一键导入
markdown-report
Best practices for creating well-structured markdown reports, summaries, documentation, and written deliverables saved to files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Best practices for creating well-structured markdown reports, summaries, documentation, and written deliverables saved to files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Authoritative user guide + reference map for Mux-Swarm itself (v0.12.1). Use when the user asks how Mux works, how to configure it, what a command/flag/config-key does, how modes/teams/sandbox/auth/ACP/delegation work, or how to troubleshoot Mux. Points to exact sections in the bundled DOCS.md instead of dumping it.
Structured diff and PR code review with a prioritized checklist. Use when reviewing staged changes, pull requests, or any code diff before merge.
Profile, clean, and analyze tabular data (CSV/JSON/Parquet) with pandas/polars. Use when exploring datasets, computing aggregations, joining tables, resampling time series, or producing analysis charts.
Find vulnerable and outdated dependencies across ecosystems (Python, Node, .NET, Rust, Go). Use when auditing a project for CVEs, preparing a release, or investigating a security report.
Design distinctive, polished UI that avoids generic 'AI slop'. Use when making visual design decisions: typography, color, spacing, hierarchy, motion, and component composition.
Run real SAST and secret-scanning tools locally (semgrep, bandit, gitleaks, trivy). Use when auditing a codebase for vulnerabilities, exposed secrets, or vulnerable dependencies before shipping or on demand.
| name | markdown-report |
| description | Best practices for creating well-structured markdown reports, summaries, documentation, and written deliverables saved to files. |
Use this skill when producing any written deliverable that will be saved as a markdown file — research reports, summaries, documentation, analysis, meeting notes, or any structured text output.
Every report should follow this skeleton:
# Title
> One-line summary of what this document covers and its key conclusion.
## TL;DR
- 3-5 bullet points capturing the most important findings
- A reader who only reads this section should understand the main takeaways
## Section 1: [Topic]
Body text organized by subtopic, not by source.
## Section 2: [Topic]
Continue with the next logical section.
## Conclusion
Brief synthesis — what does this all mean? What are the implications or next steps?
## Sources
- [Source Name](URL) — accessed YYYY-MM-DD
When comparing options, features, or data points, always use a table:
| Feature | Option A | Option B | Option C |
|---------|----------|----------|----------|
| Price | $10/mo | $25/mo | Free |
| Speed | Fast | Faster | Slow |
Never write "Option A costs $10/mo and is fast, while Option B costs $25/mo and is faster..." — that belongs in a table.
When including code, commands, or technical output:
python, bash, ```jsonquarterly-report.md, api-comparison.md2026-02-20-market-analysis.mdreport.md is useless, q1-2026-sales-analysis.md is clearFor important documents, include a metadata block at the top:
---
title: Q1 2026 Market Analysis
date: 2026-02-20
author: Mux Agent
status: final
---