Skill: Export

## Purpose

154 stars
Complexity: easy

About this skill

The Export skill automates the process of transforming complex analytical results into various accessible formats suitable for different stakeholders. After an analysis or pipeline run is complete, the skill intelligently locates the latest relevant output material—prioritizing slide decks, narrative analyses, pipeline summaries, or storyboards. It then uses this source material to generate professional documents and data exports. Users can specify the desired output format, such as a full Marp slide presentation, a concise executive summary email, a quick Slack update, a detailed 1-page decision brief, or raw data tables in CSV. The skill is designed to handle different tones and content structures for each format, ensuring the message is tailored for its intended audience, from executive-friendly summaries to bullet-point updates. This capability significantly enhances productivity by rapidly creating professional communication pieces from analysis work.

Best use case

The primary use case is the rapid dissemination of analytical insights and data to various internal or external audiences after an analysis project or automated pipeline has concluded. It benefits analysts, project managers, and team leads who need to quickly communicate findings, recommendations, or data to executives, team members, or clients without manually reformatting information for each channel.

## Purpose

The user should expect to receive one or more clearly formatted output files (e.g., `.md`, `.csv`) containing the analysis results tailored to the requested format and audience.

Practical example

Example input

/export email

Example output

A Markdown file (`outputs/email_summary_DATE.md`) containing a 3-paragraph executive summary email with a subject line, key finding, and recommendation based on the latest analysis.

When to use this skill

  • When the user explicitly requests to `/export` or "export this as..."
  • Immediately after a data analysis or pipeline execution is finished.
  • When findings need to be communicated in a specific, formatted document or message.
  • To quickly generate multiple communication artifacts (e.g., slides, email, Slack) from a single analysis.

When not to use this skill

  • When no analysis results or source material are available.
  • When raw, unformatted data is needed without any interpretation or presentation layers.
  • When extensive custom formatting or highly artistic design is required beyond the predefined templates.
  • If the user needs to *perform* analysis rather than just *export* its results.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/export/SKILL.md --create-dirs "https://raw.githubusercontent.com/ai-analyst-lab/ai-analyst/main/.claude/skills/export/skill.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/export/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Skill: Export Compares

Feature / AgentSkill: ExportStandard Approach
Platform SupportClaudeLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

## Purpose

Which AI agents support this skill?

This skill is designed for Claude.

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Skill: Export

## Purpose
Export analysis results in different formats for different audiences. Converts
pipeline outputs into ready-to-share deliverables.

## When to Use
- User says `/export` or "export this as..." or "send this to..."
- After completing an analysis or pipeline run
- When the user needs results in a specific format

## Invocation
`/export slides` — generate/refresh Marp slide deck from latest analysis
`/export email` — write an executive summary email (markdown)
`/export slack` — write a concise Slack update (markdown)
`/export brief` — write a 1-page decision brief (markdown)
`/export data` — export analysis data tables as CSV
`/export all` — generate all text formats + data

## Instructions

### Step 1: Find Source Material
Check for completed analysis outputs in order of preference:
1. `outputs/slides_*.md` — latest deck
2. `outputs/analysis_*.md` — latest narrative
3. `working/pipeline_summary.md` — pipeline summary
4. `working/storyboard_*.md` — storyboard

If no outputs exist:
- Check `working/` for partial results
- If nothing found: "No analysis results to export. Run an analysis first or use `/run-pipeline`."

### Step 2: Generate Requested Format

**Format: slides**
- If deck already exists, ask: "Deck found at {path}. Regenerate or export as-is?"
- If no deck, invoke Deck Creator agent with latest narrative + charts
- Output: `outputs/slides_{DATE}.md`

**Format: email**
- Structure: Subject line + 3-paragraph body (context, key finding, recommendation)
- Tone: Executive-friendly, no jargon, action-oriented
- Include: 1-2 key numbers, the "so what", and a clear ask
- Output: `outputs/email_summary_{DATE}.md`

**Format: slack**
- Structure: Bold headline + 3-5 bullet points + thread-friendly
- Keep under 300 words
- Use emoji sparingly (checkmarks, arrows only)
- Include: key metric, direction, and recommended action
- Output: `outputs/slack_update_{DATE}.md`

**Format: brief**
- Structure: Title + Executive Summary (3 sentences) + Key Findings (numbered) +
  Recommendation + Next Steps + Appendix (data sources, methodology)
- 1 page target (~500 words)
- Output: `outputs/decision_brief_{DATE}.md`

**Format: data**
- Export all DataFrames from `working/` as CSVs to `outputs/data/`
- Include a README listing each file and its contents
- Output: `outputs/data/` directory

**Format: all**
- Run email + slack + brief + data sequentially
- Skip slides if already exists

### Step 3: Post-Export
- List all exported files with paths
- Suggest: "Copy the email to your clipboard?" or "Want to adjust the tone?"

## Rules
1. Never fabricate findings — only use data from actual analysis outputs
2. Always cite the source analysis date and dataset
3. Adapt detail level to format (email = high-level, brief = medium, data = raw)
4. Apply Stakeholder Communication skill for all text outputs
5. If the analysis had confidence scores, include them in brief format

## Edge Cases
- **Partial analysis:** Export what's available, note gaps: "Note: validation step was not completed."
- **Multiple analyses in outputs/:** Use the most recent by date, or ask user which one
- **Charts missing:** Text formats still work, note: "Charts not available for this export."
- **User requests unknown format:** List available formats and ask to choose

Related Skills

tech-blog

159
from majiayu000/claude-skill-registry

Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.

Content & DocumentationClaude

x-article-publisher

128
from anbeime/skill

Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.

Content & DocumentationClaude

docx

44
from rysweet/amplihack

Create, edit, and analyze Word documents with tracked changes support

Content & DocumentationClaude

info-card-designer

27
from joeseesun/info-card-designer

This skill transforms any text or information into a magazine-quality HTML info card, automatically capturing screenshots for easy sharing on platforms like X (Twitter), WeChat, and Xiaohongshu. It features a distinctive Swiss Internationalism design style and responsive layouts.

Content & DocumentationClaude

ccg

20
from ShunsukeHayashi/Miyabi

The AI Course Content Generator (CCG) creates complete online courses, including structured curricula, lesson scripts, audio, slides, and videos, leveraging the Gemini API for comprehensive content generation.

Content & DocumentationClaude

writing-content

6
from ai-mindset-org/pos-sprint

An interactive content creation skill inspired by the Julian Shapiro framework, featuring research, scoring, and AI-slop detection.

Content & DocumentationClaude

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation

openclaw-youtube

3891
from openclaw/skills

YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking.

Content & Documentation

openclaw-media-gen

3891
from openclaw/skills

Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.

Content & Documentation