Menu
Choose Windows native vs WSL2 for agent shell work. Backend Python/GPU, pytest, and Unix-path MCP in WSL2; gh and light search on Windows. Use when picking where to run installs, tests, or MCP servers.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.
Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.
Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.
Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.
Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.
Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.
| name | agent-platform-tooling |
| description | Choose Windows native vs WSL2 for agent shell work. Backend Python/GPU, pytest, and Unix-path MCP in WSL2; gh and light search on Windows. Use when picking where to run installs, tests, or MCP servers. |
Windows host vs WSL2 Ubuntu for coding agents in image-scoring-backend and sibling gallery workspace.
Pick the right environment before installing tools or running long jobs. Reduces path, performance, and line-ending issues.
Platform-specific — see windows-wsl-split.md and install-blocks.md.
Cross-links: wsl-environment, wsl-tf-python-runner
gh pr list --limit 10
rg "pattern" modules/ -n --max-count 30
cd ~/src/image-scoring-backend # or /mnt/d/Projects/image-scoring-backend
source ~/.venvs/tf/bin/activate
python scripts/doctor.py --no-gpu
bash ./scripts/wsl/run_wsl_tests.sh
See windows-wsl-split.md for the full split diagram.
gh issue/PR operationsrg / fd on D:\Projects\...modules.*-m wsl, GPU, DB, ML markers)scripts/wsl/~/src for heavy I/O; use /mnt/d/Projects when sharing with Windows IDE.LD_LIBRARY_PATH for Firebird when DB/Firebird FFI involved — see wsl-tf-python-runner.wsl --unregister or distro reset/mnt/c: clone to ~/src/image-scoring-backend.Windows:
Get-Command gh, rg, git
WSL:
python3 --version; source ~/.venvs/tf/bin/activate && python --version; which rg fd git