
Proxychains Network Proxy
Routes blocked or timing-out network commands through a local proxy using proxychains4
- Repository
- 2025Emma/vibe-coding-cn
- Stars
- 23,127
- Licence
- MIT
- Files
- 6 files
What it does
When a terminal command like git, pip, npm, curl or docker fails with a timeout, DNS error or blocked-access error, this skill tells the agent to retry the command prefixed with proxychains4, which forces its network connections through a proxy server (default http://127.0.0.1:9910). It also includes a setup script and reference guides that create a proxychains configuration file and explain how to troubleshoot the proxy.
Great for
- Developers whose machine already runs a local proxy and who hit slow or blocked access to GitHub, PyPI, npm or Docker registries
- Users who understand their own network setup and want the agent to retry failed commands through an existing proxy
- Teams standardising proxychains configuration on Linux or macOS development machines
Skip it if
- Users without a proxy service listening on 127.0.0.1:9910 (or another configured port), since every retry will fail and the agent will only report errors
- Situations where routing traffic through a third-party proxy may violate policy, network rules or local law, because the skill makes the agent reroute commands automatically without asking
- Environments handling sensitive credentials or private data, because commands and traffic are sent through a proxy the user may not fully control
Try asking
- “My git clone of a GitHub repo keeps timing out, can you retry it through the proxy?”
- “pip install is failing with connection errors, set up proxychains and try again”
- “Help me configure proxychains to use my local proxy on port 9910”
- “Docker pull hangs on registry access, retry it with the proxy”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 6 original files, the MIT licence and an attribution note.
proxychains.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip proxychains.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip proxychains.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Confirm your proxy is running first (for example with ss -tunlp | grep 9910) before asking the agent to use this skill, so failures are not mistaken for network problems.
- Review the generated ~/.proxychains/proxychains.conf and the setup script before running it, since it writes config files and makes test requests to google.com through the proxy.
- Ask the agent to show each command it will prefix with proxychains4 before it runs, because the skill describes automatic retries and forced routing of many tools.
What's inside
- references/index.md
- references/quick-reference.md
- references/setup-guide.md
- references/troubleshooting.md
- scripts/setup-proxy.sh
- SKILL.md
Redistributed unmodified from 2025Emma/vibe-coding-cn under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.