly signaled at an exact workflow stage (e.g. "brainstorm 短设计计划前，读 references/01-aesthetic-direction.md"), with the overview kept inline and details appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 clearly states concrete capabilities and provides an explicit 'Use when' clause with natural trigger phrases. It distinguishes the skill well and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "重组并创作为...自包含 HTML 专题页", "先写 plan.md 再写 HTML", "保留原文事实断言和结论强度", "不套模板，不做机械 Markdown 转换" — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ("将 Markdown 报告...重组并创作为...HTML 专题页") and when ("用户要求...时使用"), an explicit 'Use when' equivalent, so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes natural user phrases a person would actually say — "转成 HTML", "网页化报告", "美化报告", "做成专题页", "便于分享", "提升可读性/设计感", "把报告做成网页" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche — long-form Markdown documents transformed into editorial single-file HTML 专题页 — with triggers specific to the report-to-webpage task, making conflict with other skills unlikely.	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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-md-to-html-report/SKILL.md
Commit: 179fea1

Reviewed: 2 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.