by saharmor
Automatically generate high-quality markdown context files for AI coding agents like Claude, Cursor, and Gemini, Powered By DeepWiki
# Add to your Claude Code skills
git clone https://github.com/saharmor/sidekick-dev-webGuides for using ai agents skills like sidekick-dev-web.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:31:23.004Z",
"npmAuditRan": true,
"pipAuditRan": true
}sidekick-dev-web is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by saharmor. Automatically generate high-quality markdown context files for AI coding agents like Claude, Cursor, and Gemini, Powered By DeepWiki. It has 116 GitHub stars.
Yes. sidekick-dev-web passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/saharmor/sidekick-dev-web" and add it to your Claude Code skills directory (see the Installation section above).
sidekick-dev-web is primarily written in TypeScript. It is open-source under saharmor on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh sidekick-dev-web against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automatically generate high-quality markdown context files for AI coding agents like Claude, Cursor, Windsurf, and Gemini by analyzing any public GitHub repository.
https://github.com/user-attachments/assets/aa944e4d-f537-4069-b44a-2894d7233e1c
# Clone and start both frontend and backend
git clone https://github.com/saharmor/sidekick-code-web.git
cd sidekick-code-web
./start-dev.sh
This automatically sets up the Python virtual environment, installs dependencies, and starts:
Frontend (GitHub Pages):
cd frontend
npm run build:prod
# If deploying to GitHub Pages, ensure Vite base is set for subpath
# Site URL will be https://<user>.github.io/sidekick-code-web/
Backend (Render):
cd backend && pip install -r requirements.txtcd backend && uvicorn main:app --host 0.0.0.0 --port $PORTDEBUG=false and CORS_ORIGINSDocker:
cd backend
docker build -t sidekick-dev-api .
docker run -p 8000:8000 sidekick-dev-api
Backend (.env):
DEBUG=false # Enable debug mode and API docs
CORS_ORIGINS=http://localhost:5173 # Allowed frontend origins
DEEPWIKI_TIMEOUT=60 # DeepWiki request timeout seconds
Frontend (.env.local):
VITE_API_URL=https://your-backend.render.com # Custom backend URL
Each markdown file provides comprehensive project context including:
MIT License - see LICENSE file for details.
Built by Sahar Mor • Follow @theaievangelist • Stay updated on AI