SkillAtlasSkill 详情

markdown

This is the open-source content repository behind

审核状态:已审核Quality 80Security 80

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年9月3日

Skill Store — Marketplace Repository

This is the open-source content repository behind Skill Store. It stores every approved Agent Skill, the records that go with it, and the automated security audits published with each skill.

This repo is a companion to the Skill Store platform, not the place to submit skills. Skills are added through skillstore.io — its review pipeline writes to this repo automatically. Please do not open a pull request here to add a skill; PRs adding skills will be closed. See Contributing a skill below.

Installing a skill

The recommended way to install any skill is the skillstore CLI — one command works for both Claude Code and Codex:

npx skillstore add author/skill-name

For example:

npx skillstore add aiskillstore/code-review

It downloads the skill and drops it into the right skills/ directory for your tool. Claude Code auto-discovers it; for Codex, restart the session.

Prefer to do it by hand, or installing via Claude Web? See the full Installation Guides for every method (CLI, manual, and ZIP upload) and the scope directories (~/.agents/skills/, .claude/skills/, ~/.claude/skills/, .codex/skills/, …).

Contributing a skill

Submit through the platform — not through a pull request:

  1. Go to skillstore.io/submit.
  2. Enter the GitHub repository URL that contains your SKILL.md.
  3. Your submission runs through automated security analysis.
  4. A maintainer reviews and approves it.
  5. On approval, the skill is published here and appears on skillstore.io.

What makes a valid skill

  • SKILL.md — the skill definition (required, per the Agent Skills spec)
  • Supporting files the skill references (optional)
  • LICENSE (recommended)

Security audit

Every submission is scanned automatically before it can be published. The audit flags things like:

  • Dangerous code patterns (eval, exec, raw system commands)
  • File access outside the project scope
  • Network calls to external hosts
  • Obfuscated or minified code
  • Credential / secret handling

Security analysis is report-only: findings inform maintainers and users, but a risk result does not automatically block an otherwise approved skill from being published. See our Security Trust Center for the methodology, limitations, and risk-level definitions.

Live Security Passport example:

Skillstore security

Repository layout

.
├── skills/        # Approved, published skills (one folder each, with SKILL.md)
├── pending/       # Submissions awaiting review
├── packages/
│   ├── cli/       # The `skillstore` CLI (npx skillstore add …)
│   └── skillstore/
├── schemas/       # JSON schemas for skill records
├── scripts/       # Maintenance & scoring scripts
└── .github/workflows/   # Submission, audit, and sync automation

The contents of this repo are maintained by Skill Store's automated pipeline. Manual changes are limited to maintainers.

Links

License

The marketplace catalog is MIT-licensed. Individual skills carry their own licenses — check each skill's LICENSE file.

其他

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:2 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/46ki75/markdown" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/46ki75/markdown" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/46ki75/markdown" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/46ki75/markdown" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/46ki75/markdown" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: markdown
description: >
  Markdown linting and automated fixing using markdownlint-cli2. Use when Claude needs to: (1) Check markdown files for style issues, (2) Fix markdown formatting problems, (3) Ensure markdown follows best practices, (4) Validate markdown documents, or (5) Apply consistent markdown styling

Markdown Lint

Automated markdown validation and fixing using markdownlint-cli2.

Workflow Overview

1. Run auto-fix     → markdownlint-cli2 --fix <file>
2. Check remaining  → markdownlint-cli2 <file>
3. Fix manually     → str_replace for structural issues
4. Verify           → markdownlint-cli2 <file> (should show 0 errors)

Expected results: Auto-fix resolves 70-90% of issues. Remaining 3-5 issues require manual correction.

Basic Commands

# Auto-fix single file
markdownlint-cli2 --fix document.md

# Check file
markdownlint-cli2 document.md

# Multiple files
markdownlint-cli2 --fix file1.md file2.md

# All markdown in directory
markdownlint-cli2 --fix "**/*.md"

# With custom config
markdownlint-cli2 --config .markdownlint.json document.md

File Paths

# Uploaded files
markdownlint-cli2 --fix /mnt/user-data/uploads/document.md

# Working directory
markdownlint-cli2 --fix /home/claude/document.md

# Output to user
cp /path/to/fixed.md /mnt/user-data/outputs/

Manual Fixes Required

Auto-fix cannot resolve these issues - they need Claude's judgment:

MD025 - Multiple H1 Headers

Why: Requires understanding document hierarchy
Fix: Convert extra H1s to appropriate level

# Main Title

# Second Title → Change to: ## Second Title

MD036 - Emphasis as Header

Why: Requires determining author intent
Fix: Replace bold/italic with proper header

**Section Title** → Change to: ## Section Title

MD013 - Line Too Long

Why: Requires deciding where to break content
Fix: Wrap at natural points (spaces, punctuation)

This is a very long line exceeding 80 characters that needs wrapping.
↓
This is a very long line exceeding 80 characters that needs
wrapping.

