windows-claude-code-doctor
by Ilia Malkin
Diagnose and fix Windows-specific AI coding agent failures across shells, paths, WSL, locks, ports, and CRLF diffs.
- Fix Linux command leakage in PowerShell or cmd.exe sessions.
- Translate paths between WSL and native Windows to fix broken tool calls.
- Resolve database and file locks (EADDRINUSE/EBUSY) on Windows.
$5
· or 25 creditsSecure checkout via Stripe
Included in download
- Fix Linux command leakage in PowerShell or cmd.exe sessions.
- Translate paths between WSL and native Windows to fix broken tool calls.
- terminal, file_write, env_vars automation included
- Ready for Git Bash
Sample input
My AI coding agent is running on Windows PowerShell and keeps failing commands like rm -rf node_modules && npm install. It also says port 3000 is already in use. Diagnose the environment and give me the safest fix.
Sample output
Environment: Windows-native PowerShell Failure class: Linux command leakage + port conflict
Evidence:
- diagnose-shell.ps1 detected PowerShell, not Bash.
- The command uses Bash-style rm -rf and shell chaining assumptions.
- find-port-holder.ps1 -Port 3000 identified the owning PID and process name.
Fix:
- Replace rm -rf node_modules with: Remove-Item -LiteralPath .\node_modules -Recurse -Force
- Run npm install only after the delete succeeds.
- Stop the identified dev server process gracefully before restarting.
Verification:
- Re-run find-port-holder.ps1 -Port 3000.
- Re-run the install through: invoke-native.ps1 -- npm install
windows-claude-code-doctor
by Ilia Malkin
Diagnose and fix Windows-specific AI coding agent failures across shells, paths, WSL, locks, ports, and CRLF diffs.
$5
· or 25 creditsSecure checkout via Stripe
Included in download
- Fix Linux command leakage in PowerShell or cmd.exe sessions.
- Translate paths between WSL and native Windows to fix broken tool calls.
- terminal, file_write, env_vars automation included
- Ready for Git Bash
- Instant install
Sample input
My AI coding agent is running on Windows PowerShell and keeps failing commands like rm -rf node_modules && npm install. It also says port 3000 is already in use. Diagnose the environment and give me the safest fix.
Sample output
Environment: Windows-native PowerShell Failure class: Linux command leakage + port conflict
Evidence:
- diagnose-shell.ps1 detected PowerShell, not Bash.
- The command uses Bash-style rm -rf and shell chaining assumptions.
- find-port-holder.ps1 -Port 3000 identified the owning PID and process name.
Fix:
- Replace rm -rf node_modules with: Remove-Item -LiteralPath .\node_modules -Recurse -Force
- Run npm install only after the delete succeeds.
- Stop the identified dev server process gracefully before restarting.
Verification:
- Re-run find-port-holder.ps1 -Port 3000.
- Re-run the install through: invoke-native.ps1 -- npm install
About This Skill
Windows Claude Code Doctor helps AI coding agents recover from the Windows-specific failures that break real development loops: Bash commands leaking into PowerShell, broken Windows/WSL/Git Bash path translation, WSL vs native runtime confusion, lost PowerShell exit codes, CRLF diff explosions, SQLite lock loops, busy ports, and EBUSY/EPERM file locks. It is built for Claude Code, Codex CLI, Cursor, OpenClaw, VS Code agents, Gemini CLI, and other SKILL.md-compatible coding agents. The skill gives agents a practical triage workflow, seven focused troubleshooting playbooks, reusable PowerShell diagnostics, and reference notes for the most common Windows agent failure modes. Buy this if you run AI coding agents on Windows or WSL and want them to stop guessing, stop retrying broken Linux commands, and produce evidence-backed fixes with clear verification steps.
Use Cases
- Fix Linux command leakage in PowerShell or cmd.exe sessions.
- Translate paths between WSL and native Windows to fix broken tool calls.
- Resolve database and file locks (EADDRINUSE/EBUSY) on Windows.
- Normalize line endings to prevent CRLF pollution in git diffs.
- Capture correct exit codes from native Windows commands in terminal agents.
Known Limitations
Designed for Windows, WSL, Git Bash/MSYS2, PowerShell, and cmd.exe workflows. The bundled diagnostics are PowerShell scripts, so non-Windows agents should use the conceptual playbooks unless they can call powershell.exe. Exact file-handle ownership requires Sysinternals handle.exe; without it, the skill reports likely locking processes instead. It does not automatically kill processes, change Git global config, edit Defender settings, or make machine-wide policy changes.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/windows-claude-code-doctor -o /tmp/windows-claude-code-doctor.zip && unzip -o /tmp/windows-claude-code-doctor.zip -d ~/.claude/skills && rm /tmp/windows-claude-code-doctor.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
File Scopes
orks with any SKILL.md-compatible coding agent. Diagnostic scripts require Windows PowerShell 5.1+ or PowerShell 7+. Best for Windows, Git Bash/MSYS2, and WSL development environments.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
Multi-Agent Orchestration Master Library
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
ai-automation-qa-pack
Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.