agentleFS
AtmoskunAtmoskun/claude-skills/skills/chatgpt-organizer/SKILL.md

chatgpt-organizer

Skill0 starsChanged 9 months agoMITView on GitHub

Parse, categorize, search, and export ChatGPT conversation history to Obsidian. User says /chatgpt-organizer or asks to organize/search/analyze ChatGPT exports. Processes ChatGPT data exports (ZIP files) into an organized, searchable knowledge base: - Parse conversations using iterative back-trace (no RecursionError on deep trees) - Index in SQLite with FTS5 full-text search - Categorize via rule-based keywords + Gemini Flash for ambiguous cases - Summarize conversations using Gemini Flash - Export to Obsidian Vault as organized Markdown with YAML frontmatter IMPORTANT: All…

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    IMPORTANT: All scripts must be run via run.py using the full Python path.

    line 20
  2. Very specific:

    Add --categorize to run rule-based categorization during import:

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ChatGPT Conversation Organizer

Parse, categorize, search, and export ChatGPT conversation history to Obsidian.

Trigger

User says /chatgpt-organizer or asks to organize/search/analyze ChatGPT exports.

What This Skill Does

Processes ChatGPT data exports (ZIP files) into an organized, searchable knowledge base:

  • Parse conversations using iterative back-trace (no RecursionError on deep trees)
  • Index in SQLite with FTS5 full-text search
  • Categorize via rule-based keywords + Gemini Flash for ambiguous cases
  • Summarize conversations using Gemini Flash
  • Export to Obsidian Vault as organized Markdown with YAML frontmatter

Instructions for Claude

IMPORTANT: All scripts must be run via run.py using the full Python path.

PYTHON="python"
SKILL="$HOME/.claude/skills/chatgpt-organizer"

Step 1: Import from ZIP

$PYTHON $SKILL/scripts/run.py import_export --zip <ZIP_PATH>

Add --categorize to run rule-based categorization during import:

$PYTHON $SKILL/scripts/run.py import_export --zip <ZIP_PATH> --categorize

Step 2: Search conversations

$PYTHON $SKILL/scripts/run.py search "keyword"
$PYTHON $SKILL/scripts/run.py search "portfolio" --category investment-research
$PYTHON $SKILL/scripts/run.py search "Apple" --ticker AAPL
$PYTHON $SKILL/scripts/run.py search "code" --model gpt-4 --limit 10

Step 3: View statistics

$PYTHON $SKILL/scripts/run.py stats

Step 4: AI Categorization (requires GEMINI_API_KEY)

# Rule-based only (free)
$PYTHON $SKILL/scripts/run.py categorizer

# Rule-based + Gemini for ambiguous
$PYTHON $SKILL/scripts/run.py categorizer --gemini

# Re-categorize all
$PYTHON $SKILL/scripts/run.py categorizer --recategorize --gemini

Step 5: AI Summaries (requires GEMINI_API_KEY)

# Summarize all unsummarized
$PYTHON $SKILL/scripts/run.py summarize

# Only investment research
$PYTHON $SKILL/scripts/run.py summarize --category investment-research

# First 50 only
$PYTHON $SKILL/scripts/run.py summarize --limit 50

Categories

IDLabelFocus
investment-researchInvestment Research投资, 估值, earnings, thesis
meeting-notesMeeting Notes会议, 纪要, transcript
technical-codingTechnical / Codingpython, API, code, bug
personal-taxPersonal / Taxtax, IRS, 报税, insurance
learningLearningexplain, what is, 概念
writingWritingwrite, draft, 文章, 润色
data-analysisData Analysisanalyze, data, chart, CSV
otherOther(fallback)

Output

  • Obsidian: Documents/Obsidian Vault/ChatGPT/{Category}/YYYY-MM-DD - title.md
  • Database: ~/.claude/skills/chatgpt-organizer/data/chatgpt.db

Framework Tagging (after categorization)

在分类和 ticker 检测之后,自动标注内容属于分析框架的哪些维度:

from shared.framework_tagger import tag_content
sections = tag_content(text, mode="keyword")  # keyword mode for ChatGPT (fast)

将结果添加到 frontmatter extra dict:

framework_sections: [S1, S4.2, S7]

如果 framework_tagger 不可用或返回空列表,跳过(不报错)。

Post-Export

自动执行: 完成所有处理后,立即对输出文件夹执行 link 扫描(等同于 /link ChatGPT/),为新增笔记添加 [[wikilinks]]。 用户说"跳过 link"时跳过此步。

Dependencies

  • orjson, google-generativeai, python-dotenv, pathvalidate
  • Auto-installed in .venv on first run via run.py

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.