Install
$ agentstack add skill-brads777-claudeprojectexport-claudeprojectexport ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Claude Export Extractor — Claude Code Skill
Extract projects from a Claude.ai data export ZIP into local directories for use with Claude Code.
What This Skill Does
Claude.ai projects contain knowledge docs, prompt templates, and conversation history. This skill extracts specific projects from an export ZIP into organized local folders so the content can be used as context for Claude Code work.
Output structure per project:
/
project_knowledge/ # Knowledge docs, attachments, prompt template
_project_metadata.json # Project name, UUID, dates, counts
_prompt_template.md # Project custom instructions (if any)
... # All uploaded docs, deduplicated
conversations/ # Related conversation history as markdown
.md ... # One file per conversation
Workflow
Step 1: Locate the ZIP
Ask the user for the path to their Claude.ai export ZIP file. Common locations:
~/Downloads/C:\Downloads\- The user may have already mentioned it
Verify the file exists before proceeding.
Step 2: List projects
Run the extractor in JSON mode to get a machine-readable project list:
PYTHONIOENCODING=utf-8 python ~/.claude/skills/ClaudeProjectExport/claude_export_extractor.py "" --json
This returns a JSON array with each project's name, doc count, conversation count, and size.
Step 3: Present projects to the user
Show the projects in a clean table format. Ask which projects to extract.
Step 4: Get output directories
For each selected project, ask where to save the output. Suggest a sensible default based on the project name and current working directory.
Step 5: Extract
Run the extractor in non-interactive mode:
PYTHONIOENCODING=utf-8 python ~/.claude/skills/ClaudeProjectExport/claude_export_extractor.py "" --extract --output ","
Step 6: Report results
Confirm what was saved: doc count, conversation count, output paths.
Notes
- Conversations are matched to projects by keyword similarity (no UUID link in export format)
- Duplicate docs within a project are automatically deduplicated by filename
PYTHONIOENCODING=utf-8is required on Windows to avoid emoji encoding errors- Pass
allnumbers to--extractfor a full dump
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Brads777
- Source: Brads777/ClaudeProjectExport
- License: MIT
- Homepage: https://toolsiq.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.