Exception: URLs typically exempt

MD041 - Missing First Line Header

Why: Requires structural decision
Fix: Add H1 at start or restructure

Execution Pattern

For Uploaded Files

# 1. Auto-fix
markdownlint-cli2 --fix /mnt/user-data/uploads/document.md

# 2. Check remaining
markdownlint-cli2 /mnt/user-data/uploads/document.md
# Output: "Summary: 3 error(s)"
# Lists specific errors like "MD025/single-title Multiple top-level headings"

# 3. Manual fixes (example)
str_replace "# Extra Title" → "## Extra Title"

# 4. Verify
markdownlint-cli2 /mnt/user-data/uploads/document.md
# Output: "Summary: 0 error(s)"

# 5. Output
cp /mnt/user-data/uploads/document.md /mnt/user-data/outputs/

For New Content

create_file /home/claude/doc.md "content..."
markdownlint-cli2 --fix /home/claude/doc.md
markdownlint-cli2 /home/claude/doc.md
# Fix remaining issues if any
cp /home/claude/doc.md /mnt/user-data/outputs/

Configuration

Create .markdownlint.json to customize rules:

{
  "default": true,
  "MD013": { "line_length": 120 },
  "MD033": false
}

Common adjustments:

  • "MD013": false - Disable line length checking
  • "MD013": { "line_length": 120 } - Increase limit to 120
  • "MD013": { "code_blocks": false } - Exclude code blocks
  • "MD033": false - Allow HTML
  • "MD041": false - Don't require first line header

Config file search order:

  1. .markdownlint-cli2.jsonc
  2. .markdownlint-cli2.yaml
  3. .markdownlint.jsonc / .markdownlint.json
  4. .markdownlint.yaml / .markdownlint.yml

Reporting to User

Provide clear summary of fixes:

✅ Markdown linting complete!

Initial: 18 errors
After auto-fix: 4 errors
Manual fixes:
  • MD025: Converted 2 H1 headers to H2
  • MD036: Replaced bold with proper header
  • MD013: Wrapped long line

Final: 0 errors

Error Count Interpretation

Before auto-fix:

  • 0-5: Minor issues
  • 6-15: Moderate issues
  • 16+: Significant issues

After auto-fix:

  • 0-2: Excellent
  • 3-5: Typical
  • 6+: Check if config needed

Common Fix Patterns

# Multiple H1s - analyze structure first
# If sections: convert to H2
str_replace "# Introduction" → "## Introduction"

# If subsections: convert to H3
str_replace "# Details" → "### Details"

# Emphasis as headers - determine appropriate level
str_replace "**Important**" → "## Important"
str_replace "_Note_" → "### Note"

# Long lines - break at natural points
# After conjunctions: and, but, or
# After punctuation: , . ;
# Preserve URLs on single line

Troubleshooting

Auto-fix not working:

# Check file exists
view /path/to/file.md

# Verify permissions
ls -l /path/to/file.md

# Use absolute path
markdownlint-cli2 --fix /full/path/to/file.md

Too many errors after auto-fix:

# Create relaxed config
echo '{"MD013": false, "MD041": false}' > .markdownlint.json
markdownlint-cli2 --config .markdownlint.json --fix file.md

Specific rule causing issues:

  • Disable in config: "MD013": false
  • Or adjust parameters: "MD013": { "line_length": 120 }

When NOT to Lint

Skip linting when:

  • Code examples intentionally violate rules
  • Embedded HTML/JSX required (disable MD033)
  • Generated docs with different conventions
  • Legacy docs where changes break references

Use custom config to disable problematic rules.

Quick Rule Reference

Most common rules Claude will encounter:

  • MD001 - Header increment by one level
  • MD004 - Consistent list markers
  • MD009 - No trailing spaces
  • MD010 - No hard tabs
  • MD012 - No multiple blank lines
  • MD013 - Line length (default: 80)
  • MD018 - Space after # in headers
  • MD022 - Blank lines around headers
  • MD025 - Single H1 only
  • MD031 - Blank lines around code
  • MD032 - Blank lines around lists
  • MD034 - Bare URLs in <>
  • MD036 - No emphasis as headers
  • MD040 - Language for code blocks

Full rule documentation: https://github.com/DavidAnson/markdownlint/blob/main/doc/Rules.md

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!