From Nushell Fluency
Audit a provided Nushell pipeline. Executes `nu-lint` for diagnostics if available, otherwise uses an experimental agent as fallback.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nu-fluency:audit-pipelinepipelineThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
```!
echo 'resolving nu-lint installation'
which nu-lint ||
wsl.exe --exec which nu-lint ||
echo 'nu-lint is not installed'
The pipeline to review: $pipeline
Determine if nu-lint is installed using the environment output.
If nu-lint is available:
Write the pipeline to a temp .nu file and run the linter:
let cfg = `${CLAUDE_PLUGIN_ROOT}` | path join configs strict.nu-lint.toml
let tmp = mktemp --suffix .nu
'$pipeline' | save --force $tmp
nu-lint --format compact -c $cfg $tmp
Render the diagnostics directly, one per line, with line/column references.
nu-lint --explain <rule> output as the "why"Use the generate-diagnostics Task agent as a fallback diagnostics generator.
Prepend a one-line caveat to your output indicating the diminished integrity.
Report your findings in a neat, organized fashion.
Never apply rewrites automatically; the user decides what to take.
npx claudepluginhub zaynram/nu-fluency --plugin nu-fluencyCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.