Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
中文简介正在准备中。当前显示原文说明。
Diagnose and fix MARP slide layout issues including whitespace problems, box alignment, bullet formatting, and CSS rendering inconsistencies. Use when MARP slides have visual layout problems or need CSS optimization.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Diagnoses and fixes common MARP slide layout issues including whitespace problems, box alignment, bullet formatting inconsistencies, and responsive design issues. Provides visual diff comparisons and automated CSS fixes for common rendering problems. Outputs actionable fix recommendations with before/after comparisons.
pyyaml (for frontmatter parsing), re (standard library)Parse the MARP markdown file and detect layout issues across multiple categories.
python3 scripts/analyze_marp_layout.py \
--input path/to/slides.md \
--output analysis_report.json
The analyzer checks for:
Read the generated JSON report to understand detected issues.
{
"file": "slides.md",
"timestamp": "2026-04-03T08:00:00Z",
"total_issues": 12,
"issues_by_category": {
"whitespace": 3,
"alignment": 4,
"bullets": 2,
"overflow": 2,
"css": 1
},
"issues": [
{
"id": "WS001",
"category": "whitespace",
"severity": "medium",
"line": 45,
"description": "Double blank line creates excessive gap",
"suggestion": "Remove one blank line",
"auto_fixable": true
}
]
}
Apply auto-fixable issues to generate a corrected MARP file.
python3 scripts/fix_marp_layout.py \
--input path/to/slides.md \
--report analysis_report.json \
--output fixed_slides.md \
--auto-only
Create a side-by-side comparison showing original vs. fixed content.
python3 scripts/generate_diff_report.py \
--original path/to/slides.md \
--fixed fixed_slides.md \
--output diff_report.md
For non-auto-fixable issues, apply manual fixes based on the recommendations in the analysis report. Common manual interventions include:
{
"schema_version": "1.0",
"file": "slides.md",
"timestamp": "2026-04-03T08:00:00Z",
"total_issues": 12,
"auto_fixable_count": 8,
"manual_review_count": 4,
"issues_by_category": {
"whitespace": 3,
"alignment": 4,
"bullets": 2,
"overflow": 2,
"css": 1
},
"issues": [
{
"id": "WS001",
"category": "whitespace",
"severity": "low|medium|high",
"line": 45,
"column": 0,
"description": "Description of the issue",
"suggestion": "How to fix it",
"auto_fixable": true,
"context": "surrounding code snippet"
}
],
"css_analysis": {
"total_rules": 25,
"redundant_rules": 2,
"specificity_warnings": 1
}
}
# MARP Layout Diff Report
## Summary
- **Original file**: slides.md
- **Fixed file**: fixed_slides.md
- **Issues fixed**: 8
- **Issues remaining**: 4
## Changes by Category
### Whitespace Fixes
| Line | Original | Fixed |
|------|----------|-------|
| 45 | `\n\n\n` | `\n\n` |
### Alignment Fixes
...
## Remaining Manual Issues
1. **Line 78**: Complex flexbox layout needs restructuring
- Suggestion: Simplify to single-direction flex container
scripts/analyze_marp_layout.py -- Main analysis engine detecting layout issuesscripts/fix_marp_layout.py -- Automated fix applicationscripts/generate_diff_report.py -- Visual diff report generatorreferences/marp-layout-patterns.md -- Common MARP layout patterns and anti-patternsreferences/css-fix-catalog.md -- Catalog of CSS fixes for common issues还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
中文简介正在准备中。当前显示原文说明。
AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.
中文简介正在准备中。当前显示原文说明。
Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.
中文简介正在准备中。当前显示原文说明。
AI(LLM)が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン(視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー)を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 (バランスを崩す・客観を崩す・論理を崩す)でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。
中文简介正在准备中。当前显示原文说明。
Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.
中文简介正在准备中。当前显示原文说明。
Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.
中文简介正在准备中。当前显示原文说明。