windows-npm-run-script-shell
/windows-npm-run-script-shell
Use when Windows npm run, npm test, npm run build, or npm run-script exits before running the script with ERR_INVALID_ARG_TYPE, "file argument must be of type string", missing ComSpec, broken script-shell, stripped CLI flags, sandboxed npm cache/log EPERM, or silent npm script output.
- Author
- JinNing6 ↗
- Repository
- Noosphere ↗
- Licence
- Apache-2.0
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Use when Windows npm run, npm test, npm run build, or npm run-script exits before running the script with ERR_INVALID_ARG_TYPE, "file argument must be of type string", missing ComSpec, broken script-shell, stripped CLI flags, sandboxed npm cache/log EPERM, or silent npm script output.
Triggers from the description
Original author description
Use when Windows npm run, npm test, npm run build, or npm run-script exits before running the script with ERR_INVALID_ARG_TYPE, "file argument must be of type string", missing ComSpec, broken script-shell, stripped CLI flags, sandboxed npm cache/log EPERM, or silent npm script output.
How it works
- Overview
- Triage
- Fix
- Common Mistakes
- Completion Standard
SKILL.md preview
--- name: windows-npm-run-script-shell description: Use when Windows npm run, npm test, npm run build, or npm run-script exits before running the script with ERR_INVALID_ARG_TYPE, "file argument must be of type string", missing ComSpec, broken script-shell, stripped CLI flags, sandboxed npm cache/log EPERM, or silent npm script output. --- # Windows Npm Run Script Shell ## Overview Windows npm scripts need a shell. If `ComSpec` is missing or npm cannot infer a script shell, `npm run ...` can fail inside npm before `tsc`, Vite, Vitest, or Playwright actually runs. ## Triage Use this flow before changing app code: 1. Run the target tool directly with `npx`, for example `npx tsc -b --pretty false`, `npx vite build`, or `npx vitest run`. 2. Run `npm run <script> --loglevel verbose`. 3. Open the npm debug log if output is empty. 4. Check shell config: ```powershell npm config get script-shell npm config get cache npm config get update-notifier Write-Host "ComSpec=[$env:ComSpec]" Write-Host "SHELL=[$env:SHELL]" ``` If direct `npx` commands pass but `npm run` fails with `ERR_INVALID_ARG_TYPE: The "file" argument must be of type string. Received undefined`, treat it as npm shell configuration, not a project build failure. If direct `node <script>` succeeds but `npm test`/`npm run` exits silently in a sandbox, rerun with `--loglevel verbose`. When npm reports `EPERM` creating `%LocalAppData%\npm-cache\_logs` or attempts registry access only for update checks, treat it as npm runtime side effects, not a test failure. ## Fix Prefer a project-local `.npmrc` so the fix travels with the repo: ```ini script-shell=C:\Windows\System32\cmd.exe ``` For sandboxed Windows workspaces where npm cannot write the user cache/log directory, keep npm side effects inside the repo and disable network-prone notices: ```ini cache=.npm-cache update-notifier=false fund=false audit=false script-shell=cmd.exe ``` Then rerun: ```powershell npm run build npm test -- --run ``` If the project requires PowerShell syntax in scripts, set `script-shell` to PowerShell and avoid `&&` in package scripts, because Windows PowerShell 5 does not support `&&`. ## Common Mistakes - Do not rewrite TypeScript, Vite, Vitest, or React code when `npx <tool>` succeeds and only `npm run` fails. - Do not treat silent npm output as proof that the build tool produced no diagnostics; inspect the npm debug log. - Do not ignore npm cache/log `EPERM` in sandboxed workspaces; set a project-local cache before escalating. - Do not set a global npm config unless the user asked for machine-wide changes. - Do not assume `SHELL` replaces `ComSpec` for npm on Windows. ## Completion Standard The issue is fixed only when: - The original `npm run <script>` command succeeds. - The direct tool command still succeeds. - Tests/builds that previously passed via `npx` also pass through npm scripts.
Versions
The database has no other skills named windows-npm-run-script-shell.
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version fff79e512ea0 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 86npm-release-check
Check an npm package before it is released. Use when the user is about to release a package to npm, bump a version, or asks whether a package is ready to ship. Runs one offline script that reads what npm pack would put in the tarball and reports secrets, private files, missing… - 100deploy-npm
Release an npm package: version, CHANGELOG, publish, verify. Use when "publish this package", "release to npm", or "ship a new npm version". Running-app production deploy → workflow-ship-and-observe. - 100setup
Set up the `clickhouse-js` repository in a fresh checkout so the agent can run tests, lints, type checks, builds, or examples. Use this skill before invoking any `npm run test:*`, `npm run lint`, `npm run typecheck`, `npm run build`, or `npm run run-examples` script — or after… - 100npm-publishing
Publishing OCaml to npm via js_of_ocaml and wasm_of_ocaml. Use when discussing browser targets, JavaScript compilation, WASM output, npm packages, or the two-branch workflow. - 100review-shell-scripts
Review all shell scripts against the Bash Script Convention. Use when you need to check script compliance or before committing changes. - 90windows-shell-rules-en
Working rules for Claude Code on Windows - plain ASCII file names, UTF-8 when saving text, quoted paths with spaces, check which shell will run a command (PowerShell vs Git Bash), one task per conversation. Use whenever you create files or folders, save non-English text, or run…